JP2022172850A - Medical image diagnostic device, method for determining medical imaging condition, and program - Google Patents

Abstract

To acquire a medical image that enables highly accurate diagnosis to be executed while causing imaging and analyzing to influence each other.SOLUTION: A medical image diagnostic device includes an acquisition unit and a determination unit. The acquisition unit acquires a medical image of a subject. When the medical image is input, the determination unit determines an imaging condition for the medical image of the subject on the basis of a model learned to output an examination result of a person included in the input medical image, and a map in which a degree of contribution to the examination result is associated with each position on the input medical image, and the medical image of the subject acquired by the acquisition unit.SELECTED DRAWING: Figure 2

Description

The embodiments disclosed in the specification and drawings relate to a medical image diagnostic apparatus, a method for determining medical imaging conditions, and a program.

In today's clinical practice, imaging staff optimize imaging protocols to obtain the highest quality medical images. The analysis staff is trying to obtain medical information from given medical images. That is, the acquisition and analysis of medical images tend to be performed independently of each other. For this reason, even if AI (Artificial Intelligence) for analyzing medical images achieves remarkable development in the future, it is expected that it will hardly affect the imaging side.

On the other hand, research and development and clinical application of image analysis AI, which outputs diagnostic information when a medical image is input, are progressing. In relation to this, there is known a technique for estimating which part of the information in the input image contributes greatly to the final output result.

Fei Wang, Mengqing Jiang, Chen Qian, Shuo Yang, Cheng Li, Honggang Zhang, Xiaogang Wang, Xiaoou Tang “Residual Attention Network for Image Classification”, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 21-26 July 2017 , DOI 10.1109/CVPR.2017.683 Grzegorz Jacenkow, Alison Q. O'Neil, Brian Mohr, Sotirios A. Tsaftaris “Steering Spatial Attention with Non-Imaging Information in CNNs”, Medical Image Computing and Computer Assisted Intervention - MICCAI 2020, 23rd International Conference, Lima, Peru, October 4-8, 2020, Proceedings, Part IV (pp.385-395), DOI 10.1007/978-3-030-59719-1_38

The problem to be solved by the embodiments disclosed in this specification and drawings is to obtain a medical image that enables highly accurate diagnosis while mutually affecting imaging and analysis. However, the problems to be solved by the embodiments disclosed in this specification and drawings are not limited to the above problems. A problem corresponding to each effect of each configuration shown in the embodiments described later can be positioned as another problem.

A medical image diagnostic apparatus according to an embodiment has an acquisition unit and a determination unit. The acquisition unit acquires a medical image of the subject. When a medical image is input, the determining unit associates a medical result of a person included in the input medical image and a degree of contribution to the medical result with each position on the input medical image. Imaging conditions for the medical image of the subject are determined based on the model trained to output the map and the medical image of the subject acquired by the acquisition unit.

1 is a diagram showing a configuration example of a medical image diagnostic system 1 according to an embodiment; FIG. 1 is a diagram showing a configuration example of an X-ray CT apparatus 100 according to an embodiment; FIG. 1 is a diagram showing a configuration example of a learning device 200 according to an embodiment; FIG. 4 is a flow chart showing a series of processing during training by the medical image diagnostic system 1 according to the embodiment. FIG. 4 is a diagram for explaining a method of obtaining a contribution map during training; 4 is a flow chart showing the flow of a series of runtime processes by the medical image diagnostic system 1 according to the embodiment. FIG. 4 is a diagram schematically showing a method of determining imaging conditions using a contribution map; FIG. 4 is a diagram schematically showing a method of determining imaging conditions using a contribution map; FIG. 4 is a diagram schematically showing a method of determining imaging conditions using a contribution map; FIG. 4 is a diagram for explaining a method of aligning contribution maps; FIG. 4 is a diagram for explaining a method of aligning contribution maps; FIG. 4 is a diagram for explaining a method of aligning contribution maps; FIG. 4 is a diagram for explaining a method of aligning contribution maps; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions; FIG. 4 is a diagram for explaining a method of determining imaging conditions;

A medical image diagnostic apparatus, a method for determining medical imaging conditions, and a program according to embodiments will be described below with reference to the drawings.

[Configuration of medical image diagnostic system]
FIG. 1 is a diagram showing a configuration example of a medical image diagnostic system 1 according to an embodiment. The medical image diagnostic system 1 includes, for example, one or more medical imaging devices 100 and a learning device 200 . The medical imaging apparatus 100 and the learning apparatus 200 are communicably connected via a communication network NW.

The communication network NW means all information communication networks using telecommunication technology. The communication network NW includes a wireless/wired LAN such as a hospital backbone LAN (Local Area Network), an Internet network, a telephone communication network, an optical fiber communication network, a cable communication network, a satellite communication network, and the like.

The medical imaging apparatus 100 is an apparatus that scans a subject P to generate a medical image. The subject P is, for example, a human patient, but is not limited to this, and may be an animal or an inorganic substance. The medical imaging apparatus 100 may be, for example, an X-ray CT (Computed Tomography) apparatus, an MRI (Magnetic Resonance Imaging) apparatus, an ultrasonic diagnostic imaging apparatus, a nuclear medicine diagnostic apparatus, or the like. . The medical imaging apparatus 100 is a so-called modality. As an example, the medical imaging apparatus 100 will be described below as an X-ray CT apparatus.

The learning device 200 acquires medical images from an X-ray CT apparatus (medical imaging apparatus) 100, uses the acquired medical images to learn a machine learning model, and uses the learned model to acquire medical images. to analyze. Details of the model will be described later. The learning device 200 may be a workstation or cloud server connected to the modality, the X-ray CT apparatus 100 .

[Configuration of X-ray CT apparatus]
FIG. 2 is a diagram showing a configuration example of the X-ray CT apparatus 100 according to the embodiment. The X-ray CT apparatus 100 includes, for example, a gantry device 110, a bed device 130, and a console device 140. For convenience of explanation, FIG. 2 shows both a view of the gantry device 110 viewed from the Z-axis direction and a view of the gantry device 110 viewed from the X-axis direction. In the embodiment, the rotation axis of the rotating frame 117 in the non-tilt state or the longitudinal direction of the top plate 133 of the bed device 130 is defined as the Z-axis direction, and the axis perpendicular to the Z-axis direction and horizontal to the floor surface is defined as the Z-axis direction. The X-axis direction and the direction perpendicular to the Z-axis direction and perpendicular to the floor surface are defined as the Y-axis direction.

The gantry device 110 includes, for example, an X-ray tube 111, a wedge 112, a collimator 113, an X-ray high voltage device 114, an X-ray detector 115, and a data acquisition system (DAS: Data Acquisition System) 116. , a rotating frame 117 and a controller 118 .

The X-ray tube 111 generates X-rays by applying a high voltage from the X-ray high voltage device 114 and irradiating thermal electrons from a cathode (filament) toward an anode (target). X-ray tube 111 includes a vacuum tube. For example, the X-ray tube 111 is a rotating anode type X-ray tube that generates X-rays by irradiating a rotating anode with thermal electrons.

The wedge 112 is a filter for adjusting the dose of X-rays irradiated from the X-ray tube 111 to the subject P. FIG. The wedge 112 attenuates the X-rays passing through itself so that the X-ray dose distribution irradiated from the X-ray tube 111 to the subject P becomes a predetermined distribution. Wedge 112 is also called a wedge filter or a bow-tie filter. The wedge 112 is, for example, processed aluminum so as to have a predetermined target angle and a predetermined thickness.

The collimator 113 is a mechanism for narrowing down the irradiation range of X-rays transmitted through the wedge 112 . The collimator 113 narrows down the X-ray irradiation range by, for example, forming a slit by combining a plurality of lead plates. Collimator 113 is sometimes called an X-ray diaphragm.

The X-ray high voltage device 114 has, for example, a high voltage generator and an X-ray controller. The high voltage generator has an electric circuit including a transformer, a rectifier, etc., and generates a high voltage to be applied to the X-ray tube 111 . The X-ray controller controls the output voltage of the high voltage generator in accordance with the amount of X-rays to be generated by the X-ray tube 111 . The high voltage generator may be one that boosts the voltage with the transformer described above, or one that boosts the voltage with an inverter. The X-ray high-voltage device 114 may be provided on the rotating frame 117 or may be provided on the fixed frame (not shown) side of the gantry device 110 .

The X-ray detector 115 detects the intensity of X-rays generated by the X-ray tube 111 and incident through the subject P. FIG. The X-ray detector 115 outputs to the DAS 116 an electrical signal (which may be an optical signal or the like) corresponding to the intensity of the detected X-rays. The X-ray detector 115 has, for example, multiple X-ray detection element arrays. Each of the multiple X-ray detection element arrays has multiple X-ray detection elements arranged in the channel direction along an arc centered on the focal point of the X-ray tube 111 . A plurality of X-ray detection element arrays are arranged in a slice direction (column direction, row direction).

X-ray detector 115 is, for example, an indirect detector having a grid, a scintillator array, and a photosensor array. The scintillator array has a plurality of scintillators. Each scintillator has a scintillator crystal. The scintillator crystal emits an amount of light corresponding to the intensity of incident X-rays. The grid has an X-ray shielding plate arranged on the surface of the scintillator array on which X-rays are incident and having a function of absorbing scattered X-rays. Note that the grid may also be called a collimator (one-dimensional collimator or two-dimensional collimator). The photosensor array has photosensors such as, for example, photomultiplier tubes (photomultipliers: PMTs). The photosensor array outputs an electrical signal corresponding to the amount of light emitted by the scintillator. The X-ray detector 115 may be a direct conversion detector having a semiconductor element that converts incident X-rays into electrical signals.

DAS 116 includes, for example, amplifiers, integrators, and A/D converters. The amplifier amplifies the electrical signal output from each X-ray detection element of the X-ray detector 115 . The integrator integrates the amplified electrical signal over a view period (described later). The A/D converter converts an electrical signal representing the result of integration into a digital signal. The DAS 116 outputs detection data based on digital signals to the console device 140 . Detected data is a digital value of x-ray intensity identified by the channel number of the x-ray detector element from which it was generated, the row number, and the view number indicating the acquired view. The view number is a number that changes according to the rotation of the rotating frame 117, and is a number that is incremented according to the rotation of the rotating frame 117, for example. Therefore, the view number is information indicating the rotation angle of the X-ray tube 111 . A view period is a period that falls between the rotation angle corresponding to a certain view number and the rotation angle corresponding to the next view number. The DAS 116 may detect view switching by a timing signal input from the control device 118, by an internal timer, or by a signal obtained from a sensor (not shown). . When X-rays are continuously emitted from the X-ray tube 111 when performing a full scan, the DAS 116 collects detection data groups for the entire circumference (360 degrees). When X-rays are continuously emitted from the X-ray tube 111 when half scanning is performed, the DAS 116 collects detection data for a half circumference (180 degrees).

The rotating frame 117 is an annular rotating member that rotates the X-ray tube 111, the wedge 112, the collimator 113, and the X-ray detector 115 while holding them facing each other. The rotating frame 117 is supported by a fixed frame so as to be rotatable around the subject P introduced therein. Rotating frame 117 also supports DAS 116 . The detected data output by DAS 116 is transmitted by optical communication from a transmitter having a light emitting diode (LED) mounted on rotating frame 117 to a photodiode mounted on a non-rotating portion (e.g., fixed frame) of mounting assembly 110. It is sent to the receiver and transferred to the console device 140 by the receiver. The method of transmitting the detection data from the rotating frame 117 to the non-rotating portion is not limited to the above-described method using optical communication, and any non-contact transmission method may be employed. The rotating frame 117 is not limited to an annular member, and may be a member such as an arm as long as it can support and rotate the X-ray tube 111 or the like.

The control device 118 has, for example, a processing circuit having a processor such as a CPU (Central Processing Unit), and a driving mechanism including a motor, an actuator, and the like. The control device 118 receives input signals from the console device 140 or the input interface 143 attached to the gantry device 110 and controls the operations of the gantry device 110 and the bed device 130 .

The control device 118 rotates the rotating frame 117, tilts the gantry device 110, and moves the top plate 133 of the bed device 130, for example. When tilting the gantry device 110 , the control device 118 rotates the rotating frame 117 about an axis parallel to the Z-axis direction based on the tilt angle (tilt angle) input to the input interface 143 . The control device 118 grasps the rotation angle of the rotating frame 117 from the output of a sensor (not shown) or the like. Controller 118 also provides the rotation angle of rotating frame 117 to processing circuit 150 at any time. The control device 118 may be provided in the gantry device 110 or may be provided in the console device 140 .

The control device 118 causes the gantry device 110 to move along the moving rails to perform main scan photography, or to perform scanography, which is positioning photography performed before execution of main scan photography.

The bed device 130 is a device on which the subject P to be scanned is placed and introduced into the rotating frame 117 of the gantry device 110 . The bed device 130 has, for example, a base 131 , a bed driving device 132 , a top board 133 and a support frame 134 . The base 131 includes a housing that supports the support frame 134 so as to be movable in the vertical direction (Y-axis direction). The bed driving device 132 includes motors and actuators. The bed driving device 132 moves the tabletop 133 on which the subject P is placed in the longitudinal direction (Z-axis direction) of the tabletop 133 along the support frame 134 . The top plate 133 is a plate-like member on which the subject P is placed.

Console device 140 has, for example, memory 141 , display 142 , input interface 143 , communication interface 144 , and processing circuitry 150 . In this embodiment, the console device 140 is described as being separate from the gantry device 110 , but the gantry device 110 may include part or all of each component of the console device 140 . The console device 140 is an example of a “medical image diagnostic device”.

The memory 141 is implemented by, for example, a RAM (Random Access Memory), a semiconductor memory device such as a flash memory, a hard disk, an optical disk, or the like. The memory 141 may also include a storage medium such as a ROM (Read Only Memory) and a register. The memory 208 may also include a storage medium such as a ROM (Read Only Memory) and a register.

The memory 141 stores, for example, detection data, projection data, reconstructed images, and the like. These data may be stored not in the memory 141 (or in addition to the memory 141) but in an external memory (for example, NAS (Network Attached Storage) or the like) with which the X-ray CT apparatus 100 can communicate.

In addition, memory 141 stores model information. Model information is information (program or data structure) that defines a trained model MDL. The learned model MDL is typically a model that has been learned so that when a medical image of a certain subject P is input, the medical results of the subject P and a contribution map are output.

The medical result may indicate, for example, whether the subject P has a specific disease or not, or the probability of having the specific disease (likelihood of having a specific disease). may be represented. For example, if the imaging region is the heart, the specific disease may be heart valve disease.

Moreover, the diagnostic results are not limited to the above, and may represent, for example, measured values such as cancer growth rate and rehabilitation success rate, or represent comparative values such as the degree of non-matching between medical images and other examinations. Alternatively, it may represent a prediction result such as prognosis prediction or treatment side effect prediction, or may represent a derived analysis result thereof. In other words, the medical care results according to this embodiment may include all events that can be output by the learned model MDL.

The contribution map is two-dimensional or more data in which the degree of contribution to the medical result is associated with each position on the medical image input to the trained model MDL. For example, on a medical image, it means that a position (area) with a higher degree of contribution has a greater influence on the medical result. In other words, from the point of view of the learned model MDL, it means that a position (area) with a higher degree of contribution is paid more attention to when judging the medical treatment result.

The trained model MDL may be implemented by, for example, a DNN (Deep Neural Network(s)) such as a CNN (Convolutional Neural Network). Such a DNN includes an attention mechanism for obtaining the contribution map described above.

An attention mechanism is, for example, a neural network that changes how to pay attention to each pixel in a medical image according to where the pixel is located in the entire image. For example, the attention mechanism multiplies each pixel on the feature map output from the convolutional layer of the CNN by different weights to determine the degree of attention (that is, attention) for each pixel. .

Also, the trained model MDL is not limited to a DNN that includes an attention mechanism, and may be implemented by other models and algorithms such as support vector machines, decision trees, naive Bayes classifiers, and random forests.

When the learned model MDL is implemented by a DNN, the model information includes, for example, the input layer, one or more hidden layers (intermediate layers), and the units (units or nodes ) are combined with each other, and weighting information such as how many coupling coefficients are given to data input/output between the combined units. The connection information includes, for example, the number of units included in each layer, information specifying the type of unit to which each unit is connected, an activation function that realizes each unit, information such as a gate provided between units in the hidden layer. including. The activation function that realizes the unit may be, for example, a ReLU (Rectified Linear Unit) function, an ELU (Exponential Linear Units) function, a clipping function, a sigmoid function, a step function, a hyperpolic tangent function, an identity function, or the like. . A gate selectively passes or weights data communicated between units, for example, depending on the value (eg, 1 or 0) returned by an activation function. A coupling coefficient includes, for example, a weight given to output data when data is output from a unit in a certain layer to a unit in a deeper layer in a hidden layer of a neural network. The coupling coefficients may also include bias components unique to each layer, and the like.

The display 142 displays various information. For example, the display 142 displays a CT image generated by the processing circuit 150, a GUI (Graphical User Interface) for receiving various operations by an operator (for example, a doctor), and the like. The display 142 is, for example, an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube) display, an organic EL (Electro Luminescence) display, or the like. The display 142 may be provided on the gantry device 110 . The display 142 may be of a desktop type, or may be a display device capable of wireless communication with the main body of the console device 140 (for example, a tablet terminal).

The input interface 143 accepts various input operations by an operator (for example, a doctor) and outputs an electrical signal indicating the content of the accepted input operation to the processing circuit 150 . For example, the input interface 143 receives input operations such as an imaging protocol for imaging the subject P, reconstruction conditions for reconstructing a CT image, and image processing conditions for generating a post-processed image from a CT image. . For example, the input interface 143 is implemented by a mouse, keyboard, touch panel, drag ball, switch, button, joystick, foot pedal, camera, infrared sensor, microphone, and the like. The input interface 143 may be provided on the gantry device 110 . Also, the input interface 143 may be realized by a display device (for example, a tablet terminal) capable of wireless communication with the main body of the console device 140 . It should be noted that the input interface 143 in this specification is not limited to those having physical operation parts such as a mouse and a keyboard. For example, the input interface 143 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs the electrical signal to the control circuit.

The communication interface 144 includes, for example, a NIC (Network Interface Card), a wireless communication module, and the like. Communication interface 144 communicates with learning device 200 and other external devices via communication network NW.

Processing circuit 150 controls the overall operation of X-ray CT apparatus 100 . The processing circuit 150 executes, for example, a system control function 151, an imaging condition determination function 152, a preprocessing function 153, a reconstruction processing function 154, an image processing function 155, an output control function 156, and the like. The processing circuit 150 implements these functions by executing a program stored in the memory 141 by a hardware processor, for example. The preprocessing function 153 and the reconstruction processing function 154 are examples of the "acquisition unit". The imaging condition determination function 152 is an example of a "determination unit".

A hardware processor is, for example, a CPU, a GPU (Graphics Processing Unit), an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (Simple Programmable Logic Device; SPLD) or Circuitry such as Complex Programmable Logic Device (CPLD), Field Programmable Gate Array (FPGA)).

Instead of storing the program in the memory 141, the program may be directly embedded in the circuitry of the hardware processor. In this case, the hardware processor realizes its function by reading and executing the program embedded in the circuit. The above program may be stored in the memory 141 in advance, or may be stored in a non-temporary storage medium such as a DVD or CD-ROM. ), it may be installed in the memory 141 from a non-transitory storage medium. The hardware processor is not limited to being configured as a single circuit, and may be configured as one hardware processor by combining a plurality of independent circuits to implement each function. Also, a plurality of components may be integrated into one hardware processor to realize each function.

Each component of console device 140 or processing circuit 150 may be distributed and realized by a plurality of pieces of hardware. The processing circuit 150 may be realized by a separate processing device that can communicate with the console device 140 instead of the configuration that the console device 140 has. The processing device may be, for example, a workstation connected to the X-ray CT apparatus 100 or a cloud server capable of collectively executing processing equivalent to that of the processing circuit 150 .

The system control function 151 controls various functions of the processing circuit 150 based on input operations received by the input interface 143 .

The imaging condition determination function 152 uses the learned model MDL defined by the model information in the memory 141 to determine imaging conditions for medical images. The imaging conditions include, for example, at least one of an imaging protocol for imaging the subject P, preprocessing conditions for detection data or projection data, and reconstruction conditions for reconstructing a CT image.

The imaging condition determination function 152 may determine imaging conditions for medical images according to an operation input to the input interface 143 .

The preprocessing function 153 performs preprocessing such as logarithmic conversion processing, offset correction processing, inter-channel sensitivity correction processing, and beam hardening correction on the detection data output from the DAS 116 to generate projection data. The projection data thus obtained are stored in the memory 141 .

The reconstruction processing function 154 performs reconstruction processing on the projection data generated by the preprocessing function 153 using a filtered back projection method, an iterative reconstruction method, or the like, to obtain a CT image, which is one of medical images. and store the generated CT image in the memory 141 .

The image processing function 155 converts the CT image 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 143 . Conversion to a three-dimensional image may be performed by preprocessing function 153 .

The output control function 156 causes the display 142 to display CT images generated through reconstruction processing by the reconstruction processing function 154 and images generated by the image processing function 155 (eg, three-dimensional images and cross-sectional images). Also, the output control function 156 may transmit these images to the learning device 200 or other external devices via the communication interface 144 .

Also, the output control function 156 uses the learned model MDL defined by the model information in the memory 141 to display the diagnostic results of the subject P on the display 142 .

[Configuration of learning device]
FIG. 3 is a diagram showing a configuration example of the learning device 200 according to the embodiment. Learning device 200 includes, for example, communication interface 202 , input interface 204 , display 206 , memory 208 , and processing circuitry 210 .

The communication interface 202 includes, for example, a NIC and a wireless communication module. The communication interface 202 communicates with the X-ray CT apparatus 100 and other external devices via the communication network NW.

The input interface 204 accepts various input operations by the operator and outputs an electrical signal indicating the content of the accepted input operation to the processing circuit 210 . For example, the input interface 204 is implemented by a mouse, keyboard, touch panel, drag ball, switch, button, joystick, foot pedal, camera, infrared sensor, microphone, and the like. It should be noted that the input interface 204 in this specification is not limited to having physical operation components such as a mouse and keyboard. For example, the input interface 204 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs the electrical signal to the control circuit.

The display 206 displays various information. For example, the display 206 displays a processing result of the processing circuit 210, a GUI for receiving various operations by the operator, and the like. The display 206 is, for example, an LCD, an organic EL display, or the like.

The memory 208 is implemented by, for example, a RAM, a semiconductor memory device such as a flash memory, a hard disk, or an optical disk. These storage media may be realized by other storage devices such as NAS and external storage server devices connected via the communication network NW. The memory 208 may also include storage media such as ROMs and registers.

Processing circuitry 210 includes, for example, an acquisition function 212 , a learning function 214 , and an output control function 216 . The processing circuit 210 implements these functions by executing a program stored in the memory 208 by a hardware processor (computer), for example.

Hardware processor means circuitry such as, for example, CPUs, GPUs, application specific integrated circuits, programmable logic devices (eg, simple or complex programmable logic devices, field programmable gate arrays). Instead of storing the program in memory 208, the program may be configured to be directly embedded within the circuitry of a hardware processor. In this case, the hardware processor implements its functions by reading and executing the program embedded in the circuit. The above program may be stored in the memory 208 in advance, or may be stored in a non-temporary storage medium such as a DVD or CD-ROM. ) may be installed into memory 208 from a non-transitory storage medium. The hardware processor is not limited to being configured as a single circuit, and may be configured as one hardware processor by combining a plurality of independent circuits to implement each function. Also, a plurality of components may be integrated into one hardware processor to realize each function.

Acquisition function 212 acquires a CT image from X-ray CT apparatus 100 via communication interface 202 . Assume that the CT image is associated as a label with a medical result determined in advance by a doctor or the like (a medical result treated as a correct answer). A medical result associated with a CT image is also called a target. That is, the acquisition function 212 acquires teacher data in which a correct medical result is associated with a CT image.

The learning function 214 uses the teacher data acquired by the acquisition function 212 to learn the unlearned model MDL.

The output control function 216 transmits model information defining the model MDL learned by the learning function 214 , that is, the learned model MDL, to the X-ray CT apparatus 100 via the communication interface 202 .

[Overall Flow of Medical Image Diagnosis System (Training)]
A series of processes of the medical image diagnostic system 1 according to the embodiment will be described below. FIG. 4 is a flow chart showing a series of processing during training by the medical image diagnostic system 1 according to the embodiment.

First, the imaging condition determination function 152 of the X-ray CT apparatus 100 determines imaging conditions for a CT image of the subject P (step S100).

For example, the imaging condition determination function 152 may determine the imaging protocol for the subject P according to the settings input to the input interface 143, that is, the settings input to the input interface 143 by the imaging staff or the like.

Next, the system control function 151 of the X-ray CT apparatus 100 controls the various functions of the processing circuit 150 based on the imaging conditions such as the imaging protocol determined by the imaging condition determination function 152, thereby controlling the subject P. Scan (step S102).

Next, the preprocessing function 153 and the reconstruction processing function 154 of the X-ray CT apparatus 100 generate a CT image of the subject P (step S104). For example, preprocessing function 153 generates projection data based on the detected data output by DAS 116 . The reconstruction processing function 154 generates a CT image of the subject P by performing reconstruction processing on the projection data generated by the preprocessing function 153 . The CT image generated in S104 may be a two-dimensional image or a three-dimensional image.

The system control function 151 acquires the diagnostic result of the CT image of the subject P via the input interface 143 (step S106). For example, when the CT image of the subject P is generated, the system control function 151 instructs the output control function 156 to output the CT image. In response to this, the output control function 156 causes the display 142 to display the CT image. For example, a doctor looks at the CT image on the display 142 to determine whether the subject P has a disease or not, and inputs the information to the input interface 143 . The system control function 151 acquires the information input to the input interface 143 as medical treatment results. Then, the system control function 151 causes the memory 141 to store a data set in which the CT image of the subject P and the medical treatment result of the subject P are combined as teacher data.

Next, the acquisition function 212 of the learning device 200 acquires teacher data from each of one or more X-ray CT apparatuses 100 via the communication interface 202 (step S108).

Next, the learning function 214 of the learning device 200 aligns the plurality of CT images acquired as teacher data by the acquisition function 212 (step S110).

Next, the learning function 214 learns an unlearned model MDL using teacher data (step S112).

For example, the learning function 214 inputs a CT image to an unlearned model MDL, and adjusts the model MDL so that the medical care result output by the model MDL approaches the correct medical care result (target medical care result). Adjust parameters (weighting factors, bias components, etc.). A medical result may be represented, for example, as a vector indicating the presence or absence of a specific disease or a vector indicating its probability (likelihood). The learning function 214 sets parameters of the model MDL to SGD (Stochastic Gradient Descent), Momentum SGD, and AdaGrad so that the difference between the vector of the medical care result output by the model MDL and the vector of the target medical care result is small. , RMSprop, AdaDelta, Adam (Adaptive moment estimation), etc.

Next, the learning function 214 inputs the CT image aligned with the trained model MDL, and acquires the contribution map from the trained model MDL (step S114).

For example, if the CT image is a two-dimensional image, the contribution map may be two-dimensional data, and if the CT image is a three-dimensional image, the contribution map may be three-dimensional data. Also, the contribution map may be time-series data in which contribution is associated with each position on the CT image in time series.

In response, the output control function 216 transmits the contribution map and model information of the learned model MDL to the X-ray CT apparatus 100 via the communication interface 202 . This completes the processing (training processing) of this flowchart.

FIG. 5 is a diagram for explaining a method of obtaining a contribution map during training. For example, assume that CT images of three subjects P1, P2, and P3 are obtained. In this case, the learning function 214 aligns the three CT images so that certain characteristic regions match when the three CT images are superimposed. For example, assume that the full CT image is an image obtained when scanning the upper body. In this case, the learning function 214 may align the positions of the three CT images so that the characteristic parts such as the scapula of the shoulder are at the same position.

After aligning the plurality of CT images, the learning function 214 inputs an image obtained by synthesizing the plurality of CT images into one into a trained model MDL, or selects a representative one of the plurality of CT images. CT images are input to the trained model MDL. As described above, the learned model MDL outputs a contribution map and medical care results when a CT image is input. This contribution map is used when determining imaging conditions (imaging protocol, etc.) at runtime, which will be described later. In the contribution map in the figure, dark-colored portions (close to black) represent high-contribution portions, and light-colored portions (close to white) represent low-contribution portions.

[Overall Flow of Medical Image Diagnosis System (Runtime)]
A series of processes of the medical image diagnostic system 1 according to the embodiment will be described below. FIG. 6 is a flow chart showing the flow of a series of runtime processes by the medical image diagnostic system 1 according to the embodiment. The term "runtime" as used herein means executing the process of estimating medical care results using the learned model MDL.

First, the system control function 151 of the X-ray CT apparatus 100 controls various functions of the processing circuit 150 based on arbitrary imaging conditions to scan the subject P' to be diagnosed (step S200). The subject P′ scanned at runtime may be the same as or different from the subject P scanned during training. The scan in S200 may be, for example, scanography performed before main scan imaging.

Next, the preprocessing function 153 and the reconstruction processing function 154 of the X-ray CT apparatus 100 generate a CT image of the subject P' (step S202). For example, preprocessing function 153 generates projection data based on the detected data output by DAS 116 . The reconstruction processing function 154 performs reconstruction processing on the projection data generated by the preprocessing function 153 to generate a CT image of the subject P'. The CT image generated in S202 is used for alignment with the contribution map, and is not input to the trained model MDL to obtain medical results. Therefore, even if the CT image input to the trained model MDL is a three-dimensional image, a CT image of a two-dimensional image (two-dimensional projection still image) may be generated in the processing of S202.

Next, the imaging condition determination function 152 of the X-ray CT apparatus 100 aligns the contribution map with the CT image of the subject P' based on the contribution map transmitted by the learning device 200 during training. (Step S204).

For example, the imaging condition determination function 152 enlarges, shrinks, or scales the contribution map so that the characteristic part on the contribution map matches the characteristic part on the CT image of the subject P′. Performs image processing such as rotation and shift movement. As a result, the contribution map is aligned with the CT image of the subject P'. Hereinafter, the contribution map that is aligned with the CT image of the subject P' will be referred to as a "position-corrected contribution map".

Next, the imaging condition determination function 152 determines new imaging conditions for the CT image of the subject P' based on the position-corrected contribution map (step S206).

For example, the imaging condition determination function 152 may determine an imaging protocol that lowers the dose of X-rays for regions with low contribution and increases the dose of X-rays for regions with high contribution. As a result, the quality (SN ratio) of the CT image of the subject P' can be improved while reducing the exposure dose of the subject P'.

Further, for example, the imaging condition determination function 152 determines an imaging protocol that shortens the X-ray irradiation time for regions with low contribution and lengthens the X-ray irradiation time for regions with high contribution. good. The irradiation time may be, for example, the width of the X-ray irradiation pulse or the integration time. As a result, the quality (SN ratio) of the CT image of the subject P' can be improved while reducing the exposure dose of the subject P'.

Also, for example, the imaging condition determination function 152 may determine an imaging protocol such that the high-definition X-ray detector 115 detects X-rays irradiated to a region with a high degree of contribution. This improves the spatial resolution of regions with high contribution.

Also, for example, the imaging condition determination function 152 may determine an imaging protocol that includes a spatial filter (for example, a median filter or the like) at the boundary between a high-contribution area and a low-contribution area. As a result, image noise can be reduced, and the quality of the CT image of the subject P' can be improved.

Also, for example, the imaging condition determination function 152 may determine an imaging protocol that roughens the energy BIN in photon counting for regions with a low degree of contribution and refines the energy BIN for regions with a high degree of contribution. This can improve energy resolution.

Further, for example, the imaging condition determination function 152 reduces the current or voltage of the X-ray tube 111 for regions with low contribution and increases the current or voltage of the X-ray tube 111 for regions with high contribution. An imaging protocol may be determined. Thereby, the quality (SN ratio) of the CT image of the subject P' can be improved.

Next, the system control function 151 scans the subject P' again by controlling various functions of the processing circuit 150 based on the imaging conditions determined by the imaging condition determination function 152 (step S208). The scan in S208 may be the main scan.

Next, the preprocessing function 153 and the reconstruction processing function 154 generate a CT image of the subject P' (step S210).

Next, the output control function 156 inputs the CT image of the subject P' generated in S210 to the learned model MDL (step S212).

Next, the output control function 156 acquires the medical treatment result and contribution map of the subject P' from the learned model MDL to which the CT image of the subject P' is input (step S214).

Next, the output control function 156 refers to the imaging protocol or the like to determine whether or not scanning of the subject P' is to be continued (step S216). The medical care result of the sample P' is displayed on the display 142, and the processing of this flowchart (runtime processing) is terminated.

7 to 9 are diagrams schematically showing a method of determining imaging conditions using a contribution map. For example, the imaging condition determination function 152 may determine an imaging protocol (imaging condition), which is one of the imaging conditions, using a contribution map obtained during training, as shown in FIG.

In addition, as shown in FIG. 8, the imaging condition determination function 152 uses the contribution map obtained during training to determine preprocessing conditions (logarithmic transformation processing, offset correction processing, inter-channel conditions for various pre-processing such as sensitivity correction processing and beam hardening correction) may be determined. In addition, the imaging condition determination function 152 may determine a reconstruction condition, which is one of the imaging conditions, using a contribution map obtained during training, as shown in FIG.

[How to align contribution maps; Part 1]
FIG. 10 is a diagram for explaining a method of aligning contribution maps. For example, assume that a learned model MDL is created based on CT images of an unspecified number of subjects P such as P1, P2, and P3, and a contribution map is generated using the learned model MDL. . On the other hand, the reproducibility of the imaging system of the X-ray CT apparatus 100 may be high in terms of hardware. In such a case, registration of contribution maps derived from an unspecified number of subjects P is unnecessary. This eliminates the need to scan the subject P' to align the contribution maps. Therefore, the imaging condition determination function 152 omits the processing of S204 at runtime, and determines new imaging conditions for the CT image of the subject P' based on the contribution map transmitted by the learning device 200 during training. good.

[Method of Aligning Contribution Maps; Part 2]
FIG. 11 is a diagram for explaining a method of aligning contribution maps. Contrary to the example of FIG. 10, the reproducibility of the imaging system of the X-ray CT apparatus 100 may be low in terms of hardware. The imaging system includes the X-ray tube 111, wedge 112, collimator 113, X-ray detector 115, rotating frame 117, and the like. In such cases, the imaging condition determination function 152 aligns the contribution maps at runtime. For example, the imaging condition determination function 152 uses a two-dimensional CT image obtained by scanography, the first three-dimensional CT image, or the like to determine the contribution from an unspecified number of subjects P, such as P1, P2, and P3. Alignment of the degree map may be performed. Then, the imaging condition determination function 152 creates a new CT image of the subject P′ based on the contribution map obtained by positioning the CT image of the subject P′, that is, the position-corrected contribution map. Determine imaging conditions.

[How to align contribution maps; Part 3]
FIG. 12 is a diagram for explaining a method of aligning contribution maps. As illustrated, the imaging condition determination function 152 combines contribution maps derived from an unspecified number of subjects P, such as subjects P1, P2, and P3, and contribution maps derived from the subject P′, and determines the subject A new imaging condition for the CT image of P' may be determined. The contribution map derived from the unspecified number of subjects P is an example of the "first map", and the contribution map derived from the subject P' is an example of the "second map".

In the runtime flowchart of FIG. 6, when scanning is continued in the process of S216, the process returns to S204. At this time, the imaging condition determination function 152 synthesizes the contribution map derived from the unspecified number of subjects P and the contribution map derived from the subject P' (the contribution map obtained in the process of S214), Imaging conditions may be determined based on the combined contribution map (an example of a “third map”). The composite ratio of the contribution map derived from the unspecified number of subjects P and the contribution map derived from the subject P' is, for example, 1:3, compared to the contribution map derived from the subject P, The weight of the contribution map derived from the subject P' may be increased. This makes it possible to determine imaging conditions more suitable for the subject P'.

[Method of Aligning Contribution Maps; Part 4]
FIG. 13 is a diagram for explaining a method of aligning contribution maps. As shown, the imaging condition determination function 152 may combine past contribution maps derived from the subject P' to determine new imaging conditions for CT images of the subject P'. For example, it is assumed that the contribution map derived from the subject P' was obtained one year ago, two years ago, and three years ago. In this case, the imaging condition determination function 152 may synthesize these three contribution maps derived from the subject P' and determine the imaging conditions based on the synthesized contribution maps. The synthesis ratio may be, for example, one year ago: two years ago: three years ago=5:3:1. That is, the weight may be increased for a contribution degree map with a newer time. This makes it possible to determine imaging conditions more suitable for the current subject P'.

[Method for determining imaging conditions; Part 1]
FIG. 14 is a diagram for explaining a method of determining imaging conditions. For example, the imaging condition determination function 152 may determine the imaging angle based on the contribution map. Specifically, as shown in the figure, the imaging condition determination function 152 increases the dose of X-rays irradiated to the front of the subject P' lying on the bed, and An imaging protocol may be determined that reduces the dose of X-rays to be delivered.

[Method for determining imaging conditions; Part 2]
FIG. 15 is a diagram for explaining a method of determining imaging conditions. For example, on the contribution map, portions with a high degree of contribution (dark portions) may be separated at multiple locations. In this case, the imaging condition determination function 152 may determine an imaging protocol such that the subject P' lying on the bed is obliquely irradiated with high-dose X-rays, as shown in the drawing.

[Method for determining imaging conditions; Part 3]
FIG. 16 is a diagram for explaining a method of determining imaging conditions. For example, the imaging condition determination function 152 may change the imaging protocol according to the rotation of the imaging system. Specifically, at a certain sampling time k, X-rays are emitted from the X-ray tube 111(k) and the X-rays are detected by the X-ray detector 115(k). In this case, the processing circuit 150 generates a CT image based on the X-ray detection data detected by the X-ray detector 115(k), and inputs the CT image to the trained model MDL to obtain the time Generate a contribution map at k. The imaging condition determination function 152 determines the imaging protocol for the next time k+1 based on the contribution map at time k. As a result, the dose of X-rays emitted from the X-ray tube 111(k+1) at time k+1 is determined, and the dose of the X-ray tube 111(k+1) and the X-ray detector 115(k+1) when X-rays are emitted is determined. position is determined.

[Method for determining imaging conditions; Part 4]
FIG. 17 is a diagram for explaining a method of determining imaging conditions. For example, the imaging condition determination function 152 may change the imaging protocol each time the imaging system rotates once. Specifically, when the time advances from 1, 2, . A CT image is generated based on the detected X-ray detection data, and the CT image is input to the learned model MDL to generate a contribution map at time k. Based on the contribution map at time k, the imaging condition determination function 152 then determines an imaging protocol for the next cycle k+1 to 2k in which the imaging system rotates once.

[Method for determining imaging conditions; Part 5]
FIG. 18 is a diagram for explaining a method of determining imaging conditions. The imaging protocol also includes a protocol for reading detection data from the X-ray detector 115 (hereinafter referred to as a data reading protocol). Therefore, the imaging condition determination function 152 may determine the data readout protocol based on the contribution map. For example, the imaging condition determination function 152 may determine a data reading protocol in which the number of bindings is increased for areas with lower contribution on the contribution map, and no binding is performed for areas with higher contribution. As a result, it is possible to improve the quality of the CT image by improving the spatial resolution of the high-contribution region while reducing the noise by lowering the spatial resolution of the low-contribution region.

[Method for determining imaging conditions; Part 6]
FIG. 19 is a diagram for explaining a method of determining imaging conditions. Imaging condition determination function 152 may dynamically change the range of energy bins in photon counting based on the contribution map. For example, assume that the X-ray detector 115 can change the BIN range. Further, as contribution maps, a contribution map 1 indicating a spatial distribution effective for low energy, a contribution map 2 indicating a spatial distribution effective for medium energy, and a contribution map 3 indicating a spatial distribution effective for high energy are obtained. It is assumed that there is In this case, the imaging condition determination function 152 changes the BIN threshold of each detection area according to contribution maps 1, 2, and 3. FIG. For example, in the region on the body axis direction (on the Z-axis direction) in FIG. 19, low energy works well and high energy has little effect. As a result, it is possible to finely decompose the energy of a region with a high degree of contribution.

[Method for determining imaging conditions; Part 7]
FIG. 20 is a diagram for explaining a method of determining imaging conditions. The imaging condition determination function 152 may dynamically change the energy for X-ray irradiation according to the degree of contribution. As shown in the figure, for example, suppose there are a contribution map obtained by irradiating an X-ray with an energy of 80 keV and a contribution map obtained by irradiating an X-ray with an energy of 120 keV. In this case, the imaging condition determination function 152 increases the energy to 80 keV for regions with high contribution on the 80 keV contribution map, and increases the energy to 120 keV for regions with high contribution on the 120 keV contribution map. An imaging protocol that enhances may be determined.

[Method for determining imaging conditions; Part 7]
FIG. 21 is a diagram for explaining a method of determining imaging conditions. The imaging condition determination function 152 may determine the imaging protocol according to the time change of the contribution. As described above, the contribution map may be time-series data in which contribution is associated with each position on the CT image in time series.

For example, it is assumed that scan A at time t1 is imaging when a contrast agent is administered into a blood vessel, and scan B at time t2 and scan C at time t3 are imaging of the myocardium. The processing circuit 150 inputs the CT image obtained in the scan A to the trained model MDL to generate a contribution map for future times t2 and t3. The imaging condition determination function 152 determines an imaging protocol for the next time t2 and an imaging protocol for the next time t3 based on the contribution degree maps at times t2 and t3.

Furthermore, the processing circuit 150 generates a contribution map by inputting a CT image to the learned model MDL every time the imaging system of the X-ray CT apparatus 100 rotates continuously and scans are repeated. can be repeated. Then, the processing circuit 150 may end the scan when the contribution of the contribution map exceeds the threshold (necessary contribution).

[Method for determining imaging conditions; Part 8]
22 and 23 are diagrams for explaining a method of determining imaging conditions. For example, as shown in FIG. 22, after angiography is started, a contribution map is generated so that the contribution also increases around the time when the blood vessel of interest is dyed the darkest (around 2 seconds in the figure). may occur. In this case, as shown in FIG. 23, the imaging condition determination function 152 may determine an imaging protocol that increases the dose of X-rays around the time when blood vessels are dyed the darkest (around 2 seconds in the figure). .

[Method for determining imaging conditions; Part 9]
24 and 25 are diagrams for explaining a method of determining imaging conditions. As in FIGS. 24 and 25, contribution maps along the body axis direction (Z direction) of the subject P' can also be generated. For example, it is assumed that scanning is started along the body axis direction (Z direction) from the head of the subject P'. In this case, the imaging condition determination function 152 determines that the scan position reaches a position on the contribution map where the contribution is equal to or less than the threshold while the scan position is gradually changing from the head of the subject P′ to the legs. An imaging protocol may then be determined to end the scan.

In the example of FIG. 24, the contribution is evenly high from the head to the feet of the subject P'. In this case, the imaging condition determination function 152 scans the whole body from the head to the feet of the subject P' while changing the dose of X-rays according to the change in the degree of contribution without ending the scan in the middle. Decide on an imaging protocol.

On the other hand, in the example of FIG. 25, the degree of contribution is high only around the chest of the subject P'. In this case, the imaging condition determination function 152 determines an imaging protocol such that the X-ray dose is increased around the chest and then the scan after the abdomen (from Z1 in the figure) is finished.

[Method for determining imaging conditions; Part 10]
26 and 27 are diagrams for explaining a method of determining imaging conditions. For example, when the subject P' is scanned while the imaging system rotates like k, k+1, k+2, and k+3, a contribution map is generated for each scanning position. In this case, the imaging condition determination function 152 may determine an imaging protocol for reducing the exposure dose of the subject P' at each scan position based on the contribution map of each scan position. Specifically, as shown in FIG. 27, in each of the contribution maps k, k+1, k+2, and k+3, a region with a low contribution (a region with a contribution less than or equal to a threshold value) is set as an X-ray dose reduction region. do. In the dose reduction region, for example, a collimator made of lead that blocks X-rays may be physically installed, or a compensating filter that reduces the output of X-rays may be installed.

[Method for determining imaging conditions; Part 11]
FIG. 28 is a diagram for explaining a method of determining imaging conditions. As illustrated, the imaging condition determination function 152 may set the X-ray dose reduction region according to the degree of contribution in the body axis direction (Z direction) of the subject P'. For example, in the neck contribution map, the contribution is large from the center to the bottom of the map. In this case, the neck dose drop areas are set at the right and left ends of the map. In the breast contribution map, the contribution of the entire map is large. In this case, no chest dose reduction area is set. In the anti-belly contribution map, only the lower right contribution of the map is large. In this case, the dose drop region of the antinode is set to the entire left side of the map when viewed from the center.

According to the embodiment described above, when a CT image is input, the learning device 200 learns the model MDL so as to output the medical treatment result and contribution map of the person included in the input CT image. When the X-ray CT apparatus 100 images the subject P' and generates a CT image, the CT image of the subject P' is generated based on the CT image and the contribution map output by the learned model MDL during training. Determine the imaging conditions for the image. As a result, it is possible to obtain a medical image that enables highly accurate diagnosis while mutually affecting imaging and analysis.

Further, according to the above-described embodiment, in order to determine an imaging protocol that lowers the dose of X-rays for regions with a low degree of contribution and increases the dose of X-rays for regions with a high degree of contribution, the subject It is possible to improve the quality (SN ratio) of the CT image of the subject P' while reducing the exposure dose of P'.

Further, according to the above-described embodiment, in order to determine an imaging protocol that shortens the X-ray irradiation time for regions with a low contribution and lengthens the X-ray irradiation time for regions with a high contribution, It is possible to improve the quality (SN ratio) of the CT image of the subject P' while reducing the exposure dose of the subject P'.

Further, according to the above-described embodiment, since the imaging protocol is determined such that the high-definition X-ray detector 115 detects the X-rays irradiated to the region with the high contribution, the region with the high contribution is determined. Spatial resolution is improved.

In addition, according to the above-described embodiment, image noise can be reduced because an imaging protocol is determined in which a spatial filter (for example, a median filter or the like) is placed at the boundary between a high contribution area and a low contribution area. As a result, the quality of the CT image of the subject P' can be improved.

Further, according to the above-described embodiment, the imaging protocol is determined such that the number of BINs for photon counting is reduced for regions with low contribution and the number of BINs for photon counting is increased for regions with high contribution. can be improved.

Further, according to the above-described embodiment, the current or voltage of the X-ray tube 111 is decreased for regions with a low degree of contribution, and the current or voltage of the X-ray tube 111 is increased for regions with a high degree of contribution. Since the protocol is determined, the quality (SN ratio) of the CT image of the subject P' can be improved.

(Other embodiments (modifications))
Modifications of the above-described embodiment will be described below. In the above-described embodiment, the X-ray CT apparatus 100, which is a modality, and the learning apparatus 200, which is a workstation or a cloud server, are separate apparatuses, but the present invention is not limited to this.

For example, learning device 200 may be one function of X-ray CT apparatus 100 . Specifically, the X-ray CT apparatus 100 may have various functions of the learning device 200 (acquisition function 212 and learning function 214). Also, the X-ray CT apparatus 100 may be one function of the learning apparatus 200 . Specifically, the learning device 200 may include various functions of the X-ray CT apparatus 100 (imaging condition determination function 152). Thus, the X-ray CT apparatus 100 and the learning apparatus 200 may be integrated. The medical image diagnostic system 1 including these devices is another example of the "medical image diagnostic apparatus".

Also, in the above-described embodiment, the number of trained models MDL is one, but the number is not limited to this. For example, if there are multiple specific diseases to be diagnosed, a trained model MDL may be generated for each disease. For example, assume that there is a trained model MDL1 for lung cancer, a trained model MDL2 for pleurisy, and a trained model MDL3 for bronchial asthma. In this case, the same CT image is input to each of the three trained models MDL1-3. Each of the three trained models MDL1-3 outputs a contribution map. If the disease is different, there is a possibility that the part to be noted on the CT image will be different, and the contribution map may be different accordingly. In such a case, the contribution maps for each learned model MDL may be added or averaged to synthesize one contribution map.

Further, in the above-described embodiment, when a CT image is input based on teacher data in which correct medical results are associated with the CT images as labels (targets), a contribution map and medical results are output. Although the model MDL is learned as described above, the present invention is not limited to this. For example, the model MDL may be a combination of model A, which has been fully pre-trained, and model B, which has been fully pre-trained. Model A may be trained to output a contribution map when CT images are input, and may be, for example, a DNN that functions as an attention mechanism. Also, the model B may be trained to output medical results when a CT image is input, and may be, for example, a CNN. In this way, a plurality of pre-learned models for each function, such as the function of estimating medical treatment results and the function of generating a contribution degree map, are combined into one as a "model MDL" according to the present embodiment. good too. In this case, the model MDL does not have to be learned based on teacher data.

While several embodiments have been described, these embodiments are provided by way of example and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and their modifications are included in the scope and spirit of the invention, as well as the scope of the invention described in the claims and equivalents thereof.

DESCRIPTION OF SYMBOLS 1... Medical image diagnostic system 100... X-ray CT apparatus 110... Mounting apparatus 130... Bed apparatus 140... Console apparatus 141... Memory 142... Display 143... Input interface 144... Communication interface 150... Processing Circuit 151 System control function Imaging condition determination function 153 Preprocessing function 154 Reconstruction processing function 155 Image processing function 156 Output control function 200 Learning device 202 Communication interface 204 Input interface 206 Display 208 Memory 210 Processing circuit 212 Acquisition function 214 Learning function 216 Output control function

Claims (21)

an acquisition unit that acquires a medical image of a subject;
When a medical image is input, a map is output in which a medical result of a person included in the input medical image and a degree of contribution to the medical result are associated with each position on the input medical image. a determination unit that determines imaging conditions for the medical image of the subject based on the model learned as above and the medical image of the subject acquired by the acquisition unit;
A medical image diagnostic device comprising: The determination unit determines the imaging conditions based on the map output by the model during learning and the medical image of the subject acquired by the acquisition unit.
The medical image diagnostic apparatus according to claim 1. The decision unit
aligning the map output by the model during learning with the medical image of the subject acquired by the acquisition unit;
Determining the imaging conditions based on the map aligned with the medical image of the subject;
The medical image diagnostic apparatus according to claim 2. The acquisition unit newly acquires a medical image of the subject captured based on the imaging conditions,
The determining unit inputs the medical image of the subject previously acquired by the acquiring unit to the model, and the first map, which is the map output by the model during learning, and the medical image newly determining the imaging condition based on the second map, which is the map output by the input model, and the medical image of the subject newly acquired by the acquisition unit;
The medical image diagnostic apparatus according to claim 2 or 3. The decision unit
weighting and synthesizing the first map and the second map;
aligning the synthesized third map with the medical image of the subject newly acquired by the acquiring unit;
determining the imaging conditions based on the third map aligned with the medical image of the subject;
The medical image diagnostic apparatus according to claim 4. The determination unit increases the weight of the second map compared to the first map.
The medical image diagnostic apparatus according to claim 5. The acquiring unit acquires a new medical image of the subject each time the imaging condition is determined,
The determination unit inputs the medical image of the subject to the model each time the medical image of the subject is acquired, and outputs the image from the model each time the medical image of the subject is input. weighting and synthesizing the plurality of second maps and the first map;
The medical image diagnostic apparatus according to claim 5 or 6. wherein the determination unit increases the weight of the second map, among the plurality of second maps, for a second map output at a later time by the model;
The medical image diagnostic apparatus according to claim 7. The imaging conditions include at least one of an imaging protocol for imaging the subject, a preprocessing condition for data obtained by scanning the subject, and a reconstruction condition for reconstructing the medical image from the data. included,
The medical image diagnostic apparatus according to any one of claims 1 to 8. The map is time series data in which the contribution is associated with each position on the input medical image in a time series.
The medical image diagnostic apparatus according to any one of claims 1 to 9. the medical image is a medical image taken by X-ray,
The determining unit determines, as the imaging condition, an imaging protocol that reduces the dose of the X-rays irradiated to the low-contribution region on the map.
The medical image diagnostic apparatus according to any one of claims 1 to 10. the medical image is a medical image taken by X-ray,
The determination unit determines, as the imaging condition, an imaging protocol that increases the dose of the X-rays irradiated to the region with the high contribution on the map,
The medical image diagnostic apparatus according to any one of claims 1 to 11. the medical image is a medical image taken by X-ray,
The determination unit determines, as the imaging condition, an imaging protocol that shortens the irradiation time of the X-rays for the low-contribution region on the map.
The medical image diagnostic apparatus according to any one of claims 1 to 10. the medical image is a medical image taken by X-ray,
The determination unit determines, as the imaging condition, an imaging protocol that lengthens the irradiation time of the X-rays for the region with the high contribution on the map.
14. The medical image diagnostic apparatus according to any one of claims 1-13. the medical image is a medical image taken by X-ray,
The determination unit determines, as the imaging condition, an imaging protocol that reduces the number of photon bindings in the low-contribution region on the map.
15. The medical image diagnostic apparatus according to any one of claims 1-14. the medical image is a medical image taken by X-ray,
The determination unit determines, as the imaging condition, an imaging protocol that increases the number of photon bindings in the high-contribution region on the map.
16. A medical imaging diagnostic apparatus according to any one of claims 1-15. the medical image is a medical image taken by X-ray,
The determination unit determines, as the imaging condition, an imaging protocol that reduces the current or voltage of the X-ray tube that emits the X-rays in the low-contribution region on the map.
17. A medical imaging diagnostic apparatus according to any one of claims 1-16. the medical image is a medical image taken by X-ray,
The determination unit determines, as the imaging condition, an imaging protocol that increases the current or voltage of the X-ray tube that irradiates the X-rays in the region of high contribution on the map.
18. A medical imaging diagnostic apparatus according to any one of claims 1-17. The decision unit
when a plurality of said models exist, inputting a medical image of said subject into each of said plurality of said models, synthesizing said map output by each of said plurality of said models;
determining the imaging conditions based on the combined map;
19. A medical imaging diagnostic apparatus according to any one of claims 1-18. the computer
obtaining a medical image of a subject;
When a medical image is input, a map is output in which a medical result of a person included in the input medical image and a degree of contribution to the medical result are associated with each position on the input medical image. Determining imaging conditions for the medical image of the subject based on the learned model and the acquired medical image of the subject,
A method for determining medical imaging conditions. to the computer,
acquiring a medical image of a subject;
When a medical image is input, a map is output in which a medical result of a person included in the input medical image and a degree of contribution to the medical result are associated with each position on the input medical image. Determining imaging conditions for the medical image of the subject based on the model trained as described above and the acquired medical image of the subject;
program to run the

Images