JP2020048685A - Breast cancer diagnosis support apparatus, breast cancer diagnosis support system, and breast cancer diagnosis support method - Google Patents

Abstract

To provide a breast cancer diagnosis support apparatus capable of generating diagnosis result data on a breast cancer on the basis of medical image data on the breast, a breast cancer diagnosis support system, and a bread cancer diagnosis support method.SOLUTION: A breast cancer diagnosis support apparatus includes an acquisition unit and a processing unit. The acquisition unit acquires X-ray image data based on the radiography of the breast of a subject. The processing unit generates the diagnosis result data on a breast cancer of the subject by inputting the X-ray image data on the subject into a learned model that generates diagnosis result data on the breast cancer on the basis of the X-ray image data of the breast.SELECTED DRAWING: Figure 1

Description

  Embodiments of the present invention relate to a breast cancer diagnosis support device, a breast cancer diagnosis support system, and a breast cancer diagnosis support method.

  Generally, a dedicated X-ray apparatus (a mammography apparatus, a mammography apparatus) or an ultrasonic diagnostic apparatus is used for breast cancer screening. A person who has undergone a breast cancer screening using these devices can surely notice breast cancer earlier than an unexamined person.

  However, although the rate of breast cancer screening is increasing in Japan, it is still not sufficient. This is considered to be one of the reasons that breast cancer screening using a mammography apparatus or an ultrasonic diagnostic apparatus is not incorporated in a normal medical examination, thereby imposing an additional cost and time burden on the examinee. In addition, if a breast cancer screening using a mammography apparatus or an ultrasonic diagnosis apparatus is imposed on all of the medical examination examinees, the work on the medical institution side such as doctors, medical radiologists, and clinical laboratory technicians increases. Furthermore, when performing remote diagnosis, a server for the diagnosis and a monitor for image interpretation must be prepared, which increases the burden on medical institutions.

U.S. Pat. No. 8,175,351

  An object of the present invention is to generate breast cancer diagnosis result data based on chest medical image data.

  A breast cancer diagnosis support device according to an embodiment includes an acquisition unit and a processing unit. The acquisition unit acquires X-ray image data based on an X-ray image of the chest of the subject. The processing unit, for a learned model that generates breast cancer diagnosis result data based on the chest X-ray image data, by inputting the X-ray image data of the subject, the breast cancer of the subject Generate diagnostic result data.

FIG. 1 is a block diagram illustrating a configuration example of a breast cancer diagnosis support device according to a first embodiment. FIG. 7 is an explanatory diagram showing an example of a data flow at the time of learning of a diagnosis result generation function. FIG. 4 is an explanatory diagram illustrating an example of a data flow when the diagnosis result generation function is operated. (A) is an explanatory diagram showing an example of a data flow at the time of learning of a diagnosis result generation function when identification information such as the height of a subject to be photographed is used in addition to chest X-ray image data, and (b) is data during operation. Explanatory drawing which shows an example of a flow. (A) is an explanatory view showing an example of a data flow at the time of learning of a diagnosis result generation function when information on a lung cancer to be imaged is used in addition to chest X-ray image data, and (b) is a data flow at the time of operation. Explanatory drawing which shows an example. FIG. 9 is a block diagram showing a configuration example of a chest simple X-ray imaging apparatus including the breast cancer diagnosis support apparatus according to the second embodiment. FIG. 9 is a block diagram showing a configuration example of a breast cancer diagnosis support system including a breast cancer diagnosis support device according to a third embodiment. 9 is a sequence chart showing an example of a procedure for generating breast cancer diagnosis result data 71 based on chest X-ray image data by the breast cancer diagnosis support system.

  Hereinafter, embodiments of a breast cancer diagnosis support device, a breast cancer diagnosis support system, and a breast cancer diagnosis support method will be described in detail with reference to the drawings.

  A breast cancer diagnosis support apparatus, a breast cancer diagnosis support system, and a breast cancer diagnosis support method according to one embodiment provide a breast cancer diagnosis based on medical image data of a chest before performing a breast cancer examination using a mammography apparatus or an ultrasound diagnosis apparatus. Generates result data. Medical image data generated by various modalities can be used as medical image data. In the following description, an example in which X-ray image data is used as medical image data will be described.

(First embodiment)
FIG. 1 is a block diagram illustrating a configuration example of the breast cancer diagnosis support device 10 according to the first embodiment. The breast cancer diagnosis support device 10 has at least a storage circuit 13 and a processing circuit 15. FIG. 1 shows an example in which the breast cancer diagnosis support apparatus 10 further includes an input interface 11, a display 12, and a network connection circuit 14.

  The input interface 11 is configured by a general input device such as a trackball, a switch button, a mouse, a keyboard, and a numeric keypad, and outputs an operation input signal corresponding to a user operation to the processing circuit 15. The display 12 is configured by a general display output device such as a liquid crystal display or an OLED (Organic Light Emitting Diode) display.

  The storage circuit 13 has a configuration including a recording medium readable by a processor, such as a semiconductor memory element such as a random access memory (RAM), a flash memory, a hard disk, or an optical disk. And parameter data and other data. Note that some or all of the programs and data in the recording medium of the storage circuit 13 may be downloaded by communication via the network 100, or may be provided to the storage circuit 13 via a portable storage medium such as an optical disk. You may.

  The storage circuit 13 may store the X-ray image data of the subject obtained via the network 100.

  The network connection circuit 14 implements various information communication protocols according to the form of the network 100. The network connection circuit 14 connects to other electric devices via the network 100 according to the various protocols. The network 100 refers to a general information communication network using a telecommunication technology, and 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, and a cable communication. Network and satellite communication networks.

  The breast cancer diagnosis support apparatus 10 is connected to the chest X-ray imaging apparatus 101 and the image server 102 via a network 100 so as to be able to transmit and receive data to and from each other. Further, the breast cancer diagnosis support apparatus 10 may be connected to a HIS (Hospital Information System, a hospital information system) 103 and an RIS (Radiology Information System, a radiology information system) 104 via a network 100 so as to be able to transmit and receive data to and from each other.

  The processing circuit 15 realizes a function of totally controlling the breast cancer diagnosis support device 10. The processing circuit 15 is a processor that reads and executes the breast cancer diagnosis program stored in the storage circuit 13 to execute processing for generating breast cancer diagnosis result data based on chest X-ray image data. is there.

  As shown in FIG. 1, the processor of the processing circuit 15 implements an acquisition function 21 and a diagnosis result generation function 22. Further, the processor of the processing circuit 15 may further implement the additional inspection determination function 23. Each of these functions is stored in the storage circuit 13 in the form of a program.

  The acquisition function 21 acquires X-ray image data based on X-ray imaging of the chest of the subject from the chest X-ray imaging apparatus 101 or the image server 102.

  The diagnosis result generation function 22 generates diagnosis result data of the breast cancer to be imaged, based on the X-ray image data of the chest of the X-ray imaging including the subject. The diagnostic result generation function 22 presents the diagnostic result data to the user (for example, a doctor) by displaying the generated diagnostic result data on the display 12 or outputting the voice through a speaker (not shown). The diagnosis result generation function 22 is an example of a processing unit.

  After confirming the diagnostic result data of the subject, the user determines whether or not the subject requires an additional test for breast cancer based on the diagnostic result data, and if necessary, consults the subject for the additional test. Prompt. The additional test for breast cancer may include, for example, at least one of a test using a mammography device and a test using an ultrasonic diagnostic device.

  When the breast cancer diagnosis support apparatus 10 implements the additional test determination function 23, the additional test determination function 23 adds an additional information related to breast cancer to the subject based on the diagnostic result data of the subject output by the diagnostic result generation function 22. It is determined whether or not the test is necessary. If it is determined that the test is necessary, information to that effect may be displayed on the display 12 or outputted to a user through a speaker (not shown) to present the information to the user.

When the additional test determination function 23 determines that an additional test is necessary, the additional test determination function 23 may instruct the HIS 103 or the RIS 104 connected via the network 100 to reserve an additional test for breast cancer of the subject.
Next, the operation of the diagnosis result generation function 22 will be described.

  The diagnosis result generation function 22 performs a process of generating breast cancer diagnosis result data based on X-ray image data of the chest. For this processing, for example, a look-up table that associates X-ray image data of the chest with diagnosis result data of breast cancer may be used. Further, machine learning may be used for this processing. In the case of using machine learning, for example, a feature amount is obtained from X-ray image data of the chest, and the obtained feature amount is obtained using a dictionary for breast cancer diagnosis and an SVM (support vector machine) or the like, which previously learned a breast cancer image as correct data. The likelihood calculated by collation may be output as diagnosis result data. Further, as the machine learning, deep learning using a multilayer neural network such as a CNN (convolutional neural network) or a convolutional deep belief network (CDBN) may be used.

  In the following description, an example is shown in which the diagnosis result generation function 22 includes a neural network 31 and generates breast cancer diagnosis result data based on chest X-ray image data using deep learning.

  FIG. 2 is an explanatory diagram illustrating an example of a data flow when the diagnosis result generation function 22 learns.

  The diagnosis result generation function 22 sequentially updates the parameter data 32 by inputting a large number of training data and performing learning. The training data includes chest simple X-ray images 411, 412, 413,... As training input data constituting the training input data group 41, and ideal breast cancer diagnosis results 511, 512 constituting the training output data group 51. , 513. The ideal breast cancer diagnosis results 511, 512, 513,... Are determined by taking out and diagnosing the tissue from the subject of the corresponding chest simple X-ray image 411, 412, 413,. It may be a definitive diagnosis of breast cancer.

  Each time the training data is input, the diagnosis result generation function 22 obtains a result of processing the chest simple X-ray images 411, 412, and 413 by the neural network 31 to obtain a definite diagnosis result 511, 512, 513,. Is performed, that is, the parameter data 32 is updated so as to approach. Generally, when the change rate of the parameter data 32 converges within the threshold value, the learning is determined to be completed. Hereinafter, the parameter data 32 after learning is particularly referred to as learned parameter data 32a.

  Although FIG. 2 shows an example in which the chest X-ray image data is chest simple X-ray image data, the present invention is not limited to this. As the type of the chest X-ray image data, for example, X-ray image data based on tomosynthesis imaging of the chest may be used. Further, as the X-ray image data of the chest, image data (soft tissue image data) obtained by extracting soft tissue based on dual energy imaging may be used. When soft tissue image data is used as X-ray image data of the chest, breast cancer is easily diagnosed because the soft tissue image has soft bone extracted and bone removed.

  In addition, a tube voltage (for example, 120 kV) which is generally used in a normal medical examination or the like in chest X-ray imaging is a tube voltage (for example, 30 kV) suitable for soft tissue of the breast which is generally used for imaging by a mammography apparatus. Higher than. Therefore, when chest X-ray image data is used as chest X-ray image data, chest X-ray imaging is performed using a tube voltage (for example, 50 kV) lower than the tube voltage used in a normal medical examination or the like in chest X-ray imaging. It is preferable to use images obtained by simple X-ray photography.

  It should be noted that the type of the training input data and the type of the input data during operation shown in FIG. For example, if the input data during operation is X-ray image data based on tomosynthesis imaging of the subject, the training input data group 41 during learning is also X-ray image data based on tomosynthesis imaging.

  “Image data” includes raw data generated by the modality. That is, the input data of the neural network 31 may be raw data.

  FIG. 3 is an explanatory diagram illustrating an example of a data flow when the diagnosis result generation function 22 is operated.

  In operation, the diagnosis result generation function 22 receives the chest simple X-ray image data 61 of the subject to be diagnosed with breast cancer, and outputs the breast cancer diagnosis result data 71 of the subject using the learned parameter data 32a. .

  The neural network 31 and the learned parameter data 32a constitute a learned model 30. The neural network 31 is stored in the storage circuit 13 in the form of a program. The learned parameter data 32a may be stored in the storage circuit 13, or may be stored in a storage medium connected to the breast cancer diagnosis support device 10 via the network 100. In this case, the diagnosis result generation function 22 as an example of a processing unit realized by the processor of the processing circuit 15 reads out the learned model from the storage circuit 13 and executes the model to obtain a breast cancer based on the X-ray image data of the chest. To generate the diagnosis result data. The learned model may be constructed by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

  The diagnosis result data 71 of the subject's breast cancer output by the learned model 30 including the diagnosis result generation function 22 may be, for example, data indicating either benign or malignant, or a guideline for breast cancer medical care. The data may indicate whether the subject belongs to any of the category classifications specified in the above, or may be data indicating the likelihood that the subject has breast cancer as a percentage (eg, benign x%, malignant y%, etc.). You may.

  In addition, in order to improve the accuracy of breast cancer diagnosis by the diagnostic result generation function 22, at least one of the height, weight, medical history, and medical history of a relative in addition to the chest X-ray image data is input data as input data. The included identification information 42 may be used.

  In this case, at the time of learning, the identification information 421, 422, 423,... Of the respective imaging subjects of the chest simple X-ray images 411, 412, 413,. The data is input to the neural network 31 (see FIG. 4A). In operation, the diagnosis result generation function 22 inputs the identification information 62 of the subject together with the chest simple X-ray image data 61 of the subject to be diagnosed with breast cancer to the learned model 30 read from the storage circuit 13. Then, the diagnosis result data 71 of the breast cancer of the subject is output (see FIG. 4B). By using the chest X-ray image data and the identification information of the imaging subject as input data, it is possible to generate learned parameter data 32a that has been subjected to learning according to the type of the imaging subject. The accuracy of diagnosing breast cancer can be improved as compared with the case where only line image data is used as input data.

  Further, in order to improve the accuracy of breast cancer diagnosis performed by the diagnostic result generation function 22, information on a lung cancer to be imaged may be used as input data in addition to chest X-ray image data. The chest X-ray image data may include not only breast cancer tissue but also lung cancer tissue. Therefore, by including information about lung cancer in the training input data, it is preferable to prevent a shadow caused by lung cancer from being erroneously detected as breast cancer among shadows included in X-ray image data of the chest.

  The information on the lung cancer indicates, for example, the position of the lung cancer acquired based on the result of Computer Aided Detection / Diagnosis (CAD) on a medical image (not limited to a chest plain X-ray image) of the imaging subject. And information indicating the position of the lung cancer acquired based on the result of the interpretation of the lung image by the interpreting doctor on the medical image.

  When the position information of the lung cancer is used as the input data, at the time of learning, the position information 431, 432, 433 of the lung cancer of each of the imaging subjects of the chest simple X-ray images 411, 412, 413,. ... are also input to the neural network 31 as training input data (see FIG. 5A). In operation, the diagnosis result generation function 22 transmits the lung cancer position information 63 of the subject together with the chest simple X-ray image data 61 of the subject to be diagnosed with breast cancer to the learned model 30 read from the storage circuit 13. By inputting, the diagnosis result data 71 of the subject's breast cancer is output (see FIG. 5B).

  By using the chest X-ray image data and the position information of the lung cancer of the subject as input data, the possibility of erroneously diagnosing lung cancer as breast cancer is lower than when only chest X-ray image data is used as input data. Since it can be significantly reduced, the diagnostic accuracy of breast cancer can be improved.

  In addition, by combining the examples shown in FIGS. 4 and 5, in addition to the X-ray image data of the chest, both identification information such as the height of the imaging target and information on the lung cancer of the imaging target may be used as input data. Good.

  In the breast cancer diagnosis support apparatus 10 according to the present embodiment, the diagnosis result generation function 22 as an example of the processing unit uses the learned model 30, and the X-ray image data 61 of the chest of the subject provides The breast cancer diagnosis result data 71 can be generated. For this reason, the user who has checked the diagnosis result data 71 of the subject can determine whether or not an additional test for breast cancer is necessary based on the diagnosis result data 71. Further, based on this determination, the user can prompt the subject to undergo an examination using a mammography apparatus and an additional examination using an ultrasonic diagnostic apparatus as necessary.

  Therefore, according to the breast cancer diagnosis support apparatus 10, the subject can undergo a simple breast cancer screening by undergoing an examination using a chest X-ray imaging apparatus as the first stage of breast cancer screening. For this reason, only when there is a suspicion of breast cancer based on the diagnostic result data 71 of the subject output from the diagnostic result generation function 22, the subject performs an examination using a mammography apparatus or an ultra What is necessary is just to undergo an examination using an ultrasonic diagnostic apparatus. Therefore, for subjects who were originally unlikely to have breast cancer and did not need to undergo these tests, and for medical institutions, the financial costs associated with tests using mammography and ultrasonic diagnostic equipment, Time cost and human cost can be reduced.

  In addition, an examination using a chest X-ray apparatus is often incorporated into a normal medical examination. For this reason, according to the breast cancer diagnosis support apparatus 10, it is possible to easily know whether or not there is a suspicion of breast cancer in the subject based on the chest simple X-ray image data obtained by the normal health examination. Therefore, according to the breast cancer diagnosis support apparatus 10, the breast cancer test using a mammography apparatus or the ultrasonic diagnostic apparatus has been felt as a burden and has not been subjected to these tests, but the possibility of breast cancer is originally high. The possibility of early detection of breast cancer in a large number of subjects who had to undergo these tests can be greatly improved, and the lives of many subjects can be expected to be saved.

(Second embodiment)
FIG. 6 is a block diagram illustrating a configuration example of a chest X-ray imaging apparatus 80 including the breast cancer diagnosis support apparatus according to the second embodiment.

  The chest simple X-ray imaging device 80 includes an imaging device 81 that performs a simple X-ray imaging of the chest of the subject, and a console device 82 as an example of the breast cancer diagnosis support device 10. The breast simple X-ray imaging apparatus 80 according to the second embodiment differs from the breast cancer diagnosis support apparatus 10 according to the first embodiment in that the chest simple X-ray image data 61 obtained by imaging the subject by itself can be used. Since other configurations and operations are not substantially different from those of the breast cancer diagnosis support apparatus 10 shown in FIG. 1, the same configurations are denoted by the same reference numerals and description thereof is omitted. Further, the processing related to the generation of the learned model 30 is the same as that of the breast cancer diagnosis support apparatus 10 shown in FIG.

  The imaging device 81 has an imaging system such as an X-ray tube and an X-ray detector for performing simple X-ray imaging of the chest of the subject in a standing position, and converts the chest simple X-ray image data 61 of the subject obtained by imaging. It is given to the console device 82.

  The acquisition function 21x of the processing circuit 15x of the console device 82 as an example of the breast cancer diagnosis support device 10 acquires the chest simple X-ray image data of the subject from the imaging device 81. Using the learned model 30, the diagnosis result generation function 22x outputs diagnosis result data 71 of the subject's breast cancer based on the chest simple X-ray image data of the subject.

  As with the breast cancer diagnosis support apparatus 10 according to the first embodiment, the subject is incorporated into a normal health examination as the first stage of breast cancer screening also by the chest X-ray imaging apparatus 80 according to the second embodiment. A simple breast cancer screening can be completed by receiving an examination using a chest X-ray apparatus that is frequently performed.

(Third embodiment)
FIG. 7 is a block diagram illustrating a configuration example of a breast cancer diagnosis support system 90 including the breast cancer diagnosis support device according to the third embodiment. FIG. 8 is a sequence chart showing an example of a procedure when the breast cancer diagnosis support system 90 generates the breast cancer diagnosis result data 71 based on the X-ray image data of the chest.

  The breast cancer diagnosis support system 90 includes a client device 91 and a server device 92 connected to each other via a network 100. The breast cancer diagnosis support system 90 according to the third embodiment includes the functions of the breast cancer diagnosis support device 10 according to the first embodiment distributed to a client device 91 and a server device 92. Note that processing related to generation of the learned model 30 is the same as that of the breast cancer diagnosis support apparatus 10 illustrated in FIG.

  The client device 91 is configured by, for example, a general personal computer, and has an input interface 11c having the same configuration as the input interface 11, the display 12, and the network connection circuit 14 of the breast cancer diagnosis support device 10 according to the first embodiment. A display 12c and a network connection circuit 14c are provided.

  On the other hand, the server device 92 includes a storage circuit 13 s, a network connection circuit 14 s, and a process each having the same configuration as the storage circuit 13, the network connection circuit 14, and the processing circuit 15 of the breast cancer diagnosis support device 10 according to the first embodiment. It has a circuit 15s. The processor of the processing circuit 15s is configured to read and execute the program stored in the storage circuit 13s, thereby realizing the acquisition function 21, the diagnosis result generation function 22, and the additional test determination function 23 according to the first embodiment. You.

  Now, it is assumed that the user desires to perform a breast cancer diagnosis of the subject based on the X-ray image data of the subject, and the user can use the client device 91 of the breast cancer diagnosis support system 90.

  In this case, first, the user generates the breast cancer diagnosis result data 71 of the subject to the server device 92 based on the X-ray image data of the subject via the input interface 11c, and converts the stationary breast cancer diagnosis result data to 71. A request is made to reply (step S1 in FIG. 8). At this time, the client device 91 may acquire X-ray image data of the subject from the chest simple X-ray imaging device 101 or the image server 102 and transmit the data to the server device 92.

  Upon receiving this request, the server device 92 acquires X-ray image data of the subject (Step S2). When the X-ray image data of the subject is not transmitted from the client device 91, the server device 92 acquires the X-ray image data of the subject from the chest X-ray imaging apparatus 101 or the image server 102.

  Next, the server device 92 generates the breast cancer diagnosis result data 71 of the subject based on the X-ray image data 61 of the subject using the learned model 30 (step S3, see FIG. 3). Next, the server device 92 transmits the diagnosis result data 71 of the breast cancer of the subject to the client device 91.

  The client device 91 receives the diagnosis data 71 of the breast cancer of the subject from the server device 92, displays the diagnosis result data 71 of the breast cancer of the subject on the display 12c, or outputs the voice through a speaker (not shown). Is presented to the user (step S5).

  Thus, the same operation and effect as the breast cancer diagnosis support device 10 according to the first embodiment can be achieved by the breast cancer diagnosis support system 90 according to the third embodiment.

  Further, the breast cancer diagnosis support system 90 according to the third embodiment may include a plurality of client devices 91 that can be configured at low cost with respect to one server device 92. In this case, the user can easily obtain the breast cancer diagnosis result data 71 of the subject based on the X-ray image data 61 of the subject by using the client devices 91 installed in various places, and the mammography can be performed on the subject. It is possible to determine whether or not an additional test such as a test using a device or a test using an ultrasonic diagnostic device is necessary.

  According to at least one embodiment described above, it is possible to generate the breast cancer diagnosis result data 71 based on the chest medical image data.

  Note that the diagnosis result generation functions 22, 22x of the processing circuits 15, 15x in the present embodiment are an example of a processing unit in the claims.

  In the above embodiments, the term “processor” may be, for example, a dedicated or general-purpose CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or an application-specific integrated circuit (ASIC). A circuit such as a programmable logic device (for example, a Simple Programmable Logic Device (SPLD), a Complex Programmable Logic Device (CPLD), and an FPGA) is meant. The processor realizes various functions by reading and executing the program stored in the storage medium.

  Further, in the above embodiment, an example in which a single processor of the processing circuit realizes each function has been described. However, a processing circuit is configured by combining a plurality of independent processors, and each processor realizes each function. Is also good. In the case where a plurality of processors are provided, the storage medium for storing the program may be provided separately for each processor, or one storage medium may collectively store programs corresponding to the functions of all processors. Is also good.

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

10 Breast cancer diagnosis support device 21, 21x acquisition function 22, 22x diagnosis result generation function (processing unit)
23 Additional examination determination function 30 Learned model 31 Neural network 32 Parameter data 32a Trained parameter data 41 Training input data group 42 Identification information 51 Training output data group 61 X-ray image data 62 Identification information 63 Lung cancer position information 71 Diagnosis result data 80 chest X-ray imaging apparatus 90 breast cancer diagnosis support system 91 client device 92 server device

Claims (12)

An acquisition unit configured to acquire X-ray image data based on an X-ray image of the chest of the subject;
By inputting the X-ray image data of the subject to a trained model that generates breast cancer diagnosis result data based on chest X-ray image data, the diagnostic result data of the subject's breast cancer is obtained. A processing unit to generate;
Breast cancer diagnosis support device equipped with The X-ray image data includes:
It is image data based on dual energy shooting of the chest,
The breast cancer diagnosis support device according to claim 1. The X-ray image data includes:
Image data based on tomosynthesis imaging of the chest
The breast cancer diagnosis support device according to claim 1. The X-ray image data includes:
Image data based on X-ray imaging of the chest using a tube voltage lower than the tube voltage used in chest X-ray imaging,
The breast cancer diagnosis support device according to claim 1. The trained model is
Height of the imaging target of the X-ray image data, weight, medical history, and generating the diagnosis result data of breast cancer further based on identification information including at least one of the medical history of relatives,
The processing unit includes:
By further inputting the identification information of the subject to the learned model, to generate the diagnosis result data of breast cancer of the subject,
The breast cancer diagnosis support device according to any one of claims 1 to 4. The trained model is
Generating the diagnosis result data of breast cancer further based on information about the lung cancer of the imaging target of the X-ray image data,
The processing unit includes:
By further inputting information on the lung cancer of the subject to the learned model, to generate the diagnosis result data of breast cancer of the subject,
The breast cancer diagnosis support device according to any one of claims 1 to 5. The information about the lung cancer,
Information indicating the position of lung cancer based on the computer-aided detection result for the medical image of the subject or the imaging target, or information indicating the position of lung cancer based on the result of interpretation of lung cancer for the medical image,
The breast cancer diagnosis support device according to claim 6. Based on the diagnostic result data, the subject determines whether or not an additional test for breast cancer is necessary, and if it is determined to be necessary, the information that the subject requires an additional test for breast cancer. Additional inspection determination unit for presenting to the user,
The breast cancer diagnosis support device according to any one of claims 1 to 7, further comprising: The additional inspection is
Including at least one of an examination using a mammography apparatus and an examination using an ultrasonic diagnostic apparatus,
The breast cancer diagnosis support device according to claim 8. An acquisition unit that acquires medical image data of the chest of the subject,
By inputting the medical image data of the subject to a trained model that generates breast cancer diagnosis result data based on medical image data of the chest, the diagnostic result data of breast cancer of the subject is generated. A processing unit;
Breast cancer diagnosis support device equipped with A breast cancer diagnosis support system including a client device and a server device communicably connected to the client device via a network,
The client device and the server device,
An acquisition unit configured to acquire X-ray image data based on an X-ray image of the chest of the subject;
The diagnostic result data of breast cancer of the subject is generated by inputting the X-ray image data of the subject to a learned model that generates breast cancer diagnosis result data based on X-ray image data. A processing unit;
A breast cancer diagnosis support system equipped with Obtaining X-ray image data based on X-ray imaging of the chest of the subject;
By inputting the X-ray image data of the subject to a trained model that generates breast cancer diagnosis result data based on chest X-ray image data, the diagnostic result data of the subject's breast cancer is obtained. Generating,
Breast cancer diagnosis support method having

Images