JP7027046B2 - Medical image imaging device and method - Google Patents

Description

Embodiments of the present invention relate to medical image imaging devices and methods.

Conventionally, in an examination using an X-ray CT device (CT; Computed Tomography), a computer-aided diagnosis (CAD) that detects a lesion site by using a predetermined assisted diagnostic algorithm for a reconstructed image of a subject is used. ) Processing may be executed. In such a case, the image interpreting doctor refers to the CAD processing result and interprets the reconstructed image.

Japanese Unexamined Patent Publication No. 2008-012171 Japanese Unexamined Patent Publication No. 2008-011905

An object to be solved by the present invention is to provide a medical image imaging device and a method capable of optimizing the imaging conditions of the present scan with reference to the processing result of the assistive diagnosis.

The medical image imaging device of the embodiment includes an image generation unit, a detection unit, a diagnosis support processing unit, a setting unit, and an imaging control unit. The image generation unit generates image data of the subject. The detection unit detects each of a plurality of parts of the subject in the image data generated as a positioning image. The diagnosis support processing unit executes the diagnosis support processing corresponding to the predetermined portion of the image data in the region corresponding to the predetermined portion of the subject detected by the detection unit. The setting unit sets the imaging conditions for this scan for the site where the lesion site is specified among the plurality of sites as the processing result of the diagnosis support processing unit. Based on the imaging conditions, the imaging control unit controls the imaging mechanism so as to perform imaging on the imaging region including the region where the lesion site is specified.

FIG. 1 is a diagram showing an example of a configuration of a medical information processing system according to the first embodiment. FIG. 2 is a diagram showing an example of the configuration of the X-ray CT apparatus according to the first embodiment. FIG. 3 is a diagram for explaining three-dimensional scanno image capture by the scan control circuit according to the first embodiment. FIG. 4A is a diagram for explaining an example of a portion detection process by the detection function according to the first embodiment. FIG. 4B is a diagram for explaining an example of a portion detection process by the detection function according to the first embodiment. FIG. 5 is a diagram for explaining an example of a portion detection process by the detection function according to the first embodiment. FIG. 6 is a diagram for explaining an example of a portion detection process by the detection function according to the first embodiment. FIG. 7 is a diagram showing an example of a virtual patient image stored by the storage circuit according to the first embodiment. FIG. 8 is a diagram for explaining an example of collation processing by the position collation function according to the first embodiment. FIG. 9 is a diagram showing an example of conversion of a scan range by coordinate conversion according to the first embodiment. FIG. 10 is a diagram (1) for explaining the first embodiment. FIG. 11 is a diagram (2) for explaining the first embodiment. FIG. 12 is a flowchart showing a processing procedure by the X-ray CT apparatus according to the first embodiment. FIG. 13 is a diagram (1) for explaining the second embodiment. FIG. 14 is a diagram (2) for explaining the second embodiment. FIG. 15 is a flowchart showing a processing procedure by the X-ray CT apparatus according to another embodiment.

Hereinafter, embodiments of the medical image imaging apparatus and method will be described in detail with reference to the accompanying drawings. Hereinafter, a medical information processing system including an X-ray CT (Computed Tomography) device will be described as an example. In the medical information processing system 100 shown in FIG. 1, only one server device and one terminal device are shown, but in reality, a plurality of server devices and terminal devices can be further included. Further, the medical information processing system 100 can also include, for example, a medical image diagnostic device such as an X-ray diagnostic device, an MRI (Magnetic Resonance Imaging) device, and an ultrasonic diagnostic device.

(First Embodiment)
FIG. 1 is a diagram showing an example of the configuration of the medical information processing system 100 according to the first embodiment. As shown in FIG. 1, the medical information processing system 100 according to the first embodiment includes an X-ray CT device 1, a server device 2, and a terminal device 3. The X-ray CT device 1, the server device 2, and the terminal device 3 can communicate with each other directly or indirectly by, for example, an in-hospital LAN (Local Area Network) installed in the hospital. ing. For example, when PACS (Picture Archiving and Communication System) is introduced in the medical information processing system 100, each device is DICOM (Digital Imaging and Communications in).
Medicine) Send and receive medical images, etc. to and from each other in accordance with the standard.

Further, in the medical information processing system 100, for example, HIS (Hospital Information System), RIS (Radiology Information System), and the like are introduced to manage various information. For example, the terminal device 3 transmits the inspection order created according to the above system to the X-ray CT device 1 and the server device 2. The X-ray CT device 1 acquires patient information from a patient list (modality work list) for each modality created by a test order directly received from the terminal device 3 or a server device 2 that receives the test order, and the patient. Collect X-ray CT image data for each. Then, the X-ray CT apparatus 1 transmits the collected X-ray CT image data and the image data generated by performing various image processing on the X-ray CT image data to the server apparatus 2. The server device 2 stores the X-ray CT image data and the image data received from the X-ray CT device 1, generates image data from the X-ray CT image data, and receives an image in response to an acquisition request from the terminal device 3. The data is transmitted to the terminal device 3. The terminal device 3 displays the image data received from the server device 2 on a monitor or the like. Hereinafter, each device will be described.

The terminal device 3 is a device arranged in each clinical department in the hospital and operated by a doctor working in each clinical department, such as a PC (Personal Computer), a tablet PC, a PDA (Personal Digital Assistant), and a mobile phone. Is. For example, in the terminal device 3, a medical record information such as a patient's symptom and a doctor's finding is input by a doctor. Further, the terminal device 3 inputs an inspection order for ordering the inspection by the X-ray CT device 1, and transmits the input inspection order to the X-ray CT device 1 and the server device 2. That is, the doctor in the clinical department operates the terminal device 3 to read the reception information of the visiting patient and the information of the electronic medical record, examine the corresponding patient, and input the medical record information into the read electronic medical record. Then, the doctor in the clinical department operates the terminal device 3 to transmit the test order according to the necessity of the test by the X-ray CT device 1.

The server device 2 stores medical images collected by the medical image diagnostic device (for example, X-ray CT image data and image data collected by the X-ray CT device 1), and performs various image processing on the medical image. It is a device for performing, for example, a PACS server. For example, the server device 2 receives a plurality of examination orders from the terminal device 3 arranged in each clinical department, creates a patient list for each medical diagnostic imaging device, and creates the created patient list for each medical diagnostic imaging device. Send to. As an example, the server device 2 receives an examination order for performing an examination by the X-ray CT apparatus 1 from the terminal apparatus 3 of each clinical department, creates a patient list, and X-rays the created patient list. It is transmitted to the CT device 1. Then, the server device 2 stores the X-ray CT image data and the image data collected by the X-ray CT device 1, and in response to the acquisition request from the terminal device 3, the X-ray CT image data and the image data are stored in the terminal device. Send to 3.

The X-ray CT apparatus 1 collects X-ray CT image data for each patient, and uses the collected X-ray CT image data and image data generated by performing various image processing on the X-ray CT image data as a server. It is transmitted to the device 2. FIG. 2 is a diagram showing an example of the configuration of the X-ray CT apparatus 1 according to the first embodiment. As shown in FIG. 2, the X-ray CT apparatus 1 according to the first embodiment has a gantry 10, a sleeper apparatus 20, and a console 30.

The gantry 10 is a device that irradiates the subject P (patient) with X-rays, detects the X-rays transmitted through the subject P, and outputs the X-rays to the console 30, the X-ray irradiation control circuit 11 and the X-ray generation. It has a device 12, a detector 13, a data acquisition circuit (DAS: Data Acquisition System) 14, a rotating frame 15, and a gantry drive circuit 16. The data acquisition circuit 14 is an example of an acquisition unit.

The rotating frame 15 supports the X-ray generator 12 and the detector 13 so as to face each other with the subject P interposed therebetween, and rotates at high speed in a circular orbit centered on the subject P by a gantry drive circuit 16 described later. It is an annular frame.

The X-ray irradiation control circuit 11 is a device that supplies a high voltage to the X-ray tube 12a as a high voltage generating unit, and the X-ray tube 12a uses the high voltage supplied from the X-ray irradiation control circuit 11 to X-ray. Generate a line. The X-ray irradiation control circuit 11 adjusts the X-ray dose irradiated to the subject P by adjusting the tube voltage and the tube current supplied to the X-ray tube 12a under the control of the scan control circuit 33 described later. ..

Further, the X-ray irradiation control circuit 11 switches the wedge 12b. Further, the X-ray irradiation control circuit 11 adjusts the X-ray irradiation range (fan angle and cone angle) by adjusting the opening degree of the collimator 12c. In this embodiment, the operator may manually switch between a plurality of types of wedges.

The X-ray generator 12 is a device that generates X-rays and irradiates the subject P with the generated X-rays, and has an X-ray tube 12a, a wedge 12b, and a collimator 12c.

The X-ray tube 12a is a vacuum tube that irradiates the subject P with an X-ray beam by a high voltage supplied by a high voltage generator (not shown), and the X-ray beam is sent to the subject P as the rotating frame 15 rotates. Irradiate against. The X-ray tube 12a generates an X-ray beam that spreads with a fan angle and a cone angle. For example, under the control of the X-ray irradiation control circuit 11, the X-ray tube 12a is continuously exposed to X-rays around the entire circumference of the subject P for full reconstruction, or is exposed to half reconstruction for half reconstruction. It is possible to continuously expose X-rays within the range (180 degrees + fan angle). Further, under the control of the X-ray irradiation control circuit 11, the X-ray tube 12a can intermittently emit X-rays (pulse X-rays) at a preset position (tube position). The X-ray irradiation control circuit 11 can also modulate the intensity of X-rays exposed from the X-ray tube 12a. For example, the X-ray irradiation control circuit 11 increases the intensity of X-rays emitted from the X-ray tube 12a at a specific tube position, and exposes the X-ray tube 12a in a range other than the specific tube position. Decreases the intensity of the emitted X-rays.

The wedge 12b is an X-ray filter for adjusting the X-ray dose of X-rays exposed from the X-ray tube 12a. Specifically, the wedge 12b transmits the X-rays exposed from the X-ray tube 12a so that the X-rays radiated from the X-ray tube 12a to the subject P have a predetermined distribution. It is a filter that attenuates. For example, the wedge 12b is a filter obtained by processing aluminum so as to have a predetermined target angle and a predetermined thickness. The wedge is also called a wedge filter or a bow-tie filter.

The collimator 12c is a slit for narrowing down the irradiation range of X-rays whose X-ray dose is adjusted by the wedge 12b under the control of the X-ray irradiation control circuit 11 described later.

The gantry drive circuit 16 rotates the rotating frame 15 to rotate the X-ray generator 12 and the detector 13 on a circular orbit centered on the subject P.

The detector 13 is a two-dimensional array type detector (surface detector) that detects X-rays transmitted through the subject P, and the detection element sequence formed by arranging X-ray detection elements for a plurality of channels is the subject P. A plurality of rows are arranged along the body axis direction (Z-axis direction shown in FIG. 2). Specifically, the detector 13 in the first embodiment has X-ray detection elements arranged in multiple rows such as 320 rows along the body axis direction of the subject P, for example, the lungs of the subject P. It is possible to detect X-rays that have passed through the subject P over a wide range, such as the area including the heart and the heart.

The data acquisition circuit 14 is a DAS and collects projection data from the X-ray detection data detected by the detector 13. For example, the data acquisition circuit 14 generates projection data by performing amplification processing, A / D conversion processing, sensitivity correction processing between channels, etc. on the X-ray intensity distribution data detected by the detector 13. The projected projection data is transmitted to the console 30 described later. For example, when X-rays are continuously exposed from the X-ray tube 12a during the rotation of the rotating frame 15, the data acquisition circuit 14 collects the projection data group for the entire circumference (360 degrees). Further, the data acquisition circuit 14 associates the tube position with each of the collected projection data and transmits the data to the console 30 described later. The tube position is information indicating the projection direction of the projection data. The sensitivity correction process between channels may be performed by the preprocessing circuit 34, which will be described later.

The sleeper device 20 is a device on which the subject P is placed, and has a sleeper drive device 21 and a top plate 22 as shown in FIG. The sleeper drive device 21 moves the top plate 22 in the Z-axis direction to move the subject P into the rotating frame 15. The top plate 22 is a plate on which the subject P is placed.

The gantry 10 executes, for example, a helical scan in which the rotating frame 15 is rotated while the top plate 22 is moved to spirally scan the subject P. Alternatively, the gantry 10 executes a conventional scan in which the rotating frame 15 is rotated while the position of the subject P is fixed after the top plate 22 is moved to scan the subject P in a circular orbit. Alternatively, the gantry 10 executes a step-and-shoot method in which the position of the top plate 22 is moved at regular intervals to perform conventional scanning in a plurality of scan areas.

The console 30 is a device that accepts the operation of the X-ray CT device by the operator and reconstructs the X-ray CT image data using the projection data collected by the gantry 10. As shown in FIG. 2, the console 30 has an input circuit 31, a display 32, a scan control circuit 33, a preprocessing circuit 34, a storage circuit 35, an image reconstruction circuit 36, and a processing circuit 37. .. The scan control circuit 33 is an example of an image pickup control unit, and the preprocessing circuit 34 and the image reconstruction circuit 36 are an example of an acquisition unit.

The input circuit 31 has a mouse, keyboard, trackball, switch, button, joystick, etc. used by the operator of the X-ray CT device 1 to input various instructions and settings, and information on the instructions and settings received from the operator. Is transferred to the processing circuit 37. For example, the input circuit 31 receives from the operator the shooting conditions for the X-ray CT image data, the reconstruction conditions for reconstructing the X-ray CT image data, the image processing conditions for the X-ray CT image data, and the like. Further, the input circuit 31 accepts an operation for selecting a test for the subject. Further, the input circuit 31 accepts a designation operation for designating a portion on the image.

The display 32 is a monitor referenced by the operator, and under the control of the processing circuit 37, displays the image data generated from the X-ray CT image data to the operator, or displays the image data to the operator via the input circuit 31. GUI (Graphical) for accepting various instructions and settings from
User Interface) is displayed. In addition, the display 32 displays a plan screen for a scan plan, a screen during scanning, and the like. Further, the display 32 displays a virtual patient image including exposure information, image data, and the like. The virtual patient image displayed by the display 32 will be described in detail later.

The scan control circuit 33 controls the collection process of projection data on the gantry 10 by controlling the image pickup mechanism. Here, the image pickup mechanism includes, for example, an X-ray irradiation control circuit 11, a gantry drive circuit 16, a data acquisition circuit 14, and a sleeper drive device 21. That is, the scan control circuit 33 controls the operations of the X-ray irradiation control circuit 11, the gantry drive circuit 16, the data acquisition circuit 14, and the sleeper drive device 21 under the control of the processing circuit 37, thereby projecting on the gantry 10. Controls the data collection process. Specifically, the scan control circuit 33 controls the collection process of projection data in the imaging in which the positioning image (scano image) is collected and the main imaging (scan) in which the image used for diagnosis is collected. Here, in the X-ray CT apparatus 1 according to the first embodiment, a two-dimensional scanno image and a three-dimensional scanno image can be taken.

For example, the scan control circuit 33 fixes the X-ray tube 12a at a position of 0 degrees (a position in the front direction with respect to the subject P), and continuously shoots while moving the top plate at a constant speed. Take a two-dimensional scano image. Alternatively, the scan control circuit 33 fixes the X-ray tube 12a at a position of 0 degrees, and while moving the top plate intermittently, the scan control circuit 33 intermittently repeats shooting in synchronization with the movement of the top plate to form a two-dimensional image. Take a scanno image. Here, the scan control circuit 33 can capture a positioning image not only from the front direction with respect to the subject but also from an arbitrary direction (for example, a side surface direction).

Further, the scan control circuit 33 captures a three-dimensional scanno image by collecting projection data for the entire circumference of the subject when capturing the scanno image. FIG. 3 is a diagram for explaining three-dimensional scanno image capture by the scan control circuit 33 according to the first embodiment. For example, as shown in FIG. 3, the scan control circuit 33 collects projection data for the entire circumference of the subject by helical scan or non-helical scan. Here, the scan control circuit 33 executes a helical scan or a non-helical scan on a wide area such as the entire chest, abdomen, upper body, and whole body of the subject at a lower dose than the main imaging. As the non-helical scan, for example, the above-mentioned step-and-shoot method scan is executed.

In this way, the scan control circuit 33 collects the projection data for the entire circumference of the subject, and the image reconstruction circuit 36 described later reconstructs the three-dimensional X-ray CT image data (volume data). As shown in FIG. 3, it becomes possible to generate a positioning image from an arbitrary direction using the reconstructed volume data. Here, whether to shoot the positioning image in two dimensions or three dimensions may be arbitrarily set by the operator, or may be set in advance according to the inspection content.

Returning to FIG. 2, the preprocessing circuit 34 performs logarithmic transformation processing and correction processing such as offset correction, sensitivity correction, and beam hardening correction on the projection data generated by the data acquisition circuit 14. Generate corrected projection data. Specifically, the preprocessing circuit 34 generates corrected projection data for each of the projection data of the positioning image generated by the data acquisition circuit 14 and the projection data collected by the main shooting, and the storage circuit 35. Store in.

The storage circuit 35 stores the projection data generated by the preprocessing circuit 34. Specifically, the storage circuit 35 stores the projection data of the positioning image generated by the preprocessing circuit 34 and the projection data for diagnosis collected by the main imaging. Further, the storage circuit 35 stores image data and a virtual patient image generated by the image reconstruction circuit 36 described later. Further, the storage circuit 35 appropriately stores the processing result by the processing circuit 37 described later. The virtual patient image and the processing result by the processing circuit 37 will be described later.

The image reconstruction circuit 36 reconstructs the X-ray CT image data using the projection data stored in the storage circuit 35. Specifically, the image reconstruction circuit 36 reconstructs X-ray CT image data from the projection data of the positioning image and the projection data of the image used for diagnosis. Here, there are various reconstruction methods, and examples thereof include back projection processing. Further, as the back projection process, for example, a back projection process by the FBP (Filtered Back Projection) method can be mentioned. Alternatively, the image reconstruction circuit 36 can reconstruct the X-ray CT image data by using the successive approximation method.

Further, the image reconstruction circuit 36 generates image data by performing various image processing on the X-ray CT image data. Then, the image reconstruction circuit 36 stores the reconstructed X-ray CT image data and the image data generated by various image processes in the storage circuit 35.

The processing circuit 37 controls the operation of the gantry 10, the sleeper device 20, and the console 30 to control the entire X-ray CT device 1. Specifically, the processing circuit 37 controls the CT scan performed on the gantry 10 by controlling the scan control circuit 33. Further, the processing circuit 37 controls the image reconstruction processing and the image generation processing in the console 30 by controlling the image reconstruction circuit 36. Further, the processing circuit 37 controls the display 32 to display various image data stored in the storage circuit 35.

Further, as shown in FIG. 2, the processing circuit 37 executes the detection function 37a, the position collation function 37b, and the support diagnosis function 37c. Here, for example, each processing function executed by the detection function 37a, the position collation function 37b, and the support diagnosis function 37c, which are the components of the processing circuit 37 shown in FIG. 2, is a storage circuit in the form of a program that can be executed by a computer. It is recorded in 35. The processing circuit 37 is a processor that realizes a function corresponding to each program by reading each program from the storage circuit 35 and executing the program. In other words, the processing circuit 37 in the state where each program is read has each function shown in the processing circuit 37 of FIG. The detection function 37a is an example of a detection unit, and the support diagnosis function 37c is an example of a diagnosis support processing unit and a setting unit.

The detection function 37a detects a plurality of sites in the subject P included in the three-dimensional image data. Specifically, the detection function 37a detects a site such as an organ included in the three-dimensional X-ray CT image data (volume data) reconstructed by the image reconstruction circuit 36. For example, the detection function 37a detects a site such as an organ based on an anatomical landmark on at least one of the volume data of the positioning image and the volume data of the image used for diagnosis. Here, the anatomical feature point is a point showing the feature of a specific part such as a bone, an organ, a blood vessel, a nerve, or a lumen. That is, the detection function 37a detects bones, organs, blood vessels, nerves, lumens, etc. included in the volume data by detecting anatomical feature points such as specific organs and bones. Further, the detection function 37a has a detection function 37a.
By detecting the characteristic feature points of the human body, it is possible to detect the positions of the head, neck, chest, abdomen, legs, etc. included in the volume data. The site described in this embodiment means a bone, an organ, a blood vessel, a nerve, a lumen, or the like including these positions. Hereinafter, an example of detecting a site by the detection function 37a will be described. The "site detection process" executed by the detection function 37a is also referred to as "AL analysis".

For example, the detection function 37a extracts anatomical feature points from the voxel values included in the volume data in the volume data of the positioning image or the volume data of the image used for diagnosis. Then, the detection function 37a compares the three-dimensional position of the anatomical feature point in the information such as a textbook with the position of the feature point extracted from the volume data, so that the feature point extracted from the volume data can be compared. Inaccurate feature points are removed from the inside to optimize the position of the feature points extracted from the volume data. As a result, the detection function 37a detects each part of the subject P included in the volume data. As an example, the detection function 37a first extracts anatomical feature points included in the volume data by using a supervised machine learning algorithm. Here, the above-mentioned supervised machine learning algorithm is constructed by using a plurality of supervised images in which correct anatomical feature points are manually arranged, and is used by, for example, a decision forest. Will be done.

Then, the detection function 37a optimizes the extracted feature points by comparing the model showing the three-dimensional positional relationship of the anatomical feature points in the body with the extracted feature points. Here, the above-mentioned model is constructed by using the above-mentioned teacher image, and for example, a point distribution model or the like is used. That is, the detection function 37a is a model in which the shape and positional relationship of the part, points unique to the part, etc. are defined based on a plurality of teacher images in which correct anatomical feature points are manually arranged, and the extracted features. By comparing with the points, inaccurate feature points are removed and the feature points are optimized.

Hereinafter, an example of the site detection process by the detection function 37a will be described with reference to FIGS. 4A, 4B, 5 and 6. 4A, 4B, 5 and 6 are diagrams for explaining an example of a portion detection process by the detection function 37a according to the first embodiment. In FIGS. 4A and 4B, the feature points are arranged two-dimensionally, but in reality, the feature points are arranged three-dimensionally. For example, the detection function 37a applies a supervised machine learning algorithm to the volume data to extract voxels regarded as anatomical feature points as shown in FIG. 4A (black dots in the figure). Then, the detection function 37a fits the position of the extracted voxel to the model in which the shape and positional relationship of the part, the point peculiar to the part, etc. are defined, and as shown in FIG. 4B, among the extracted voxels. Inaccurate feature points are removed and only voxels corresponding to more accurate feature points are extracted.

Here, the detection function 37a assigns an identification code for identifying the feature points indicating the features of each part to the extracted feature points (voxels), and the identification code and the position (coordinate) information of each feature point. The information associated with and is attached to the image data and stored in the storage circuit 35. For example, as shown in FIG. 4B, the detection function 37a assigns identification codes such as C1, C2, and C3 to the extracted feature points (voxels). Here, the detection function 37a attaches an identification code to each of the data for which the detection process has been performed, and stores the data in the storage circuit 35. Specifically, the detection function 37a is performed from at least one projection data of the projection data of the positioning image, the projection data collected under non-contrast, and the projection data collected in the state of being imaged by the contrast medium. The site of the subject contained in the reconstructed volume data is detected.

For example, as shown in FIG. 5, the detection function 37a attaches information associated with the coordinates of each voxel detected from the volume data (positioning in the figure) of the positioning image to the volume data to the storage circuit 35. Store in. As an example, the detection function 37a extracts the coordinates of the marking point from the volume data of the positioning image, and as shown in FIG. 5, "identification code: C1, coordinates (x ₁ , y ₁ , z ₁ )". , "Identification code: C2, coordinates (x ₂ , y ₂ ,,
z ₂ ) ”etc. are stored in association with the volume data. Thereby, the detection function 37a can identify what kind of feature point is in which position in the volume data of the positioning image, and can detect each part such as an organ based on this information.

Further, as shown in FIG. 5, for example, the detection function 37a attaches information in which an identification code is associated with the coordinates of each voxel detected from the volume data (scan in the figure) of the diagnostic image to the volume data. And store it in the storage circuit 35. Here, the detection function 37a is labeled from the volume data imaged by the contrast medium (contrast-enhanced Phase in the figure) and the volume data not imaged by the contrast medium (non-contrast-enhanced Phase in the figure) in the scan. The coordinates of the points can be extracted and the identification code can be associated with the extracted coordinates.

As an example, the detection function 37a extracts the coordinates of the marking point from the volume data of the non-contrast Phase from the volume data of the image for diagnosis, and as shown in FIG. 5, "identification code: C1, coordinates. ( _X'1 , _y'1 , _z'1 ) "," Identification code: C2, coordinates ( _x'2 ,
"_y'2 , _z'2 )" etc. are stored in association with the volume data. In addition, the detection function 3
In 7a, the coordinates of the marking point are extracted from the volume data of the contrast phase from the volume data of the image for diagnosis, and as shown in FIG. 5, "identification code: C1, coordinates ( _x'1 , _y'1 ". , Z'1) ”,“ identification code: _C2 , coordinates (x ′ ₂ , y ′ ₂ , z ′ ₂ ) ”, etc. are stored in association with the volume data. Here, when the labeled points are extracted from the volume data of the contrast-enhanced Phase, the labeled points that can be extracted by being contrast-enhanced are included. For example, the detection function 37a can extract a blood vessel or the like imaged by a contrast agent when extracting a labeled point from the volume data of the contrast medium. Therefore, in the case of the volume data of the contrast-enhanced Phase, as shown in FIG. 5, the detection function 37a has the coordinates ( _x'31 , _y'31 , _z'31 ) of the marker points such as blood vessels extracted by the contrast. Identification codes C31, C32, C33, _C34 , etc. for identifying each blood vessel are associated with the coordinates ( _x'34 , _y'34 , z'34) and the like.

As described above, the detection function 37a can identify what kind of marker point is in which position in the volume data of the positioning image or the diagnostic image, and based on this information, the organ or the like can be identified. Each site can be detected. For example, the detection function 37a detects the position of the target site by using the information of the anatomical positional relationship between the target site to be detected and the site around the target site. As an example, when the target site is the "lung", the detection function 37a acquires the coordinate information associated with the identification code indicating the characteristics of the lung, and also obtains the "ribs", "clavicle", and "heart". , Acquires coordinate information associated with an identification code indicating a site around the "lung" such as the "diaphragm". Then, the detection function 37a extracts the region of the "lung" in the volume data by using the information of the anatomical positional relationship between the "lung" and the surrounding portion and the acquired coordinate information.

For example, the detection function 37a is based on positional relationship information such as "lung apex: 2 to 3 cm above the clavicle" and "lung lower end: height of the 7th rib" and coordinate information of each part. As shown in, the region R1 corresponding to the “lung” in the volume data is extracted. That is, the detection function 37a extracts the coordinate information of the voxel of the region R1 in the volume data. The detection function 37a associates the extracted coordinate information with the part information, attaches it to the volume data, and stores it in the storage circuit 35. Similarly, as shown in FIG. 6, the detection function 37a can extract a region R2 or the like corresponding to the “heart” in the volume data.

Further, the detection function 37a detects a position included in the volume data based on a feature point that defines a position of the head, chest, or the like in the human body. Here, the positions of the head, chest, etc. in the human body can be arbitrarily defined. For example, if the area from the 7th cervical vertebra to the lower end of the lung is defined as the chest, the detection function 37a detects from the feature point corresponding to the 7th cervical vertebra to the feature point corresponding to the lower end of the lung as the chest. The detection function 37a can detect the site by various methods other than the method using the above-mentioned anatomical feature points. For example, the detection function 37a can detect a portion included in the volume data by a region expansion method based on a voxel value or the like.

The position collation function 37b collates the positions of the plurality of parts in the subject included in the three-dimensional image data with the positions of the plurality of parts in the human body included in the virtual patient data. Here, the virtual patient data is information representing the standard position of each of a plurality of parts in the human body. That is, the position collation function 37b collates the site of the subject with the position of the standard site, and stores the collation result in the storage circuit 35. For example, the position collation function 37b matches a virtual patient image in which a part of the human body is arranged at a standard position with a volume data of a subject.

Here, first, a virtual patient image will be described. The virtual patient image is an image actually taken by X-ray of a human body having a standard physique according to multiple combinations of parameters related to physique such as age, adult / child, male / female, weight, height, etc. It is generated in advance and stored in the storage circuit 35. That is, the storage circuit 35 stores data of a plurality of virtual patient images according to the combination of the above-mentioned parameters. Here, anatomical feature points (feature points) are associated with and stored in the virtual patient image stored by the storage circuit 35. For example, the human body has a large number of anatomical features that can be relatively easily extracted from an image based on its morphological features and the like by image processing such as pattern recognition. The positions and arrangements of these many anatomical features in the body are roughly determined according to the physique such as age, adult / child, male / female, weight, and height.

In the virtual patient image stored by the storage circuit 35, a large number of these anatomical feature points are detected in advance, and the position data of the detected feature points is attached to the data of the virtual patient image together with the identification code of each feature point. Or it is associated and stored. FIG. 7 is a diagram showing an example of a virtual patient image stored by the storage circuit 35 according to the first embodiment. For example, as shown in FIG. 7, the memory circuit 35 has identification codes “V1”, “V2” and identification codes for identifying anatomical feature points and feature points in a three-dimensional human body including a part such as an organ. A virtual patient image associated with "V3" or the like is stored.

That is, the storage circuit 35 stores the coordinates of the feature points in the coordinate space of the three-dimensional human body image in association with the corresponding identification code. As an example, the storage circuit 35 stores the coordinates of the corresponding feature points in association with the identification code “V1” shown in FIG. 7. Similarly, the storage circuit 35 stores the identification code and the coordinates of the feature point in association with each other. In FIG. 7, only the lungs, heart, liver, stomach, kidneys, etc. are shown as organs, but in reality, the virtual patient image includes a larger number of organs, bones, blood vessels, nerves, and the like. .. Further, in FIG. 7, only the feature points corresponding to the identification codes “V1”, “V2” and “V3” are shown, but in reality, a larger number of feature points are included.

The position collation function 37b matches the feature points in the volume data of the subject detected by the detection function 37a with the feature points in the virtual patient image described above by using an identification code, and uses the identification code to match the feature points in the volume data coordinate space. Associate with the coordinate space of the virtual patient image. FIG. 8 is a diagram for explaining an example of collation processing by the position collation function 37b according to the first embodiment. Here, in FIG. 8, matching is performed using three sets of feature points to which an identification code indicating the same feature point is assigned between the feature points detected from the scanno image and the feature points detected from the virtual patient image. However, the embodiment is not limited to this, and matching can be performed using any set of feature points.

For example, as shown in FIG. 8, the position matching function 37b has the feature points indicated by the identification codes “V1”, “V2” and “V3” in the virtual patient image, and the identification codes “C1” and “C2” in the scanno image. When matching with the feature points indicated by "" and "C3", the coordinate space between the images is associated by performing coordinate transformation so that the positional deviation between the same feature points is minimized. For example, as shown in FIG. 8, the position matching function 37b has the same anatomically the same feature points “V1 (x1, y1, z1), C1 (X1, Y1, Z1)” and “V2 (x2, y2, z2). ), C2 (X2, Y2, Z2) ”,“ V3 (x3, y3, z3), C3 (X3, Y3, Z3) ”to minimize the total“ LS ”of the positional deviation. Find the coordinate conversion matrix "H".

LS = ((X1, Y1, Z1) -H (x1, y1, z1))
+ ((X2, Y2, Z2)-H (x2, y2, z2))
+ ((X3, Y3, Z3)-H (x3, y3, z3))

The position collation function 37b can convert the scan range designated on the virtual patient image into the scan range on the positioning image by the obtained coordinate transformation matrix “H”. For example, the position collation function 37b uses the coordinate transformation matrix “H” to change the scan range “SRV” specified on the virtual patient image to the scan range “SRC” on the positioning image, as shown in FIG. Can be converted. FIG. 9 is a diagram showing an example of conversion of a scan range by coordinate conversion according to the first embodiment. For example, as shown on the virtual patient image of FIG. 9, when the operator sets the scan range “SRV” on the virtual patient image, the position collation function 37b is set using the coordinate transformation matrix “H” described above. The scanned range "SRV" is converted into the scan range "SRC" on the scanno image.

As a result, for example, the scan range "SRV" set to include the feature points corresponding to the identification code "Vn" on the virtual patient image has the identification code "Cn" corresponding to the same feature points on the scanno image. Is converted and set to the scan range "SRC" including. The coordinate transformation matrix "H" described above may be stored in the storage circuit 35 for each subject and appropriately read out for use, or is calculated each time a scanno image is collected. It may be the case. As described above, according to the first embodiment, the virtual patient image is displayed for specifying the range at the time of presetting, and the position / range is planned on the virtual patient image, so that after the positioning image (scano image) is taken. , It is possible to automatically set the position / range on the positioning image corresponding to the planned position / range.

Return to FIG. The assisted diagnosis function 37c executes a computer-aided diagnosis (CAD) process for detecting a lesion site by using a predetermined assisted diagnosis algorithm for a reconstructed image of a subject. The support diagnostic function 37c will be described in detail later. CAD is also referred to as diagnostic support processing.

The overall configuration of the medical information processing system 100 and the configuration of the X-ray CT apparatus 1 according to the first embodiment have been described above. Under such a configuration, the X-ray CT apparatus 1 according to the first embodiment has anatomical feature points in a virtual patient image and a structure in a subject in image data taken by a positioning scan or this scan. By converting the specified scan position or scan range based on the collation result with the feature point based on, the accuracy of presetting the shooting position and the like is improved.

By the way, in the X-ray CT apparatus 1, CAD (computer-aided diagnosis) for detecting a lesion site may be executed by using a predetermined assisted diagnosis algorithm for a reconstructed image of a subject. Here, in the X-ray CT apparatus according to the prior art, CAD is executed on the reconstructed image obtained by this scan.

In such a case, for example, the image interpreter performs CAD on the reconstructed image after the examination is completed. Then, the image interpreting doctor refers to the CAD processing result and interprets the reconstructed image. That is, in the X-ray CT apparatus according to the prior art, CAD could not be executed before the main scan in the same inspection. In other words, it was not possible to optimize the imaging conditions for this scan by referring to the CAD processing results. As a result, even if the radiologist detects the lesion site and determines that a detailed examination is necessary, the patient has already returned home and the time until re-examination is long, or the patient is forced to undergo multiple examinations. In some cases, the burden on the patient increased.

Therefore, the X-ray CT apparatus 1 according to the first embodiment executes the support diagnostic process for the detected site for each of the plurality of detected sites of the subject on the positioning image. Such a function is realized by the support diagnostic function 37c. Hereinafter, the support diagnostic function 37c will be described.

The support diagnosis function 37c executes the diagnosis support process corresponding to the predetermined part of the positioning image in the region corresponding to the predetermined part of the subject detected by the detection function 37a. For example, the support diagnosis function 37c detects a site having a possibility of illness by using a predetermined support diagnosis algorithm for each site. More specifically, the support diagnostic function 37c detects a tumor shadow or shadow as a lesion site by using a support diagnostic algorithm for lung cancer, for example, when the site is a lung. Then, the support diagnosis function 37c causes the processing result to be displayed on the display 32. Here, the support diagnosis function 37c causes the display 32 to display the result of the diagnosis support process on the virtual patient associated with each part of the subject. FIG. 10 is a diagram (1) for explaining the first embodiment.

FIG. 10 shows a GUI screen when a positioning image is taken after the chest is set as a target part in the preset of this scan. As shown in FIG. 10, on the GUI screen, a button for designating a target site (for example, a button for the head, chest, abdomen, lungs, heart, etc.) and a virtual patient image showing the whole human body are displayed on the GUI screen. The positioning image obtained by the positioning scan is displayed. Further, as shown in FIG. 10, the processing result of the diagnosis support processing is displayed on the virtual patient image. FIG. 10 shows a case where the chest scan range R1 is set on the virtual patient image. By setting the scan range R1 on the virtual patient image, the position collation function 37b converts it into the coordinate information on the positioning image and sets the scan range R11.

FIG. 10 shows a case where a lesion site D1 and a lesion site D2 are detected in the lung as a result of applying a diagnostic support process to the reconstructed image obtained by the positioning scan. Here, the support diagnosis function 37c corrects the display position of the result of the diagnosis support process according to the ratio of the positioning image and the virtual patient, and displays it on the display. Note that FIG. 10 shows a case where the lesion site D1 and the lesion site D2 are displayed in the same form, but the embodiment is not limited to this. For example, the support diagnosis function 37c may display the processing result on the display 32 in a display form according to the importance. More specifically, a case where the importance is set based on the shape and size of the tumor shadow or shadow will be described. In addition, the higher the importance, the higher the possibility of being ill as a lesion site. For example, the support diagnostic function 37c may blink the lesion site of high importance, or may display the lesion site of low importance and the lesion site of high importance in different colors.

By displaying the processing result of the diagnosis support process on the virtual patient in this way, the operator can confirm the lesion site by referring to the process result of the diagnosis support process before the main scan. .. Here, the support diagnostic function 37c may be provided with information indicating whether or not the lesion is a lesion site confirmed by the operator. For example, the support diagnostic function 37c further displays a check box in the vicinity of the lesion site. Then, when the lesion site is confirmed, the support diagnosis function 37c accepts the input from the operator to the check box. Alternatively, the support diagnostic function 37c may change the color of the lesion site instructed by the operator to indicate that the lesion site has been checked. This allows the operator to distinguish between a confirmed lesion site and an unidentified lesion site.

In addition, the operator determines that it is desirable to change to imaging under high-definition imaging conditions or add high-definition imaging conditions for the lesion site by referring to the processing results of the diagnostic support processing. In some cases. For this reason, the support diagnostic function 37c sets the imaging conditions for this scan for the site where the lesion site is specified among the plurality of sites as the processing result of the diagnosis support process. For example, the support diagnostic function 37c sets the imaging conditions for this scan for the lesion site selected by the operator among the lesion sites identified as a result of the diagnosis support process.

More specifically, the support diagnosis function 37c sets a condition for executing high-definition imaging as an imaging condition. For example, when the support diagnosis function 37c accepts the selection of the lesion site D1 shown in FIG. 10 from the operator, the support diagnosis function extracts the conditions for performing high-definition imaging as the imaging conditions for the lesion site D1 and this imaging condition. A pop-up window containing the above is displayed on the display 32. FIG. 11 is a diagram (2) for explaining the first embodiment. In the example shown in FIG. 11, “collection thickness”, “D-FOV”, “kV”, “mA”, “C-FOV”, and “shooting range” are the items of the imaging conditions for performing high-definition shooting. , And the case where the "reconstruction condition" is included.

Here, the imaging conditions shown in FIG. 11 include a portion set in advance by the operator and a portion set by the support diagnosis function 37c based on the body shape and the like. As an example, the operator presets the collection thickness (for example, 0.25 mm, etc.) and the D-FOV. On the other hand, the support diagnosis function 37c calculates kV, mA, and C-FOV from the imaging conditions of the positioning scan as conditions for executing high-definition imaging. Further, the support diagnostic function 37c calculates the reconstruction condition (interval) from D-FOV to isotropic Voxel. The reconstruction conditions include the FBP method and the successive approximation reconstruction method.

Further, as shown in FIG. 11, the support diagnosis function 37c displays “setting” and “cancellation”. Here, when "Cancel" is selected by the operator, the support diagnostic function 37c closes the pop-up window. That is, the operator can also execute the main scan by ignoring the CAD processing result. On the other hand, when "setting" is selected by the operator, the support diagnosis function 37c adds the imaging condition displayed in the pop-up window to the imaging plan.

The imaging conditions can also be set to automatically calculate what the user should set. For example, the support diagnostic function 37c may set at least one of tube voltage, tube current, imaging range, and reconstruction condition as a condition for performing high-definition imaging. As described above, the support diagnostic function 37c extracts, for example, a condition for performing high-definition imaging as an imaging condition of the main scan for the site where the lesion site selected by the operator is specified.

Then, when the imaging condition of the lesion site is not added, the scan control circuit 33 executes the main scan under the imaging condition selected in advance as the imaging plan of the main scan. Further, when the imaging condition of the lesion site is added, the scan control circuit 33 executes the main scan under the imaging conditions selected in advance and the extracted imaging conditions as the imaging plan of the main scan. That is, when the imaging condition of the lesion site is added, the scan control circuit 33 controls the imaging mechanism so as to perform imaging on the imaging region including the site where the lesion site is specified, based on the set imaging condition. ..

FIG. 12 is a flowchart showing a processing procedure by the X-ray CT apparatus 1 according to the first embodiment. FIG. 12 shows a flowchart illustrating the operation of the entire X-ray CT apparatus 1, and describes which step of the flowchart each component corresponds to.

Step S101 is a step realized by the input circuit 31. In step S101, the input circuit 31 accepts a selection of protocol presets. Step S102 is a step realized by the scan control circuit 33. In step S102, the scan control circuit 33 executes a positioning scan.

Step S103 is a step corresponding to the detection function 37a. This is a step in which the detection function 37a is realized by the processing circuit 37 calling and executing a predetermined program corresponding to the detection function 37a from the storage circuit 35. In step S103, the detection function 37a executes AL analysis on the positioning image.

Step S104 is a step corresponding to the position collation function 37b. This is a step in which the position collation function 37b is realized by the processing circuit 37 calling and executing a predetermined program corresponding to the position collation function 37b from the storage circuit 35. In step S104, the position collation function 37b collates the AL analysis result with the preset position.

Steps S105 to S110 are steps corresponding to the support diagnosis function 37c. This is a step in which the support diagnosis function 37c is realized by the processing circuit 37 calling and executing a predetermined program corresponding to the support diagnosis function 37c from the storage circuit 35. In step S105, the support diagnostic function 37c executes CAD for each site. Then, in step S106, the support diagnosis function 37c displays the CAD result for each site.

In step S107, the support diagnostic function 37c determines whether or not the selection of the lesion site has been accepted. Here, when the support diagnostic function 37c does not determine that the selection of the lesion site has been accepted (step S107, No), the process proceeds to step S111. On the other hand, when it is determined that the selection of the lesion site is accepted (step S107, Yes), the support diagnosis function 37c displays the imaging conditions according to the selected lesion site in step S108.

Then, in step S109, the support diagnosis function 37c determines whether or not the imaging plan has been changed. Here, when the support diagnosis function 37c does not determine that the imaging plan has been changed (steps S109, No), the process proceeds to step S111. On the other hand, when the support diagnosis function 37c determines that the imaging plan has been changed (steps S109, Yes), the imaging plan is updated in step S110. For example, the support diagnostic function 37c updates the imaging plan so as to execute the imaging conditions for performing high-definition imaging in addition to the imaging conditions selected in advance as the imaging plan for the main scan.

Step S111 is a step realized by the scan control circuit 33. In step S111, the scan control circuit 33 determines whether or not the execution of the main scan has been accepted. Here, if the scan control circuit 33 does not determine that the execution of this scan has been accepted (steps S111, No), the process proceeds to step S107. On the other hand, when the scan control circuit 33 determines that the execution of the main scan has been accepted (steps S111, Yes), the scan control circuit 33 executes the main scan in step S112.

The support diagnostic function 37c may execute diagnostic support processing on the three-dimensional image generated by reconstructing the projection data collected by this scan, and display the processing result on the display 32. .. In such a case, the image reconstruction circuit 36 reconstructs the projection data collected by this scan to generate three-dimensional image data. Further, the detection function 37a detects each of a plurality of parts of the subject in the three-dimensional image data. Then, the support diagnosis function 37c executes the diagnosis support process corresponding to the predetermined part of the region corresponding to the predetermined part of the subject detected by the detection function 37a in the three-dimensional image data acquired by this scan. do. This makes it possible to detect the lesion site more accurately by executing the diagnostic support process on the three-dimensional image taken in high definition by this scan. Further, in such a case, the support diagnosis function 37c executes the diagnosis support process by using, for example, an algorithm for discrimination. This makes it possible to detect a new lesion site.

As described above, in the first embodiment, before the main scan, the support diagnostic process for the detected site is executed for the positioning image for each of the plurality of detected sites of the subject. This allows the operator to easily find a site that could not be recognized as a lesion site before the main scan. In addition, it is possible to optimize the imaging conditions of this scan by referring to the processing result of the support diagnosis. For example, conditions for performing high-definition imaging of a lesion site are set. As a result, this scan can be performed with the optimum dose at the required location and with parameters that overlap the pitch with fine slice thickness. This makes it possible to efficiently improve the image quality according to the first embodiment. As a result, according to the first embodiment, it is possible to support highly accurate image interpretation.

Further, as a result, according to the first embodiment, for example, an image interpreting doctor can shorten the time until an accurate diagnosis is made. Further, according to the first embodiment, it is possible to reduce the burden on the patient without forcing the patient to perform a plurality of examinations.

Further, in the first embodiment described above, the case where the support diagnostic function 37c adds an imaging condition for executing high-definition imaging to an imaging condition selected in advance as an imaging plan for this scan has been described. The form is not limited to this. For example, the support diagnosis function 37c may update the imaging plan with imaging conditions for performing high-definition imaging instead of the imaging conditions selected in advance as the imaging plan for the main scan. In other words, the assistive diagnostic function 37c changes the imaging plan so that high-definition imaging is performed only on the site detected as the lesion site without performing the main scan under the preselected imaging conditions. Then, for example, the scan control circuit 33 executes the main scan under the imaging conditions for executing the high-definition imaging in addition to the imaging conditions selected in advance as the imaging plan for the main scan. Alternatively, the scan control circuit 33 executes the main scan under the imaging conditions for executing high-definition imaging instead of the imaging conditions selected in advance as the imaging plan for the main scan. Alternatively, the scan control circuit 33 executes the main scan only under the imaging conditions selected in advance as the imaging plan for the main scan. In other words, the scan control circuit 33 executes the main scan using at least one of the imaging conditions selected in advance and the extracted imaging conditions as the imaging plan for the main scan.

Further, when the support diagnosis function 37c has many parts for high-definition imaging, the imaging plan may be changed so as to perform high-definition imaging within a predetermined range including these high-definition imaging regions. For example, the support diagnostic function 37c presents an imaging condition for changing the entire chest to high-definition imaging when there are a plurality of lesion sites in the chest. Then, the support diagnosis function 37c changes the imaging plan so that the entire chest is imaged with high definition when the change is received from the operator.

Further, the support diagnostic function 37c may determine whether high-definition imaging is performed by a conventional scan or a helical scan. More specifically, the support diagnostic function 37c determines that when the detector is 40 mm in the body axis direction, a conventional scan is performed if the size of the lesion site is within 40 mm, and the size of the lesion site is 40 mm or more. If so, it is determined to perform a helical scan. The support diagnosis function 37c outputs the determination result to the scan control circuit 33. As a result, the scan control circuit 33 executes high-definition imaging by conventional scan or helical scan according to the determination result.

Further, in the above-mentioned first embodiment, the support diagnostic function 37c has been described as displaying the imaging conditions for the lesion site received from the operator, but the embodiment is not limited to this. For example, the support diagnosis function 37c may automatically recommend the protocol based on the CAD result without receiving the instruction from the operator. Further, although the support diagnostic function 37c has described the case where high-definition imaging is performed on the lesion site received from the operator, the embodiment is not limited to this. For example, the support diagnostic function 37c may be added to the imaging plan for the detected lesion site without accepting selection from the operator. Further, the support diagnosis function 37c, for example, when there are many parts to be imaged with high definition, perform high-definition imaging within a predetermined range including these parts to be imaged with high definition without accepting a selection from the operator. You may change the shooting plan.

(Second embodiment)
In the first embodiment, the case where the lesion site is detected in the site set as the preset of this scan by CAD has been described. By the way, CAD automatically extracts AL, recognizes a site, and is applied to each recognized site. Therefore, the lesion site detected by CAD is not necessarily limited to the preset site. Therefore, in the second embodiment, a case where a lesion site is detected by CAD other than the preset site will be described.

The configuration of the X-ray CT apparatus according to the second embodiment is the same as the configuration of the X-ray CT apparatus 1 according to the first embodiment, except that some functions of the support diagnostic function 37c are different. Therefore, the description other than the support diagnosis function 37c will be omitted.

FIG. 13 is a diagram (1) for explaining the second embodiment. FIG. 13 shows a GUI screen when a positioning image is taken after the chest is set as a target portion in the preset, as in FIG. 10. As shown in FIG. 13, on the GUI screen, a button for designating a target site (for example, a button for the head, chest, abdomen, lungs, heart, etc.) and a virtual patient image showing the whole human body are displayed on the GUI screen. The positioning image obtained by the positioning scan is displayed. Further, as shown in FIG. 13, the processing result of the diagnosis support processing is displayed on the virtual patient image.

FIG. 13 shows a case where the lesion site D1 and the lesion site D2 are detected in the lung and the lesion site D3 is detected in the liver as a result of applying the diagnostic support process to the reconstructed image obtained by the positioning scan. .. Here, the support diagnosis function 37c corrects the display position of the result of the diagnosis support process on the virtual patient image according to the ratio of the positioning image and the virtual patient, and displays it on the display 32. Further, the lesion site D1 and the lesion site D2 are the lesion sites identified in the lung. That is, the lesion site D1 and the lesion site D2 are the lesion sites specified in the chest of the target site set in the preset. On the other hand, the lesion site D3 is a lesion site identified in the liver. That is, the lesion site D3 is a lesion site specified by a site other than the target site set in the preset.

As shown in FIG. 13, it may be desirable to perform this scan even for lesion sites identified other than the target sites set in the preset. On the other hand, the operator may overlook the lesion site specified in a site other than the target site set in the preset. For this reason, the support diagnostic function 37c sets the imaging conditions for this scan for the site where the lesion site is specified among the plurality of sites as the processing result of the diagnosis support process. For example, the support diagnostic function 37c sets the imaging conditions of the present scan for the lesion site specified as a result of the diagnosis support process, in which the lesion site other than the site selected in advance as the imaging plan is specified. FIG. 14 is a diagram (2) for explaining the second embodiment.

As shown in FIG. 14, the support diagnostic function 37c displays a pop-up window on the display 32 containing a notice that calls attention, for example, "[Caution] there is a site suspected to be a lesion other than the preset site." Display. Further, as shown in FIG. 14, the support diagnosis function 37c displays “display” and “cancel”. Here, when "Cancel" is selected by the operator, the support diagnostic function 37c closes the pop-up window.

On the other hand, when "display" is selected by the operator, the support diagnostic function 37c highlights the lesion site displayed on the virtual patient and other than the preset site. For example, the support diagnostic function 37c blinks the lesion site D3 shown in FIG. 13 or displays it with an arrow. This makes it easier for the operator to recognize the lesion site D3.

Then, when the support diagnosis function 37c receives the selection of the lesion site D3 shown in FIG. 13 from the operator, the support diagnosis function 37c extracts the conditions for performing high-definition imaging as the imaging conditions for the lesion site D3, and FIG. 11 A pop-up window having the same shape as the above is displayed on the display 32. As a result, the support diagnostic function 37c closes the pop-up window without adding the imaging condition of the lesion site when "Cancel" is selected by the operator. On the other hand, the support diagnosis function 37c adds the imaging conditions displayed in the pop-up window to the imaging plan when "setting" is selected by the operator.

Then, when the imaging condition of the lesion site is not added, the scan control circuit 33 executes the main scan under the imaging condition selected in advance as the imaging plan of the main scan. Further, when the imaging condition of the lesion site is added, the scan control circuit 33 executes the main scan under the imaging conditions selected in advance and the extracted imaging conditions as the imaging plan of the main scan. That is, when the imaging condition of the lesion site is added, the scan control circuit 33 controls the imaging mechanism so as to perform imaging on the imaging region including the site where the lesion site is specified, based on the set imaging condition. ..

The support diagnostic function 37c may execute diagnostic support processing on the three-dimensional image generated by reconstructing the projection data collected by this scan, and display the processing result on the display 32. .. In such a case, the image reconstruction circuit 36 reconstructs the projection data collected by this scan to generate three-dimensional image data. Further, the detection function 37a detects each of a plurality of parts of the subject in the three-dimensional image data. Then, the support diagnosis function 37c executes the diagnosis support process corresponding to the predetermined part of the region corresponding to the predetermined part of the subject detected by the detection function 37a in the three-dimensional image data acquired by this scan. do. Then, the support diagnostic function 37c sets the imaging conditions of the present scan for the lesion site specified as a result of the diagnosis support process, in which the lesion site other than the site selected in advance as the imaging plan is specified. In such a case, the support diagnosis function 37c executes the diagnosis support process by using, for example, an algorithm for discrimination.

As described above, in the second embodiment, the X-ray CT apparatus 1 promotes imaging of a lesion site detected by the diagnosis support process other than the preset site. For example, the X-ray CT apparatus 1 sets the chest as the target site, photographs the positioning scan from the neck to the abdomen, and when the lesion site is detected in the abdomen by the diagnostic support process, it calls attention to image the abdomen as well. Display notifications. As a result, according to the second embodiment, it is possible to diagnose a lesion site detected in a site other than the target site set in the preset without overlooking.

In addition, the support diagnosis function 37c changes the imaging plan so that the main scan is executed for the lesion site specified other than the target site set in the preset, even if the operator does not accept the change of the imaging plan. You may.

(Other embodiments)
By the way, although the first and second embodiments have been described so far, various different embodiments may be implemented in addition to the above-mentioned first and second embodiments.

In the above-described embodiment, the support diagnosis function 37c has been described as displaying the processing result of the diagnosis support process on the virtual patient, but the embodiment is not limited to this. For example, the support diagnosis function 37c may display the processing result of the diagnosis support process on the positioning image.

Further, the support diagnosis function 37c may request the attending physician to add an imaging instruction based on the CAD processing result. For example, the support diagnostic function 37c generates an email prompting to approve the change of the imaging plan and sends it to the doctor in charge. Alternatively, the support diagnosis function 37c contacts the doctor in charge of the hospital extension or the like to urge the doctor to approve the change in the imaging plan.

Further, in the above-described embodiment, the case where the diagnostic support process is executed for the three-dimensional positioning image has been described, but the embodiment is not limited to this. For example, a two-dimensional CAD may be applied to a two-dimensional positioning image.

Further, the support diagnostic function 37c can also be controlled to output evaluation information for the site of the subject detected by the detection function 37a. For example, the assistive diagnostic function 37c displays evaluation information based on a calcium score for quantitatively evaluating coronary artery calcification when the detected site is the heart. In such a case, the support diagnostic function 37c calculates the calcium score based on the CT value. Then, the support diagnosis function 37c displays the evaluation information based on the calculated calcium score. As an example, the assistive diagnostic function 37c displays a warning for the execution of cardiac CT (coronary CT) when the calcium score exceeds "600". This allows the observer to determine that cardiac CT is not appropriate as a test for the subject.

Further, the X-ray CT apparatus 1 converts the result of the diagnostic support processing for the positioning image and the result of the diagnostic support processing for the three-dimensional image generated by reconstructing the projection data collected by this scan into, for example, HIS or RIS. You may try to save it. Then, the X-ray CT apparatus 1 uses the processing result saved as a comparison target at the next shooting. For example, the X-ray CT apparatus 1 compares and displays the previous processing result after the positioning scan. Further, the X-ray CT apparatus 1 may display the processing result on the virtual patient, or may display the processing result on the positioning image. Further, the X-ray CT apparatus 1 may output the processing result to an external apparatus.

In addition, as a result of AL analysis, when the kidney or lung is present on only one side, there is a difference from the standard human body model. In such a case, the X-ray CT apparatus 1 displays the deletion of the organ on the virtual patient in a recognizable state. For example, fill or annotate a missing organ. Further, the support diagnostic function 37c may exclude the deleted organ from the target of the diagnostic support process.

Further, when the X-ray CT apparatus 1 determines as a result of AL analysis that there is a foreign substance such as metal in a portion of the virtual patient that does not collate with an organ, the X-ray CT apparatus 1 presents to the virtual patient that there is metal in the portion. It should be noted that the foreign matter can be determined by, for example, the CT value. Even in such a case, the support diagnosis function 37c may exclude the portion having a foreign substance from the target of the diagnosis support process. In addition, by presenting that there is a foreign substance such as metal, the X-ray CT apparatus 1 prevents the dose from being raised too much at the time of imaging, and at the time of reconstruction, only the portion where the foreign substance such as metal is present is removed and reconstructed. Can be adapted. In addition, the X-ray CT apparatus 1 can also display a required reconstruction range. For example, the X-ray CT apparatus 1 strongly applies noise reduction to a large portion of a subject. It should be noted that the portion containing a foreign substance such as metal may be displayed on the MPR image or the axial image instead of on the virtual patient.

In addition, the X-ray CT apparatus 1 differs from the standard human body model when the organ is abnormally enlarged, small, or meandering. Even in such a case, the X-ray CT apparatus 1 displays a portion of the virtual patient that is different from the standard human body model in a recognizable state. For example, the X-ray CT apparatus 1 blinks a portion of an organ that has a difference, annotates it so that symptoms such as cardiac hypertrophy can be understood, lights and displays the entire meandering organ, and displays a meandering portion. Is displayed with an arrow. Further, as the X-ray CT apparatus 1, a device different from the standard model may be registered in HIS or RIS so that it can be referred to in the next and subsequent inspections.

In the above-described embodiment, the detection function 37a has been described as performing AL analysis using the volume data of the positioning image or the volume data of the image used for diagnosis, but the embodiment is limited to this. It's not something. For example, the detection function 37a
AL analysis may be performed using a two-dimensional positioning image. Further, the detection function 37a may execute the AL analysis by using the image used for the diagnosis of the same subject previously imaged by the own device. Further, the detection function 37a may execute the AL analysis using the medical image data of the same subject imaged by another device.

Further, in the above-described embodiment, it has been described that the diagnostic support process is executed for each part of the subject detected by executing the AL analysis, but the embodiment is not limited to this. For example, the support diagnosis function 37c may execute the diagnosis support process on the image data. FIG. 15 is a flowchart showing a processing procedure by the X-ray CT apparatus according to another embodiment.

FIG. 15 shows a flowchart illustrating the operation of the entire X-ray CT apparatus 1, and describes which step of the flowchart each component corresponds to. In FIG. 15, the same reference numerals are given to the same processes as those in the flowchart shown in FIG. 12, and detailed description thereof will be omitted. The process of step S201 shown in FIG. 15 corresponds to the process of step S101 shown in FIG. 12, and the process of step S202 shown in FIG. 15 corresponds to the process of step S102 shown in FIG.

Step S203 is a step corresponding to the support diagnosis function 37c. This is a step in which the support diagnosis function 37c is realized by the processing circuit 37 calling and executing a predetermined program corresponding to the support diagnosis function 37c from the storage circuit 35. In step S203, the support diagnostic function 37c executes CAD based on the protocol preset selected in step S201. Here, in step S201, when "abdomen" is selected as the "site" in the protocol preset, the support diagnostic function 37c executes CAD for the abdomen.

The processing of steps S204 to S210 shown in FIG. 15 corresponds to the processing of steps S106 to S112 shown in FIG. That is, the support diagnostic function 37c sets the imaging conditions of the main scan for the site where the lesion site is identified as the CAD processing result. Then, the scan control circuit 33 controls the imaging mechanism so as to perform imaging on the imaging region including the region where the lesion site is specified, based on the imaging conditions.

In FIG. 15, the case where CAD is executed based on the protocol preset is described in step S203, but the embodiment is not limited to this. For example, the support diagnostic function 37c may accept from the operator the selection of which site the CAD is to be executed in step S203. Then, the support diagnosis function 37c executes CAD corresponding to the site selected by the operator.

Alternatively, the support diagnostic function 37c may execute all of the CAD for each site held by the X-ray CT apparatus 1. For example, if the X-ray CT device 1 has a CAD for the chest, a CAD for the abdomen, and a CAD for the pelvis, the assistive diagnostic function 37c does not consider the protocol preset set in step S201, and steps. In S203, CAD for the chest, CAD for the abdomen, and CAD for the pelvis are executed, respectively.

Further, the support diagnostic function 37c may execute CAD subdivided for each site or disease. For example, as the CAD for the abdomen, the X-ray CT device 1 can be a CAD subdivided by organ such as a CAD for the liver and a CAD for the large intestine, a CAD subdivided by an organ such as a CAD for lung cancer, and a CAD subdivided by a disease such as a CAD for breast cancer. If so, the supportive diagnostic function 37c may be configured to perform subdivided CAD. In such a case, the assistive diagnostic function 37c may execute CAD based on the protocol preset. For example, in step S201, when "abdomen" and "liver" are selected as "sites" in the protocol preset, the assistive diagnostic function 37c performs CAD for the liver. Alternatively, for example, in step S201, even if "abdomen" and "liver" are selected as "sites" in the protocol preset, the assistive diagnostic function 37c will perform all CAD subdivided for the abdomen. You may. The support diagnosis function 37c may execute the CAD that has been selected by the operator, or may execute all the CAD possessed by the X-ray CT apparatus 1 without considering the protocol preset.

Further, in step S203, the support diagnosis function 37c may accept, for example, the designation of the area for executing CAD in the image from the operator. Further, the support diagnostic function 37c estimates the site based on the scan distance and executes CAD for the estimated site, for example, when the imaging direction of the subject can be specified in advance such as the head-to-tail direction. May be good.

Further, in the above-described embodiment, the X-ray CT apparatus has been described as an example of the medical image imaging apparatus, but the embodiment is not limited to this. For example, the medical image imaging device may be an X-ray diagnostic device, an ultrasonic diagnostic device, an MRI (Magnetic Resonance Imaging) device, or the like.

Further, in the above-described embodiment, it has been described that the diagnostic support process is executed in the medical image imaging apparatus, but the embodiment is not limited to this. For example, a medical image processing device or the like may be provided as a management device, and the diagnosis support process may be executed in this management device. That is, the management device acquires the image data of the subject generated by the medical image imaging device. Then, the management device detects each of a plurality of parts of the subject in the image data generated as the positioning image. Subsequently, the management device executes the diagnosis support process corresponding to the predetermined portion of the detected image data in the region corresponding to the predetermined portion. Further, the management device sets the imaging conditions of the main scan for the site where the lesion site is specified among the plurality of sites as the processing result of the diagnosis support process. Then, the management device instructs the medical image imaging device to perform imaging on the imaging region including the site where the lesion site is specified based on the imaging conditions.

Alternatively, the management device acquires image data of the subject generated by the medical image imaging device. Then, the management device executes the diagnosis support process for the image data. Further, the management device sets the imaging conditions of this scan for the site where the lesion site is identified as the processing result of the diagnosis support process. Then, the management device instructs the medical image imaging device to perform imaging on the imaging region including the site where the lesion site is specified based on the imaging conditions.

Further, the diagnostic support process may be distributed and executed in the medical image imaging device and the management device. For example, a medical image imaging device executes a process of generating image data of a subject. The management device executes a process of acquiring image data of the subject generated by the medical image imaging device, and executes a process of detecting a plurality of parts of the subject in the image data generated as a positioning image. .. Subsequently, the management device executes the diagnosis support process corresponding to the predetermined portion of the detected image data in the region corresponding to the predetermined portion. Further, the management device executes a process of setting the imaging conditions of the main scan for the site where the lesion site is specified among the plurality of sites as the processing result of the diagnosis support process. Then, the medical image imaging device executes a process of controlling the imaging mechanism so as to perform imaging on the imaging region including the region where the lesion site is specified, based on the imaging conditions.

Alternatively, for example, a medical image imaging device executes a process of generating image data of a subject. The management device executes diagnostic support processing on the image data. Further, the management device executes a process of setting the imaging conditions of the main scan for the site where the lesion site is identified as the process result of the diagnosis support process. Then, the medical image imaging device executes a process of controlling the imaging mechanism so as to perform imaging on the imaging region including the region where the lesion site is specified, based on the imaging conditions.

In the above-described embodiment, the medical image processing device has been described as an example as the management device, but the embodiment is not limited to this. For example, the console 30 of the X-ray CT apparatus 1 may be used as a management apparatus. Alternatively, for example, a device connecting a plurality of medical image imaging devices may be used as a management device. Further, the processing in the management device may be realized in cloud computing.

The word "processor" used in the above description is, for example, a CPU (central Processing unit), a GPU (Graphics Processing Unit), an integrated circuit for a specific application (ASIC), or a programmable logic device (for example, a programmable logic device). Simple Programmable Logic Device (SPLD), Complex Programmable Logic Device (CPLD), and Field Programmable Gate Array (Field Programmable).
Gate Array: FPGA))) and other circuits. The processor realizes the function by reading and executing the program stored in the storage circuit. Instead of storing the program in the storage circuit, the program may be directly embedded in the circuit of the processor. In this case, the processor realizes the function by reading and executing the program embedded in the circuit. It should be noted that each processor of the present embodiment is not limited to the case where each processor is configured as a single circuit, and a plurality of independent circuits may be combined to form one processor to realize its function. good. Further, the plurality of components in FIG. 2 may be integrated into one processor to realize the function.

Further, each component of each device shown in the above-described embodiment is a functional concept, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in any unit according to various loads and usage conditions. Can be integrated and configured. Further, each processing function performed by each device may be realized by a CPU and a program analyzed and executed by the CPU, or may be realized as hardware by wired logic.

Further, the control method described in the first embodiment can be realized by executing a control program prepared in advance on a computer such as a personal computer or a workstation. This control program can be distributed via a network such as the Internet. Further, this control program can also be executed by being recorded on a computer-readable recording medium such as a hard disk, flexible disk (FD), CD-ROM, MO, or DVD, and being read from the recording medium by the computer.

As described above, according to each embodiment, it is possible to optimize the imaging conditions of this scan by referring to the processing result of the support diagnosis.

Although some embodiments of the present invention have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other embodiments, and various omissions, replacements, and changes can be made without departing from the gist of the invention. These embodiments and variations thereof are included in the scope of the invention described in the claims and the equivalent scope thereof, as are included in the scope and gist of the invention.

1 X-ray CT device 37 Processing circuit 37a Detection function 37c Support diagnostic function

Claims (14)

An image generator that generates image data of the subject,
A detection unit that detects a plurality of parts of the subject in the image data generated as a positioning image, and a detection unit.
Among the image data, a diagnostic support processing unit that executes a diagnostic support process corresponding to the predetermined portion of the region corresponding to the predetermined portion of the subject detected by the detection unit, and a diagnostic support processing unit.
Imaging of the present scan for the lesion site selected by the operator among the lesion sites identified as the result of the diagnosis support processing among the plurality of sites as the processing result of the diagnosis support processing unit. The setting part that sets the conditions and
An imaging control unit that controls an imaging mechanism to perform imaging on an imaging region including a region where a lesion site has been identified based on the imaging conditions.
Medical image imaging device. An image generator that generates image data of the subject,
A detection unit that detects a plurality of parts of the subject in the image data generated as a positioning image, and a detection unit.
Among the image data, a diagnostic support processing unit that executes a diagnostic support process corresponding to the predetermined portion of the region corresponding to the predetermined portion of the subject detected by the detection unit, and a diagnostic support processing unit.
As a result of the processing of the diagnosis support processing unit, a lesion site other than the site selected in advance as an imaging plan among the lesion sites specified as a result of the diagnosis support process among the plurality of sites is specified. The setting unit that sets the imaging conditions for this scan for
An imaging control unit that controls an imaging mechanism to perform imaging on an imaging region including a region where a lesion site has been identified based on the imaging conditions.
Medical image imaging device. The medical image imaging device according to claim 1 or 2, wherein the diagnosis support processing unit displays the processing result on a display. The medical image imaging device according to claim 3, wherein the diagnosis support processing unit displays the processing result on the display in a display form according to the importance. An image generator that generates image data of the subject,
A detection unit that detects a plurality of parts of the subject in the image data generated as a positioning image, and a detection unit.
Among the image data, a diagnostic support processing unit that executes a diagnostic support process corresponding to the predetermined portion of the region corresponding to the predetermined portion of the subject detected by the detection unit, and a diagnostic support processing unit.
As a processing result of the diagnosis support processing unit, a setting unit for setting the imaging conditions of the main scan for the site where the lesion site is identified among the plurality of sites, and a setting unit.
An imaging control unit that controls an imaging mechanism to perform imaging on an imaging region including a region where a lesion site has been identified based on the imaging conditions.
Equipped with
The diagnosis support processing unit is a medical image imaging device that displays the processing result on a display in a display form according to the importance. The medical image imaging device according to any one of claims 3 to 5, wherein the diagnosis support processing unit displays the processing result on the display on a virtual patient associated with each site of the subject. The medical image imaging device according to claim 6, wherein the diagnosis support processing unit corrects the display position of the processing result according to the ratio of the positioning image to the virtual patient and displays it on the display. The medical image imaging device according to any one of claims 3 to 5, wherein the diagnosis support processing unit displays the processing result on the positioning image on the display. The medical image imaging device according to any one of claims 1 to 8, wherein the setting unit sets conditions for performing high-definition imaging as the imaging conditions. The medical image imaging according to claim 9, wherein the setting unit sets at least one of a tube voltage, a tube current, an imaging range, and a reconstruction condition as a condition for executing the high-definition imaging. Device. The image generation unit reconstructs the projection data collected by this scan to generate three-dimensional image data.
The detection unit detects a plurality of parts of the subject in the three-dimensional image data, respectively.
The diagnostic support processing unit performs diagnostic support processing corresponding to the predetermined portion of the region corresponding to the predetermined portion of the subject detected by the detection unit in the three-dimensional image data acquired by the main scan. The medical image imaging apparatus according to any one of claims 1 to 10. An image generator that generates image data of the subject,
A diagnostic support processing unit that executes diagnostic support processing for the image data,
As a processing result of the diagnosis support processing unit, a setting unit for setting the imaging conditions of this scan for the lesion site selected by the operator among the lesion sites specified as the result of the diagnosis support processing. ,
An imaging control unit that controls an imaging mechanism to perform imaging on an imaging region including a region where a lesion site has been identified based on the imaging conditions.
Medical image imaging device. The image generator generates the image data of the subject,
The detection unit detects a plurality of parts of the subject in the image data acquired as a positioning image, respectively.
The diagnosis support processing unit executes the diagnosis support process corresponding to the predetermined part of the detected image data for the region corresponding to the predetermined part of the subject.
A book for a site in which a lesion site selected by an operator among the lesion sites specified as a result of the diagnosis support process is specified among the plurality of sites as the processing result of the diagnosis support process by the setting unit. Set the imaging conditions for the scan and
The imaging control unit controls the imaging mechanism so as to perform imaging on the imaging region including the region where the lesion site is specified, based on the imaging conditions.
A method characterized by including each process. The image generator generates the image data of the subject,
The diagnosis support processing unit executes the diagnosis support processing on the image data, and then
The setting unit sets the imaging conditions for this scan for the lesion site selected by the operator among the lesion sites specified as the result of the diagnosis support process as the processing result of the diagnosis support process. ,
The imaging control unit controls the imaging mechanism so as to perform imaging on the imaging region including the region where the lesion site is specified, based on the imaging conditions.
A method characterized by including each process.

Images