JP2024054373A - Medical image diagnostic device and medical image diagnostic method - Google Patents

Abstract

[Problem] To facilitate alignment of a subject during imaging. [Solution] A medical image diagnostic device according to an embodiment includes an acquisition unit and a processing unit. The acquisition unit acquires information relating to a region to be scanned and an aligned image of the subject. The processing unit inputs the acquired information relating to the region to be scanned and the aligned image of the subject to a trained model that outputs a scan range of the subject during scanning based on information relating to the region to be scanned and the aligned image of the subject, and outputs a scan range relating to the subject related to the acquired information relating to the region to be scanned and the aligned image of the subject. [Selected Figure] Figure 1

Description

Embodiments of the present invention relate to a medical image diagnostic device and a medical image diagnostic method.

Conventionally, for imaging diagnostic devices such as X-ray CT scanners, there have been disclosed techniques for reducing the processing load at the image analysis stage by using machine learning to set image processing parameters and machine learning to learn template images that include the detection target itself (e.g., coronary arteries) and ALs (anatomical landmarks) of the detection target within the image.

Also, there is a technology known as ALD (Adaptive Layer Distribution) that automatically sets the scan range by recognizing the features of the human body (e.g., the outline of the head and torso).

However, with conventional technology, it was sometimes not easy to align the subject's position during imaging to reflect the results of machine learning.

US Patent Application Publication No. 2016/209995 US Patent Application Publication No. 2017/347973 US Patent Application Publication No. 2018/70908

The problem that this invention aims to solve is to make it easier to align the subject during imaging.

The medical image diagnostic device of the embodiment includes an acquisition unit and a processing unit. The acquisition unit acquires information about the part to be scanned and an aligned image of the subject. The processing unit inputs the acquired information about the part to be scanned and the aligned image of the subject to a trained model that outputs the scan range of the subject during scanning based on the information about the part to be scanned and the aligned image of the subject, and outputs the acquired information about the part to be scanned and the scan range of the subject related to the aligned image of the subject.

1 is a configuration diagram of an X-ray CT apparatus according to a first embodiment. FIG. 4 is a diagram showing an example of data stored in a memory 41. FIG. 4 is a diagram showing the configuration of a scan control function 55. FIG. 13 is a diagram for explaining the contents of processing by a scan range automatic setting function 55-2. FIG. 4 is a diagram for explaining the processing of a learning function 57; FIG. 2 is a diagram illustrating an example of a usage environment of the X-ray CT apparatus 1. FIG. 2 is a diagram illustrating an example of a usage environment of the X-ray CT apparatus 1. 4 is a flowchart showing an example of the flow of imaging processing by the X-ray CT apparatus 1. 11 is a flowchart showing an example of the flow of a learning process performed by a learning function 57. FIG. 10 is a diagram for explaining a gantry device 10A according to a second embodiment. FIG. 11 is a diagram showing an example of data stored in a memory 41A according to the second embodiment. FIG. 11 is a configuration diagram of a scan control function 55A according to a second embodiment. FIG. 13 is a diagram for explaining the contents of processing by a scan range automatic setting function 55-2A. FIG. 13 is a diagram for explaining the processing of a learning function 57A. 4 is a flowchart showing an example of the flow of imaging processing by the X-ray CT apparatus 1A. 11 is a flowchart showing an example of the flow of an optical image learning process performed by a learning function 57A.

The medical image diagnostic device and medical image diagnostic method of the embodiment will be described below with reference to the drawings. The medical image diagnostic device is a device that processes medical images from, for example, an X-ray CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, a PET (Positron Emission Tomography) device, etc. to diagnose a subject. In the following description, the medical image diagnostic device will be described as an X-ray CT device, but is not limited to this.

First Embodiment
FIG. 1 is a configuration diagram of an X-ray CT apparatus 1 according to the first embodiment. The X-ray CT apparatus 1 includes, for example, a gantry 10, a bed 30, and a console 40. In FIG. 1, for convenience of explanation, both a view of the gantry 10 seen from the Z-axis direction and a view of the gantry 10 seen from the X-axis direction are shown, but in reality, there is only one gantry 10. In this embodiment, the rotation axis of the rotating frame 17 in a non-tilted state or the longitudinal direction of the top plate 33 of the bed 30 is defined as the Z-axis direction, an axis perpendicular to the Z-axis direction and horizontal to the floor surface is defined as the X-axis direction, and a direction perpendicular to the Z-axis direction and perpendicular to the floor surface is defined as the Y-axis direction.

The gantry device 10 includes, for example, an X-ray tube 11, a wedge 12, a collimator 13, an X-ray high voltage device 14, an X-ray detector 15, a data acquisition system (hereinafter, DAS: Data Acquisition System) 16, a rotating frame 17, and a control device 18.

The X-ray tube 11 generates X-rays by irradiating thermoelectrons from a cathode (filament) to an anode (target) when a high voltage is applied from the X-ray high voltage device 14. The X-ray tube 11 includes a vacuum tube. For example, the X-ray tube 11 is a rotating anode type X-ray tube that generates X-rays by irradiating thermoelectrons to a rotating anode.

The wedge 12 is a filter for adjusting the amount of X-rays irradiated from the X-ray tube 11 to the subject P. The wedge 12 attenuates the X-rays that pass through it so that the distribution of the amount of X-rays irradiated from the X-ray tube 11 to the subject P becomes a predetermined distribution. The wedge 12 is also called a wedge filter or a bow-tie filter. The wedge 12 is made of aluminum processed to have a predetermined target angle and a predetermined thickness, for example.

The collimator 13 is a mechanism for narrowing the irradiation range of the X-rays that have passed through the wedge 12. The collimator 13 narrows the irradiation range of the X-rays, for example, by forming slits by combining multiple lead plates. The collimator 13 is sometimes called an X-ray aperture.

The X-ray high voltage device 14 has, for example, a high voltage generator and an X-ray control device. The high voltage generator has an electric circuit including a transformer and a rectifier, and generates a high voltage to be applied to the X-ray tube 11. The X-ray control device controls the output voltage of the high voltage generator according to the amount of X-rays to be generated by the X-ray tube 11. The high voltage generator may be one that boosts the voltage using the above-mentioned transformer, or one that boosts the voltage using an inverter. The X-ray high voltage device 14 may be provided on the rotating frame 17, or on the side of the fixed frame (not shown) of the gantry device 10.

The X-ray detector 15 detects the intensity of the X-rays generated by the X-ray tube 11 and passing through the subject P. The X-ray detector 15 outputs an electrical signal (which may be an optical signal, etc.) corresponding to the intensity of the detected X-rays to the DAS 18. The X-ray detector 15 has, for example, multiple rows of X-ray detection elements. Each of the multiple rows of X-ray detection elements has multiple X-ray detection elements arranged in the channel direction along an arc centered on the focal point of the X-ray tube 11. The multiple rows of X-ray detection elements are arranged in the slice direction (row direction).

The X-ray detector 15 is an indirect type detector having, for example, a grid, a scintillator array, and an optical sensor array. The scintillator array has a plurality of scintillators. Each scintillator has a scintillator crystal. The scintillator crystal emits an amount of light according to the intensity of the incident X-rays. The grid is arranged on the surface of the scintillator array on which the X-rays are incident, and has an X-ray shielding plate that has the function of absorbing scattered X-rays. The grid is sometimes called a collimator (one-dimensional collimator or two-dimensional collimator). The optical sensor array has, for example, an optical sensor such as a photomultiplier tube (PMT). The optical sensor array outputs an electrical signal according to the amount of light emitted by the scintillator. The X-ray detector 15 may be a direct conversion type detector having a semiconductor element that converts the incident X-rays into an electrical signal.

The DAS 16 includes, for example, an amplifier, an integrator, and an A/D converter. The amplifier amplifies the electrical signal output by each X-ray detection element of the X-ray detector 15. The integrator integrates the amplified electrical signal over a view period (described later). The A/D converter converts the electrical signal indicating the integration result into a digital signal. The DAS 16 outputs detection data based on the digital signal to the console device 40. The detection data is a digital value of X-ray intensity identified by the channel number and column number of the X-ray detection element that generated the data, and the view number indicating the acquired view. The view number is a number that changes according to the rotation of the rotating frame 17, and is, for example, a number that is incremented according to the rotation of the rotating frame 17. Therefore, the view number is information that indicates the rotation angle of the X-ray tube 11. The view period is the period that falls between the rotation angle corresponding to a certain view number and the rotation angle corresponding to the next view number. DAS16 may detect the view change by a timing signal input from control device 18, an internal timer, or a signal obtained from a sensor (not shown). When performing a full scan, if X-rays are continuously emitted by X-ray tube 11, DAS16 collects a group of detection data for the entire circumference (360 degrees). When performing a half scan, if X-rays are continuously emitted by X-ray tube 11, DAS16 collects detection data for half the circumference (180 degrees).

The rotating frame 17 is an annular member that supports the X-ray tube 11, wedge 12, and collimator 13, and the X-ray detector 15 in opposing relation. The rotating frame 17 is supported by a fixed frame so as to be freely rotatable around the subject P introduced inside. The rotating frame 17 also supports the DAS 16. The detection data output by the DAS 16 is transmitted by optical communication from a transmitter having a light-emitting diode (LED) provided on the rotating frame 17 to a receiver having a photodiode provided on a non-rotating part (e.g., the fixed frame) of the gantry device 10, and is transferred to the console device 40 by the receiver. Note that the method of transmitting the detection data from the rotating frame 17 to the non-rotating part is not limited to the above-mentioned method using optical communication, and any non-contact transmission method may be adopted. The rotating frame 17 is not limited to an annular member, and may be an arm-like member as long as it can support and rotate the X-ray tube 11, etc.

The X-ray CT device 1 is, for example, a Rotate/Rotate-type X-ray CT device (third generation CT) in which both the X-ray tube 11 and the X-ray detector 15 are supported by a rotating frame 17 and rotate around the subject P, but is not limited to this and may be a Stationary/Rotate-type X-ray CT device (fourth generation CT) in which multiple X-ray detection elements arranged in a circular ring are fixed to a fixed frame and the X-ray tube 11 rotates around the subject P.

The control device 18 has, for example, a processing circuit having a processor such as a CPU (Central Processing Unit) and a drive mechanism including a motor and an actuator. The control device 18 receives input signals from an input interface 43 attached to the console device 40 or the gantry device 10, and controls the operation of the gantry device 10 and the bed device 30.

The control device 18, for example, rotates the rotating frame 17, tilts the gantry 10, and moves the top plate 33 of the bed device 30. When tilting the gantry 10, the control device 18 rotates the rotating frame 17 around an axis parallel to the Z-axis direction based on the inclination angle (tilt angle) input to the input interface 43. The control device 18 knows the rotation angle of the rotating frame 17 from the output of a sensor (not shown) or the like. The control device 18 also provides the rotation angle of the rotating frame 17 to the processing circuit 50 at any time. The control device 18 may be provided in the gantry 10 or in the console device 40.

The bed device 30 is a device that places and moves the subject P to be scanned and introduces him/her into the rotating frame 17 of the gantry device 10. The bed device 30 has, for example, a base 31, a bed driving device 32, a top plate 33, and a support frame 34. The base 31 includes a housing that supports the support frame 34 so that it can move in the vertical direction (Y-axis direction). The bed driving device 32 includes a motor and an actuator. The bed driving device 32 moves the top plate 33, on which the subject P is placed, in the longitudinal direction of the top plate 33 (Z-axis direction) along the support frame 34. The top plate 33 is a plate-shaped member on which the subject P is placed.

The bed drive device 32 may move not only the tabletop 33 but also the support frame 34 in the longitudinal direction of the tabletop 33. Alternatively, the gantry device 10 may be movable in the Z-axis direction, and the rotation frame 17 may be controlled to come around the subject P by the movement of the gantry device 10. Alternatively, both the gantry device 10 and the tabletop 33 may be configured to be movable. The X-ray CT device 1 may be an apparatus in which the subject P is scanned in a standing or sitting position. In this case, the X-ray CT device 1 has a subject support mechanism instead of the bed device 30, and the gantry device 10 rotates the rotation frame 17 around an axial direction perpendicular to the floor surface.

The console device 40 has, for example, a memory 41, a display 42, an input interface 43, a memory 41, a network connection circuit 44, and a processing circuit 50. In the embodiment, the console device 40 is described as being separate from the gantry device 10, but the gantry device 10 may include some or all of the components of the console device 40.

The memory 41 is realized, for example, by a semiconductor memory element such as a RAM (Random Access Memory), a flash memory, a hard disk, an optical disk, etc. The memory 41 stores, for example, detection data, projection data, reconstructed images, CT images, etc. These data may be stored in an external memory with which the X-ray CT device 1 can communicate, instead of the memory 41 (or in addition to the memory 41). The external memory is controlled by a cloud server that manages the external memory, for example, by the cloud server accepting a read/write request. The external memory is realized, for example, by a system called a PACS (Picture Archiving and Communication Systems). A PACS is a system that systematically stores images captured by various imaging diagnostic devices.

Figure 2 is a diagram showing an example of data stored in memory 41. As shown in Figure 2, memory 41 stores information such as imaging conditions 41-1, detection data 41-2 generated by processing circuitry 50, projection data 41-3, reconstructed image 41-4, scan range 41-7, and trained model 41-8. Reconstructed image 41-4 can be classified, for example, into scanogram image 41-5 and actual captured image 41-6.

The display 42 displays various types of information. For example, the display 42 displays medical images (CT images) generated by the processing circuit, GUI (Graphical User Interface) images that accept various operations by the operator, and the like. The display 42 is, for example, a liquid crystal display, a CRT (Cathode Ray Tube), an organic EL (Electroluminescence) display, or the like. The display 42 may be provided on the pedestal device 10. The display 42 may be a desktop type, or may be a display device (for example, a tablet terminal) that can wirelessly communicate with the main body of the console device 40.

The input interface 43 accepts various input operations by the operator and outputs an electrical signal indicating the content of the accepted input operation to the processing circuit 50. For example, the input interface 43 accepts input operations such as collection conditions when collecting detection data or projection data (described later), reconstruction conditions when reconstructing a CT image, and image processing conditions when generating a post-processed image from a CT image. For example, the input interface 43 is realized by a mouse, keyboard, touch panel, trackball, switch, button, joystick, camera, infrared sensor, microphone, etc. The input interface 43 may be provided in the gantry device 10. The input interface 43 may also be realized by a display device (e.g., a tablet terminal) capable of wireless communication with the main body of the console device 40.

The network connection circuit 44 includes, for example, a network card having a printed circuit board, or a wireless communication module. The network connection circuit 44 implements an information communication protocol according to the type of the network to which it is connected. Networks include, for example, LANs (Local Area Networks), WANs (Wide Area Networks), the Internet, cellular networks, and dedicated lines.

The processing circuitry 50 controls the overall operation of the X-ray CT device 1. The processing circuitry 50 executes, for example, a system control function 51, a pre-processing function 52, a reconstruction processing function 53, an image processing function 54, a scan control function 55, a display control function 56, a learning function 57, a transfer function 58, and the like. The processing circuitry 50 realizes these functions, for example, by a hardware processor executing a program stored in the memory 41.

The hardware processor refers to a circuit such as a CPU, a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), a programmable logic device (e.g., a Simple Programmable Logic Device (SPLD) or a Complex Programmable Logic Device (CPLD), or a Field Programmable Gate Array (FPGA)). Instead of storing a program in the memory 41, the program may be directly embedded in the circuit of the hardware processor. In this case, the hardware processor realizes a function by reading and executing the program embedded in the circuit. The hardware processor is not limited to being configured as a single circuit, but may be configured as a single hardware processor by combining multiple independent circuits to realize each function. In addition, multiple components may be integrated into a single hardware processor to realize each function.

Each component of the console device 40 or the processing circuit 50 may be distributed and realized by multiple pieces of hardware. The processing circuit 50 may be realized by a processing device capable of communicating with the console device 40, rather than being a component of the console device 40. The processing device is, for example, a workstation connected to one X-ray CT device, or a device (e.g., a cloud server) connected to multiple X-ray CT devices and collectively executing processing equivalent to that of the processing circuit 50 described below.

The system control function 51 controls various functions of the processing circuit 50 based on the input operations received by the input interface 43.

The pre-processing function 52 performs pre-processing such as logarithmic conversion, offset correction, inter-channel sensitivity correction, and beam hardening correction on the detection data 41-2 output by the DAS 16 to generate projection data 41-3, and stores the generated projection data 41-3 in the memory 41.

The reconstruction processing function 53 performs reconstruction processing using a filtered backprojection method, an iterative reconstruction method, or the like on the projection data generated by the preprocessing function 52 to generate a reconstructed image 41-4, and stores the generated reconstructed image 41-4 in the memory 41.

The image processing function 54 converts the reconstructed image 41-4 into a three-dimensional image or cross-sectional image data of an arbitrary cross section by a known method based on the input operation received by the input interface 43. The conversion into a three-dimensional image may be performed by the pre-processing function 52.

The scan control function 55 controls the collection process of detection data in the gantry device 10 by issuing instructions to the X-ray high voltage device 14, the DAS 16, the control device 18, and the bed drive device 32. The scan control function 55 controls the operation of each part when taking the images to collect the scanograms 41-5 or the actual images 41-6, and when taking images to be used for diagnosis.

The display control function 56 controls the display mode of the display 42.

The learning function 57 learns the scan range 41-7. The detailed processing of the learning function 57 will be described later. The learning function 57 is an example of a "learning unit."

The transfer function 58 transfers a part or all of the captured reconstructed image 41-4 to the PACS. The transfer function 58 is an example of a "transfer unit."

With the above configuration, the X-ray CT device 1 scans the subject P in a manner such as helical scan, conventional scan, or step-and-shoot. Helical scan is a manner in which the subject P is scanned in a spiral manner by rotating the rotating frame 17 while moving the top plate 33. Conventional scan is a manner in which the subject P is scanned in a circular orbit by rotating the rotating frame 17 while the top plate 33 is stationary. A conventional scan is performed. Step-and-shoot is a manner in which the position of the top plate 33 is moved at regular intervals to perform a conventional scan in multiple scan areas.

Figure 3 is a configuration diagram of the scan control function 55. The scan control function 55 includes, for example, a scan image acquisition function 55-1, an automatic scan range setting function 55-2, a manual scan range setting function 55-3, and a scan execution function 55-4.

The scanogram acquisition function 55-1 acquires a scanogram 41-5 of the subject P to determine the scan range. Note that the scanogram is an example of an alignment image. Other examples of alignment images include scout images.

A method for acquiring a scanogram will now be described. The scanogram acquisition function 55-1 controls the control device 18 to fix the position of the X-ray tube 11 at a predetermined rotation angle, and to irradiate the subject P with X-rays from the X-ray tube 11 while moving the top plate 33 of the bed device 30 in the Z-axis direction. The scanogram acquisition function 55-1 acquires a two-dimensional scanogram 41-5 of the subject P from the detection data 41-2 acquired in this manner.

The method of acquiring the scanogram 41-5 is not limited to the above-mentioned method, and may be, for example, a method of acquiring projection data 41-3 of the entire circumference of the subject P by helical scanning or non-helical scanning. Here, the scanogram acquisition function 55-1 executes a scan at a lower dose than the actual imaging for a wide range such as the entire chest, entire abdomen, entire upper body, and entire body of the subject. The non-helical scan is, for example, a step-and-shoot scan. In this way, the scanogram acquisition function 55-1 collects detection data 41-2 of the entire circumference of the subject P, and the reconstruction processing function 53 reconstructs a three-dimensional reconstruction image 41-4 (volume data), and may generate a two-dimensional scanogram 41-5 according to any direction based on the reconstructed volume data. The scanogram 41-5 can also be treated as a three-dimensional scanogram 41-5 by using the above-mentioned volume data.

The scano image acquisition function 55-1 outputs a scano image acquired, for example, by one of the methods exemplified above, to the scan range automatic setting function 55-2. The scano image acquisition function 55-1 is an example of an "acquisition unit." Note that the "acquisition unit" is not limited to "generating and acquiring by itself" as in the above example, but may also "acquire from another functional unit."

The automatic scan range setting function 55-2 inputs the scan image output by the scan image acquisition function 55-1 and the shooting conditions into the trained model 41-8, sets the scan range 41-7 according to the resulting output information, and stores it in the memory 41.

The trained model 41-8 is trained, for example, by the learning function 57, as described below. The trained model 41-8 is trained to output a scan range when, for example, the imaging conditions of the subject (for example, some or all of the age, sex, body type, disease name, scan target area, examination conditions, and bed position conditions) are input. The scan target area includes, for example, the head, upper body, lungs, liver, etc. Examination conditions include, for example, initial imaging, follow-up observation imaging, etc. In this embodiment, the imaging conditions are input parameters, but the trained model 41-8 for each imaging condition is trained, and the automatic scan range setting function 55-2 may select the trained model 41-8 that matches the imaging conditions of the subject P and use it for the above processing. Furthermore, a trained model 41-8 for each first part of the imaging conditions is trained, and the second part of the imaging conditions is used as an input parameter, and the automatic scan range setting function 55-2 may select the trained model 41-8 that matches the first part of the imaging conditions of the subject P and use it for the above processing.

Figure 4 is a diagram for explaining the contents of the processing by the scan range automatic setting function 55-2. The scan range automatic setting function 55-2 outputs the scan range 41-7 of the subject P by inputting the imaging conditions 41-1 and the scan image 41-5 as parameters to the trained model 41-8. By performing subsequent processing based on this scan range 41-7, it is possible to shorten the time required for the scan planning from taking the scan image of the subject P to the actual imaging, compared to the case where the scan range is set manually from the beginning.

The automatic scan range setting function 55-2 stores the automatically set scan range 41-7 in the memory 41. The automatic scan range setting function 55-2 is an example of a "processing unit."

If there is no suitable trained model 41-8, the automatic scan range setting function 55-2 may omit the process of setting the scan range 41-7 and output the scanned image 41-5 to the manual scan range setting function 55-3.

The manual scan range setting function 55-3 accepts fine adjustments, redoing, new settings, etc. of the scan range by the operator. For example, the manual scan range setting function 55-3 reflects the fine adjustments input by the operator via the input interface 43 to the scan range 41-7 output by the automatic scan range setting function 55-2, and updates the scan range 41-7 in the memory 41.

In addition, the manual scan range setting function 55-3 redoes the scan range setting (or creates a new one) when the operator performs an operation indicating that the scan range 41-7 output by the automatic scan range setting function 55-2 is not to be adopted. In this case, the manual scan range setting function 55-3 sets the scan range 41-7 according to the operation input by the operator via the input interface 43 for the scan image 41-5 output by the scan image acquisition function 55-1 (for example, an input operation to display a frame indicating the scan range 41-7 on the scan image 41-5 on the display 42, move the position of the frame, or enlarge or reduce the size of the frame). The manual scan range setting function 55-3 overwrites the scan range 41-7 stored in the memory 41 with the set scan range 41-7. Similarly, even if the scan range automatic setting function 55-2 omits the process of setting the scan range 41-7, the scan range manual setting function 55-3 displays a frame line indicating the scan range 41-7 on the scan image 41-5, and sets the scan range 41-7 in response to input operations such as moving the position of the frame line, enlarging or reducing the size of the frame line, or reducing it by deleting an arbitrary percentage from the edge of the scan image 41-5. The scan range manual setting function 55-3 stores the scan range 41-7 set by fine-tuning, redoing, etc. in the memory 41. The scan range manual setting function 55-3 is an example of an "image processing unit."

The scan range automatic setting function 55-2 and the scan range manual setting function 55-3 may set the reconstruction range when reconstructing a CT image. In this case, the scan range automatic setting function 55-2 performs a predetermined calculation to convert the scan range 41-7 output by the trained model 41-8 into a reconstruction range, and causes the control device 18 to execute a scan based on the calculation result. At this time, the scan range 41-7 output by the trained model 41-8 may be wider than the reconstruction range. In addition, when the scan range automatic setting function 55-2 and the scan range manual setting function 55-3 set the reconstruction range, and when the trained model 41-8 has a trained model that outputs the reconstruction range, the trained model that outputs the reconstruction range may be used. In this case, the scan range manual setting function 55-3 sets the range expanded up, down, left, and right as the scan range 41-7.

The scan execution function 55-4 controls the control device 18 to perform actual photographing within the range defined by the scan range 41-7 stored in the memory 41 and obtain the actual photographed image 41-6 (scanned image).

A flag or the like may be set in the scan range 41-7 to identify whether the scan range was adopted as a result of automatic setting by the scan range automatic setting function 55-2 or whether it was manually set by the scan range manual setting function 55-3.

The learning function 57 acquires sets of scanograms, imaging conditions, and scan ranges for multiple subjects from the memory 41 or an external device. The learning function 57 uses the acquired scanograms and imaging conditions including information about the areas to be scanned as learning data, and generates a trained model 41-8 by performing machine learning using scanograms set for the same subjects as teacher data. The learning function 57 is an example of a "model generation unit."

The learning function 57 may also be realized by an external device. In this case, the transfer function 58 may transfer at least the scano image 41-5 to be transferred and the scan range 41-7 corresponding to the scano image 41-5, so as to be used for learning. The transfer function 58 may also transfer the reconstruction range of the reconstructed image 41-4 generated based on the scano image 41-5 to be transferred, so as to be used for learning.

Figure 5 is a diagram for explaining the processing of the learning function 57. The learning function 57 inputs multiple sets of learning data to a machine learning model in which connection information and the like are defined in advance and parameters such as connection coefficients are provisionally set, and adjusts the parameters in the machine learning model so that the results approach the teacher data corresponding to the learning data. Shooting conditions and scano images are input to the machine learning model.

The shooting conditions input to the machine learning model are, for example, the shooting conditions described above.

The scanograms input to the machine learning model may include, for example, information set during the examination (e.g., the reconstruction range in the body axis direction, and information on the region of interest (ROI) setting during image reconstruction).

The learning function 57 adjusts the parameters of the machine learning model, for example, by backpropagation. The machine learning model is, for example, a deep neural network (DNN) that uses a convolution neural network (CNN). Note that the machine learning model may perform weighting settings for each piece of learning data so that newer learning data is more easily reflected as output.

The learning function 57 ends the process when it has completed learning a predetermined number of sets of learning data and the corresponding teacher data. The machine learning model at that point is stored as the trained model 41-8.

A scano image may be captured multiple times from the same or similar directions, for example, when an artifact is detected and re-capture is required. Therefore, the learning function 57 can generate a more suitable trained model by learning only from the scano images (i.e., success cases) transferred by the transfer function 58 and updating the trained model to reflect the results of the scan range setting process by the scan control function 55. In this case, the learning function 57 may generate a more accurate trained model by extracting the range obtained as the reconstructed image 41-4 from the scano images of the success cases transferred by the transfer function 58 and using it as the learning object.

In addition, the scan images used in the scan plan may be multiple images taken at two or more different angles, and the learning function 57 may generate a trained model from some of these images, or may generate a trained model from all of the images.

The trained model 41-8 used by the learning function 57, or the training data and teacher data used by the learning function 57, may be generated by another X-ray CT device 1.

6 and 7 are diagrams for explaining an example of the usage environment of the X-ray CT device 1. The trained model generated by another X-ray CT device 1 or learning device, or the training data and teacher data used by the training function 57, are provided, for example, by a service representative MP of the manufacturer of the X-ray CT device 1 to a facility H1 using the X-ray CT device 1 as shown in FIG. 6. In addition, the trained model generated by another X-ray CT device 1, or the training data and teacher data used by the training function 57, may be shared by a cloud server C or the like via an external network NW by a plurality of facilities H1 to HN (N is any natural number) using the X-ray CT device 1 as shown in FIG. 7. The cloud server C may exclusively perform training similar to that of the training function 57.

Figure 8 is a flowchart showing an example of the flow of imaging processing by the X-ray CT device 1.

First, the console device 40 accepts input of information identifying the subject P and imaging conditions (step S100), and accepts settings for the imaging (for example, an operation to move the tabletop 33 of the bed device 30 to the imaging start position) (step S102). Next, the control device 18 controls the gantry device 10 to capture a scanogram 41-5 (step S104).

Next, the imaging conditions and the scan image, which are input parameters, are input to the trained model 41-8 (step S106), and the scan range 41-7, which is the output of the trained model, is displayed on the display 42 (step S108). Note that if there are multiple trained models 41-8 applied in step S106, multiple patterns of the scan range 41-7 may be displayed in step S108, or the most suitable trained model 41-8 may be selected in step S106.

Next, the input interface 43 accepts input of the decision made by the operator of the X-ray CT device 1 as to whether to adopt the scan range 41-7 displayed in step S108, or to have the operator manually redo the scan range setting without adopting the scan range 41-7 (step S110). When the operator manually sets the scan range, the scan range manual setting function 55-3 accepts the scan range setting made via the input interface 43 (step S112). When the scan range displayed in step S110 is adopted, the process proceeds to step S114, which will be described later.

The manual scan range setting function 55-3 accepts final fine adjustments made manually by the operator (step S114). Next, the scan execution function 55-4 performs the actual imaging (step S116).

Then, the transfer function 58 transfers the actual captured image 41-6, which is the result of the shooting, to a PACS or the like (step S118). Next, the learning function 57 generates a trained model 41-8 based on the scanogram and shooting conditions (e.g., reconstruction range, etc.). Alternatively, the learning function 57 reflects the scanogram and shooting conditions in the trained model (step S120). The details of the processing of step S120 will be described later. This concludes the explanation of this flowchart.

Figure 9 is a flowchart showing an example of the flow of the learning process by the learning function 57. The process flow shown in Figure 9 corresponds to the detailed process of step S120 in Figure 8. The flowchart in Figure 9 may be performed each time the X-ray CT device 1 finishes imaging one subject, or each time imaging is performed in which the scan range is redone by manual operation by the operator as described above (each time step S112 is executed).

First, the learning function 57 acquires a set of learning data, which is a scano image and shooting conditions (step S200). Next, the learning function 57 inputs the set of learning data acquired in step S200 into a machine learning model (step S202), and back-propagates errors from the teacher data corresponding to the set of learning data (step S204).

Next, the learning function 57 determines whether or not the processing of steps S202 and S204 has been performed for a predetermined number of sets of learning data (step S206). If the processing of steps S202 and S204 has not been performed for the predetermined number of sets of learning data, the learning function 57 returns to the process of step S200. If the processing of steps S202 and S204 has been performed for the predetermined number of sets of learning data, the learning function 57 determines the trained model 41-8 using the parameters at that time (step S208), and ends the processing of this flowchart. Note that in step S206, if the processing cannot continue because the predetermined number of sets of learning data do not exist, the subsequent processing may be reduced.

The X-ray CT device 1 of the first embodiment described above includes a scan image acquisition function 55-1 that acquires information about the area to be scanned and a scan image of the subject P, and a trained model 41-8 that outputs the scan range of the subject during scanning based on the information about the area to be scanned and the scan image of the subject P. The trained model 41-8 is equipped with a scan range automatic setting function 55-2 that inputs information about the area to be scanned and the scan image of the subject P acquired by the scan image acquisition function 55-1 and outputs the information about the area to be scanned and the scan range 41-7 related to the subject P related to the acquired information about the area to be scanned and the scan image of the subject P. This makes it possible to easily align the subject's position during imaging.

Second Embodiment
The X-ray CT apparatus 1A of the second embodiment will be described below. In the following description, the same components and functions as those of the first embodiment are given the same reference numerals as those of the first embodiment, and detailed description will be omitted. In addition, components with the same names as those of the first embodiment but different components or functions are given the reference numerals with the suffix "A".

Figure 10 is a diagram for explaining the gantry 10A according to the second embodiment. Compared to the gantry 10 of the first embodiment, the gantry 10A further includes a camera 19. The camera 19 captures an image of a space including the subject P and obtains an optical image 41-9. The camera 19 may be installed in a location other than the gantry 10, for example, in a position where the entire bed device 30 can be captured (for example, on the ceiling of a room in which the X-ray CT device 1A is installed, or in the vicinity of the bed device 30).

FIG. 11 is a diagram showing an example of data stored in memory 41A according to the second embodiment. Compared to memory 41 according to the first embodiment, memory 41A further stores optical image 41-9.

Figure 12 is a configuration diagram of a scan control function 55A according to the second embodiment. Compared to the scan control function 55 of the first embodiment, the scan control function 55A further includes an optical image acquisition function 55-5.

The optical image acquisition function 55-5 acquires the optical image 41-9 captured by the camera 19 and the imaging conditions 41-1 associated with the subject P appearing in the optical image, and outputs them to the scan range automatic setting function 55-2A. The optical image acquisition function 55-5 is another example of an "acquisition unit."

The automatic scan range setting function 55-2A inputs the optical image output by the optical image acquisition function 55-5 and the shooting conditions into the trained model 41-8A, sets the scan range 41-7 according to the resulting output information, and stores it in the memory 41.

The automatic scan range setting function 55-2A accepts adjustments, redoing, new settings, etc. of the scan range by the operator. When the automatic scan range setting function 55-2A accepts an operation indicating that the scan range is adopted, the actual shooting is performed after reflecting the contents of the fine adjustments input by the operator via the input interface 43. This fine adjustment is performed by the manual scan range setting function 55-3. When the automatic scan range setting function 55-2A accepts a process indicating redoing, new settings, etc., that is, a process indicating that the scan range based on the optical image is not adopted, the optical image may be reacquired, or a process for acquiring a scano image may be performed. The automatic scan range setting function 55-2A is another example of a "processing unit".

FIG. 13 is a diagram for explaining the processing performed by the scan range automatic setting function 55-2A. The scan range automatic setting function 55-2A outputs the scan range 41-7 of the subject P by inputting the information on the inspection conditions included in the imaging conditions 41-1 and the optical image 41-9 as parameters to the trained model 41-8. By performing subsequent processing based on this scan range 41-7, it is possible to shorten the time required for the scan planning from the scanogram capture of the subject P to the actual capture.

The learning function 57A generates a learned model that uses optical images and shooting conditions as learning data in addition to a learned model that uses scano images and shooting conditions as learning data. The learning function 57A acquires sets of optical images, shooting conditions, and scan ranges for multiple subjects from the memory 41 or an external device. The learning function 57A generates a learned model 41-8 by performing machine learning using the acquired optical images and shooting conditions including information about the area to be scanned as learning data and the scan range set for the same subject as teacher data.

FIG. 14 is a diagram for explaining the processing of the learning function 57A. The learning function 57A inputs multiple sets of learning data to a machine learning model in which connection information and the like are defined in advance and parameters such as connection coefficients are provisionally set, and adjusts the parameters in the machine learning model so that the result approaches the teacher data corresponding to the learning data. The shooting conditions and optical images are input to the machine learning model. The learning function 57A ends the processing when it has learned a predetermined number of sets of learning data and the corresponding teacher data. The machine learning model at that point is stored as the trained model 41-8A.

The generation of the scan range based on the optical image by the scan range automatic setting function 55-2A and the generation of the scan range based on the scanogram image may be used together. For example, the scan range automatic setting function 55-2A sets the scan range in the X-axis direction based on the output of the trained model of the scanogram image, and sets the scan range in the Y-axis direction based on the output of the trained model of the optical image as a substitute for the scanogram image. This makes it possible to reduce the amount of radiation exposure of the operator of the X-ray CT device 1A and the subject P.

Figure 15 is a flowchart showing an example of the flow of imaging processing by the X-ray CT device 1A. Note that steps S300 and S302 in the flowchart of Figure 15 correspond to steps S100 and S102 in the flowchart of Figure 7. Also, steps S312 to S328 in the flowchart of Figure 15 correspond to steps S104 to S120 in the flowchart of Figure 7.

First, the console device 40 accepts input of information identifying the subject P and imaging conditions (step S300), and accepts the settings for the imaging (step S302). Next, the optical image acquisition function 55-5 acquires an optical image captured by the camera 19 (step S304). Next, the optical image is applied to the trained model (step S306), and a scan range based on the trained model is displayed on the display 42 (step S308). Note that if there are multiple trained models applied in step S306, multiple patterns of scan ranges may be displayed in step S308, or the most suitable trained model may be selected in step S36.

Then, the input interface 43 accepts input of the decision made by the operator of the X-ray CT device 1A as to whether to adopt the scan range displayed in step S308 or to take a scan image and set the scan range (step S310). If an operation indicating that the displayed scan range is adopted is accepted, the process proceeds to step S322, which will be described later. If the control device 18 accepts an operation indicating that a scan image is to be taken, the control device 18 controls the gantry device 10 to take a scan image (step S312).

Next, the scan range automatic setting function 55-2A inputs the shooting conditions and the scan image, which are input parameters, to the trained model (step S314), and displays the scan range, which is the output of the trained model, on the display 42 (step S316). Note that if there are multiple trained models applied in step S314, multiple patterns of the scan range may be displayed in step S316, or the most suitable trained model may be selected in step S314.

Next, the input interface 43 accepts input of the decision made by the operator of the X-ray CT device 1A as to whether to adopt the scan range setting displayed in step S316 or to manually redo the scan range setting (step S318). If the operator manually redoes the scan range setting, the automatic scan range setting function 55-2A accepts the scan range setting made via the input interface 43 (step S320). If the scan range displayed in step S316 is adopted, the process proceeds to step S322, which will be described later.

The automatic scan range setting function 55-2A accepts final fine adjustments made manually by the operator (step S322). Next, the control device 18 performs the actual imaging (step S324).

Next, the transfer function 58 transfers the actual captured image, which is the result of the capture, to a PACS or the like (step S326). Next, the learning function 57A generates a trained model including the scanogram or optical image and the capture conditions. Alternatively, the learning function 57A reflects the scanogram or optical image and the capture conditions in the trained model (step S328). The details of the process of step S328 will be described later. This concludes the explanation of this flowchart.

Figure 16 is a flowchart showing an example of the flow of the learning process of optical images by the learning function 57A. The combination of the flowchart shown in Figure 9 and the flowchart shown in Figure 16 corresponds to the detailed processing of step S328 in Figure 15. The flowchart in Figure 16 may be performed each time the X-ray CT device 1 finishes imaging one subject, or may be performed each time imaging is performed in which the scan range is redone by manual operation by the operator as described above (each time step S320 is executed).

First, the learning function 57A acquires an optical image and shooting conditions, which are a set of learning data (step S400). Next, the learning function 57A inputs the set of learning data into a machine learning model (step S402) and back-propagates errors from the teacher data corresponding to the set of learning data (step S404).

Next, the learning function 57A determines whether or not the processing of steps S402 and S404 has been performed for a predetermined number of sets of learning data (step S406). If the processing of steps S402 and S404 has not been performed for the predetermined number of sets of learning data, the learning function 57A returns to the process of step S400. If the processing of steps S402 and S404 has been performed for the predetermined number of sets of learning data, the learning function 57A determines the trained model 41-8 using the parameters at that time (step S408), and ends the processing of this flowchart. Note that in step S406, if the processing cannot continue because the predetermined number of sets of learning data do not exist, the subsequent processing may be reduced.

The second embodiment described above not only achieves the same effects as the first embodiment, but also increases the possibility of reducing the number of scano images taken compared to the first embodiment by generating a scan range based on an optical image using the scan range automatic setting function 55-2A, thereby increasing the possibility of reducing the amount of radiation exposure of the operator of the X-ray CT device 1A and the subject P.

The above-described embodiment can be expressed as follows.
A storage device for storing programs;
a processor;
The processor executes the program,
Obtaining information about the area to be scanned and an alignment image of the subject;
a trained model that outputs a scan range of the subject during scanning based on information about a scan target portion and a registration image of the subject, and outputs a scan range of the subject related to the acquired information about the scan target portion and the registration image of the subject by inputting the acquired information about the scan target portion and the registration image of the subject into the trained model that outputs a scan range of the subject related to the acquired information about the scan target portion and the registration image of the subject;
The medical image diagnostic apparatus is configured as follows.

According to at least one of the embodiments described above, the imaging condition information (41-1) including information on the part to be scanned, the acquisition unit (55-1, 55-5) that acquires the image (41-4, 41-9) for identifying the scan range of the subject, and the processing unit (55-2, 55-2A) that inputs the imaging condition information and the image for identifying the scan range of the subject to the trained model (41-8) based on the imaging condition information and the image for identifying the scan range of the subject, and outputs the scan range of the subject during the scan, can easily align the imaging position of the subject during imaging.

Although several 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 forms, and various reductions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are within the scope of the invention and its equivalents as set forth in the claims, as well as the scope and spirit of the invention.

1, 1A...X-ray CT device 10, 10A...Gantt device 11...X-ray tube 12...Wedge 13...Collimator 14...X-ray high voltage device 15...X-ray detector 16...Data acquisition system 17...Rotating frame 18...Control device 19...Camera 30...Cedent device 31...Base 32...Cedent drive device 33...Top plate 34...Support frame 40...Console device 50...Processing circuit 51...System control function 52...Pre-processing function 53...Reconstruction processing function 54...Image processing function 55, 55A...Scan control function 55-1...Scano image acquisition function 55-2, 55-2A...Automatic scan range setting function 55-3...Manual scan range setting function 55-4...Scan execution function 55-5...Optical image acquisition function 56...Display control function 57, 57A...Learning function 58...Transfer function

Claims (1)

an acquisition unit that acquires information about a region to be scanned and an alignment image of a subject;
a processing unit that outputs a scan range of a subject during scanning based on information about a scan target portion and an aligned image of the subject by inputting the acquired information about the scan target portion and the aligned image of the subject to a trained model that outputs the scan range of the subject during scanning based on the information about the scan target portion and an aligned image of the subject;
A medical image diagnostic apparatus comprising:

Images