Processing device, processing program, processing method, and processing system

Abstract

To provide a processing device, a processing program, a processing method, and a processing system which output medical information more effectively than before.SOLUTION: A processing device executes processing for: acquiring measurement data obtained by measuring condition of a human body; acquiring medical information on each of a plurality of disease states occurring in the body on the basis of the measurement data; and outputting the acquired medical information for each disease state in an identifiable manner.SELECTED DRAWING: Figure 8A

Description

[Technical field]

[0001] The present disclosure relates to a processing device, a processing program, a processing method, and a processing system for processing measurement data of a human body. [Background technology]

[0002] Conventionally, a processing system capable of processing measurement data of a human body and outputting the acquired data has been known. Patent Document 1 describes a medical image diagnostic device that includes an ultraviolet light source that irradiates ultraviolet light, an irradiation control unit that moves the position of the ultraviolet light source relative to an object to be irradiated with the ultraviolet light in an examination room and controls the irradiation of the ultraviolet light to the object to be irradiated, and an imaging unit that captures a medical image of a subject, and has a display that displays the captured medical image and the analysis results of the medical image. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2022-014262 Summary of the Invention [Problem to be solved by the invention]

[0004] Therefore, in consideration of the above-mentioned technologies, the present disclosure aims to provide a processing device, a processing program, a processing method, and a processing system that are capable of outputting medical information more effectively through various embodiments. [Means for solving the problem]

[0005] According to one aspect of the present disclosure, there is provided a processing device having at least one processor, the at least one processor being configured to execute processing to acquire measurement data measuring a state of a human body, acquire medical information relating to each of a plurality of pathological conditions occurring in the body based on the measurement data, and output the acquired medical information in a manner that allows identification of each pathological condition.

[0006] According to one aspect of the present disclosure, there is provided a processing program for causing a computer having at least one processor to function as follows: to acquire measurement data measuring a state of a human body, to acquire medical information relating to each of a plurality of pathological conditions occurring in the body based on the measurement data, and to output the acquired medical information in a manner that enables identification of each pathological condition.

[0007] According to one aspect of the present disclosure, there is provided a "processing method executed by at least one processor in a computer having the at least one processor, the processing method including the steps of acquiring measurement data measuring a state of a human body, acquiring medical information relating to each of a plurality of pathological conditions occurring in the body based on the measurement data, and outputting the acquired medical information in a manner that enables identification of each pathological condition."

[0008] According to one aspect of the present disclosure, there is provided a processing system including "the processing device described above and a display device connected to the processing device via a communications network and configured to receive medical information output from the processing device." Effect of the Invention

[0009] According to the present disclosure, it is possible to provide a processing device, a processing program, a processing method, and a processing system capable of outputting medical information more effectively.

[0010] It should be noted that the above effects are merely illustrative for the convenience of explanation and are not limiting. In addition to or instead of the above effects, any effect described in this disclosure or any effect obvious to a person skilled in the art may be achieved. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram showing a configuration of a processing system 1 according to an embodiment of the present disclosure. [Diagram 2] FIG. 2 is a block diagram showing a configuration of the processing device 100 according to an embodiment of the present disclosure. [Diagram 3] FIG. 3 is a diagram conceptually illustrating a subject management table stored in the processing device 100 according to an embodiment of the present disclosure. [Figure 4] FIG. 4 is a diagram showing a processing flow executed in the processing system 1 according to an embodiment of the present disclosure. [Diagram 5] FIG. 5 is a diagram showing a process flow executed in the model generating device 300 according to an embodiment of the present disclosure. [Figure 6] FIG. 6 is a diagram conceptually illustrating an example of measurement data according to an embodiment of the present disclosure. [Figure 7A] FIG. 7A is a diagram conceptually illustrating an example of a process in which medical information is generated by processing measurement data according to an embodiment of the present disclosure. [Figure 7B] FIG. 7B is a diagram showing a processing flow executed in the processing system 1 according to an embodiment of the present disclosure. [Figure 7C] FIG. 7C is a diagram showing a processing flow executed in the processing system 1 according to an embodiment of the present disclosure. [Figure 8A] FIG. 8A is a diagram showing an example of medical information output from the processing device 100 according to an embodiment of the present disclosure. [Figure 8B] FIG. 8B is a diagram showing an example of medical information output from the processing device 100 according to an embodiment of the present disclosure. [Figure 9A]FIG. 9A is a diagram showing an example of medical information output from the processing device 100 according to an embodiment of the present disclosure. [Figure 9B] FIG. 9B is a diagram showing an example of medical information outputted by the processing device 100 according to an embodiment of the present disclosure. [Figure 10A] FIG. 10A is a diagram showing an example of medical information for each pathology output from the processing device 100 according to an embodiment of the present disclosure. [Figure 10B] FIG. 10B is a diagram showing an example of medical information for each pathology output from the processing device 100 according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] 1. Overview of Processing System 1 The processing system 1 according to the present disclosure is used to acquire medical images acquired by a measuring device from the measuring device and output medical information from the acquired measurement data. In particular, the processing system 1 is used to process measurement data acquired over multiple parts (e.g., the whole body) of a human subject. Such measurement data is typically obtained by measuring the state of the human body, and medical images such as CT images (computed tomography images) that capture the inside of the human body are used. Such CT images are processed by the processing device 100 and used to analyze pathological conditions occurring in the human body. The analysis results are then output to a display or the like as medical information. In this way, the processing system 1 effectively outputs medical information related to the subject's pathological condition, making it possible to grasp the pathological condition more effectively and diagnose or assist in the diagnosis of diseases related to the pathological condition.

[0013] The processing system 1 according to the present disclosure is typically preferably used in medical settings (e.g., medical institutions). Among them, it is particularly preferably used in emergency medical settings (however, there is no intention to limit the use to emergency medical settings). In such emergency medical settings, it is necessary to analyze the pathology of a subject based on measurement data, and determine a diagnosis and subsequent treatment according to the analysis results. Therefore, by using the processing system 1 according to the present disclosure, it is possible to effectively output medical information, grasp the pathology more quickly, and more efficiently diagnose a disease (or assist in diagnosis) and determine subsequent treatment, particularly in emergency medical settings.

[0014] FIG. 1 is a block diagram showing a configuration of a processing system 1 according to an embodiment of the present disclosure. According to FIG. 1, the processing system 1 includes at least a processing device 100 for processing measurement data acquired by a measuring device 400 and outputting medical information, and a display device 200 for displaying the medical information. The processing system 1 may also include a measuring device 400 for acquiring measurement data and a model generating device 300 for generating a trained analysis model used when the medical information is output by the processing device 100. The measuring device 400 is not necessarily limited to only one measuring device, and a combination of multiple measuring devices is also possible. The processing device 100, the display device 200, the model generating device 300, and the measuring device 400 are connected to each other so as to be able to communicate with each other via at least one of a wireless network and a wired network.

[0015] In the present disclosure, the "measuring device 400" may be any device used to obtain measurement data, and is not limited to a specific one. A typical example of such a measuring device is a CT device, but other examples include an MRI device, an X-ray device, an electrocardiograph device, an ultrasound diagnostic device, an endoscope device, a blood pressure monitor device, an angiograph, or a combination thereof. Such a measuring device 400 may be used not only in a medical institution, but also in the subject's home, school, workplace, or any other place. The CT device is used to obtain tomographic image data across at least multiple sites of a subject who has been brought to the hospital by ambulance, and can provide useful information for identifying the pathology that has occurred, its location, and its severity. Therefore, in the processing system 1 of the present disclosure that can generate medical information by analyzing medical images, a case where a CT device is used as the measuring device 400 will be described, but it is of course not limited to this.

[0016] In the present disclosure, the "measurement data" may be any data measured by the measuring device 400, and is not limited to a specific one. Typical examples of such measurement data include CT images, but also include MRI images, three-dimensional measurement data, X-ray images, electrocardiogram data, echographic data, endoscopic images, blood pressure measurement data, blood sampling data, respiratory function data, angiographic images, other test data, or combinations thereof. In the present disclosure, among these measurement data, CT images, MRI images, X-ray images, endoscopic images, angiographic images, or combinations thereof are preferably used. In the present disclosure, among these measurement data, CT images are preferably used. CT images are used to evaluate the state of multiple tomographic planes of a subject across a predetermined range (e.g., multiple parts or the whole body) of the subject. Therefore, it is possible to evaluate not only the state of a specific tomographic plane, but also the state of multiple spatially continuous tomographic planes. By analyzing such CT images, it is possible to obtain information on the pathology, the part where the pathology occurs, and its severity.

[0017] In addition, such measurement data is typically received from each measuring device via a communication network, but may be received from a database device or server device in which already measured measurement data is stored. In other words, measurement data does not necessarily mean data measured in real time. As an example, even measurement data stored in a database device or server device for electronic medical records or PACS (Picture Archiving and Communication Systems) can be similarly used in the processing system 1 of the present disclosure.

[0018] Moreover, the measurement data that can be used does not necessarily have to be "measurement data measured continuously in space" as described above. For example, it is possible to obtain blood pressure measurement data at a certain point in time and blood pressure measurement data measured continuously in time over a certain period of time from blood pressure measurement data. In this way, even "measurement data measured continuously in time" can be suitably used as the measurement data of the present disclosure. Furthermore, although the measurement data is input to the trained analysis model, the input data does not have to be all of the measurement data, and may be at least a part of it. In the following example, a case where a CT image is mainly used as the measurement data will be described, but of course, this is not limited to this.

[0019] In addition, in the present disclosure, the term "subject" may be any person who is the subject of measurement of measurement data, and is not limited to only those with a specific attribute. Therefore, such subjects include all kinds of people, such as patients, test subjects, diagnostic subjects, and healthy individuals. In addition, in the present disclosure, the term "operator" may be any person who at least operates the processing device 100 or refers to medical information output by the processing device 100, and is not limited to only those with a specific attribute. Therefore, such operators are not limited to medical professionals such as doctors, nurses, and laboratory technicians, but also include any people, such as the subject himself. In addition, in the present disclosure, the term "medical professional" may be any person who is engaged in medical care, and is not limited to only those with a specific attribute. Therefore, such medical professionals include any people, such as doctors, nurses, laboratory technicians, medical office staff, medical institution staff and managers, ambulance personnel, and personnel in charge of medical equipment and medical facilities.

[0020] In addition, in the present disclosure, terms such as "determination" and "diagnosis" are used for a certain disease or symptom, but these do not necessarily mean a definitive determination or diagnosis by a doctor. For example, these terms naturally include a case where the processing system 1 of the present disclosure is used by the subject himself or herself, or by an operator other than a doctor, and the subject is determined or diagnosed by the processing device 100 included in the processing system 1. These terms also include assistance to a doctor or the like in making a definitive determination or diagnosis.

[0021] 2. Configuration of the Processing Device 100 FIG. 2 is a block diagram showing a configuration of a processing device 100 according to an embodiment of the present disclosure. According to FIG. 2, the processing device 100 includes a processor 111, a memory 112, an input interface 113, an output interface 114, and a communication interface 115. These components are electrically connected to each other via control lines and data lines. Note that the processing device 100 does not need to include all of the components shown in FIG. 2, and may be configured by omitting some of the components, or may include other components. For example, the processing device 100 may include a battery for driving each component.

[0022] Such a processing device 100 can be suitably applied to any device capable of executing the processes according to the present disclosure, such as a laptop computer, a desktop computer, a smartphone, a tablet terminal, etc. Also, the processing device 100 can perform at least a part of the processes on a server device on a cloud. Therefore, the processing device 100 also includes the server device, or a combination of a device such as a laptop computer operated by an operator and the server device.

[0023] In the processing device 100, the processor 111 functions as a control unit that controls the processing device 100 or other components of the processing system 1 based on a program stored in the memory 112. Specifically, the processor 111 executes "processing of acquiring measurement data that measures the state of the human body," "processing of acquiring medical information related to each of a plurality of pathological conditions that have occurred in the body based on the measurement data," "processing of outputting the acquired medical information in a form that allows identification of each pathological condition," and the like based on the program stored in the memory 112. The processor 111 is mainly composed of one or more CPUs, but may be appropriately combined with a GPU, an FPGA, or the like.

[0024] The memory 112 is composed of a RAM, a ROM, a non-volatile memory, a HDD, an SSD, etc., and functions as a storage unit. The memory 112 stores instructions and commands for various controls of the processing system 1 according to this embodiment as a program. Specifically, the memory 112 stores programs for the processor 111 to execute "processing of acquiring measurement data that measures the state of the human body," "processing of acquiring medical information related to each of a plurality of pathological conditions that have occurred in the body based on the measurement data," "processing of outputting the acquired medical information in a form that allows identification for each pathological condition," etc. In addition to the programs, the memory 112 may also store various information to be stored in the subject management table.

[0025] The input interface 113 functions as an input unit that accepts an instruction input from an operator to the processing device 100. Examples of the input interface 113 include various hard keys such as a keyboard and a mouse, and a touch panel that is superimposed on the display of the display device 200 and has an input coordinate system corresponding to the display coordinate system of the display. In the case of a touch panel, icons corresponding to commands to be input are displayed on the display, and the operator inputs instructions via the touch panel, thereby selecting each icon. The detection method of the instruction input from the subject by the touch panel may be any method such as a capacitive type or a resistive film type. The input interface 113 does not always need to be physically provided in the processing device 100, and may be connected as necessary via a wired or wireless network.

[0026] The output interface 114 functions as an output unit for outputting information such as result information and medical information obtained as a result of analysis by the processing device 100. An example of the output interface 114 is an interface for connecting to an external device or equipment such as a display device 200 composed of a liquid crystal panel, an organic EL display, a plasma display, or the like. However, when the processing device 100 itself has a display, the display can function as the output interface. In addition, when the processing device 100 is connected to the display device 200 or the like via a communication interface 115, the communication interface 115 can also function as the output interface 114.

[0027] The communication interface 115 functions as a communication unit for transmitting and receiving measurement data, medical information, output information, etc., between the measurement device 400, the display device 200, the model generating device 300, the management device 500, the terminal device 600, other processing devices, server devices, etc., via a wired or wireless communication network. Examples of the communication interface 115 include various types of connectors for wired communication such as USB and SCSI, transmitting and receiving devices for wireless communication such as LTE, wireless LAN, Bluetooth (registered trademark), and infrared, and various connection terminals for printed circuit boards and flexible circuit boards.

[0028] Although the configuration of the display device 200 will not be described in detail, as described above, it includes a display configured of a liquid crystal panel, an organic EL display, a plasma display, or the like, at least one of an input interface and a communication interface that accepts input of various information from the processing device 100, and a processor that performs processing to display the various information accepted on the display. Such a display device 200 is not limited to one having only a display function, and may be any device that can display medical information output from the processing device 100. Therefore, the display device 200 also includes a laptop computer, a smartphone, a tablet terminal, and the like.

[0029] Furthermore, the configuration of the model generation device 300 for generating a trained analysis model will not be described in detail. However, like the processing device 100, it includes a processor, a memory, an input interface, an output interface, and a communication interface. Such a device may be a laptop computer, a desktop computer, a smartphone, a tablet terminal, a server device, or a combination of these.

[0030] In the present disclosure, the processing device 100, the display device 200, and the model generating device 300 are provided as separate devices. However, this is not limiting, and for example, the processing device 100 may function as at least one of the display device 200 and the model generating device 300.

[0031] 3. Information stored in memory 112 of processing device 100 3 is a diagram conceptually illustrating a subject management table stored in the processing device 100 according to an embodiment of the present disclosure. The information stored in the subject management table is updated and stored as needed in accordance with the progress of processing by the processor 111 of the processing device 100.

[0032] According to FIG. 3, the subject management table stores subject information, measurement data, input information, result information, medical information, etc. in association with subject ID information. "Subject ID information" is information for identifying each subject with information unique to each subject. Subject ID information is generated each time a new subject is registered by an operator or the subject himself / herself. "Subject information" is information regarding the attributes of each subject. Examples of such attribute information include subject name information, date of birth information, gender information, address information, other measurement data, medical record information, findings information, interview information, disease-related information (for example, causes of disease such as traffic accidents, falls, fires, etc. provided by emergency personnel, accident occurrence circumstances, witness information, physical findings, etc.), etc.

[0033] The "measurement data" is information indicating at least one of the measurement data itself indicating the state of the human body measured by the measuring device 400, and the processed measurement data that has been subjected to various processes such as high resolution, pixel complementation, compression, and change of data format or data form based on the measurement data as necessary. Such measurement data is information received from the measuring device 400 via the communication interface 115. The processed measurement data may be processed by the measuring device 400 or the processing device 100. When a CT image is used as the measurement data, it means each of multiple CT images taken over a predetermined range (for example, multiple parts or the whole body), or the entire multiple CT images. Such a CT image may be either a still image or a video, and may be in any image format such as a black and white image or a color image. A specific example of such measurement data will be described later with reference to FIG. 6 and the like.

[0034] "Input information" is information that is input to the trained analysis model to obtain result information. When multiple CT images are used as measurement data, the input information typically uses one or more specific CT images among the multiple CT images. Such multiple CT images are acquired at regular spatial intervals. In other words, each CT image included in the multiple CT images has spatial continuity or association with the CT images before and after it. Specific examples of such input information will be described later with reference to FIG. 7 etc.

[0035] The "result information" is information obtained by inputting input information into the trained analysis model. When multiple CT images are used as the measurement data, the result information is typically information indicating the type of pathology detected in each CT image, the location where each pathology occurs, and the severity of each pathology. Examples of the severity of such pathology include not only specific numerical values ​​but also classifications based on numerical values ​​(e.g., "Level 1", "Level 2", "Level 3", or "Level 4", or "Mild", "Moderate", or "Severe", and the number of classifications may be any). In addition, the severity included in the result information may be the degree of abnormality in each pathology, or the priority of the required medical intervention. The priority of the medical intervention may be determined based on at least one of the type of pathology and the degree of abnormality. For example, a pathology that should be treated early may be assigned a higher severity than other pathologies, regardless of the degree of abnormality.

[0036] Here, in this embodiment, a pathological condition indicates a type of change or symptom caused in the body due to an external or internal influence on the body, and preferably means a condition whose presence or absence can be detected or determined by measurement data acquired by the measurement device 400. Examples of such pathological conditions include bleeding, fracture, infection, injury, inflammation, tumor, ischemia, or abnormalities in liquid components such as pleural effusion and ascites, and abnormal distribution of gas components associated with gastrointestinal perforation, and in this embodiment, not only a specific pathological condition is the subject of analysis, but multiple pathological conditions are the subject of analysis. In addition, a pathological condition generally does not include information on the site where it occurs, and is different from a disease (e.g., a specific disease or illness such as subarachnoid hemorrhage) in which the site where the pathological condition occurs is specified by a doctor's diagnosis or the like.

[0037] The result information may also include more detailed information such as findings information for each pathology. For example, examples of findings information include information on findings that can be observed from the acquired measurement data, such as at least one of "bleeding point," "amount of bleeding," "speed of bleeding," and "recency of bleeding" for the pathology of "bleeding," and at least one of "fracture point," "fracture form," and "recency of fracture" for the pathology of "fracture."

[0038] "Medical information" is information generated based on result information. The medical information is output to the display device 200 via the output interface 114 and displayed on the display device 200, or transmitted to a terminal device 600 selected based on the result information. Typical examples of medical information include the medical information shown in Figs. 8A to 10B. That is, the medical information includes: (1) Measurement data (2) Information indicating the presence or absence of pathologies identified by the analysis of the measurement data, information indicating the type of each pathology, the location where each pathology is occurring (i.e., information indicating the location where each pathology is occurring), and information indicating the severity of each pathology. (3) Findings obtained through analysis of measurement data (4) Papers or websites that provide treatments for diseases related to the condition (5) Information on the pathology and medicines that are useful for treating diseases related to that pathology (6) Information about medical institutions specializing in the condition or diseases related to the condition (7) Information regarding devices and equipment for the treatment of pathological conditions or diseases related to those conditions It should be noted that the medical information does not necessarily include all of the above information. Furthermore, the above information is merely an example of the medical information, and it may of course include other information.

[0039] In particular, in this embodiment, the medical information is output in such a way that the identified pathological conditions and the locations where the pathological conditions occur can be identified. (1) Depending on the severity of each pathology, display objects are output that notify only those pathologies with high severity. (2) When outputting multiple pathologies identified on one screen, a different display object is generated for each pathology, and each display object is output at a position corresponding to the location where the pathology occurred. (3) Divide the screen into multiple screens according to the pathological condition, and output the screen selected according to the instruction input from the operator. (4) A combination of (1) to (3) above These output methods are merely examples, and any method may be used as long as it is possible to output information in a manner that allows identification of each pathology.

[0040] The information stored in the subject management table may be stored in memory 112 of processing device 100, but may also be stored in other devices, such as other processing devices or database devices.

[0041] 4. Processing flow executed by the processing device 100 Fig. 4 is a diagram showing a processing flow executed in the processing device 100 according to an embodiment of the present disclosure. Specifically, Fig. 4 is a diagram showing a processing flow executed by the processor 111 of the processing device 100 from when a medical image is acquired in the measuring device 400 until when medical information is output. The processing flow is mainly performed by the processor 111 of the processing device 100 reading and executing a program stored in the memory 112.

[0042] First, although not shown in the figure, for example, when a subject is rushed to a medical institution, a medical professional operates the measuring device 400 (e.g., a CT device) to take multiple CT images of the subject's entire body. The measured data are then acquired by the measuring device 400 and transmitted to the processing device 100 via a communication interface of the measuring device 400 together with subject ID information for identifying the measured subject.

[0043] When the processor 111 of the processing device 100 receives measurement data including multiple CT images from the measuring device 400 via the communication interface 115, the processor 111 stores the received measurement data in the subject management table in association with the subject ID information (S111).

[0044] The processor 111 performs a predetermined pre-processing on each of the received CT images (S112). The pre-processing is not essential and may be performed as desired. Examples of such pre-processing include filter processing such as band pass filters including high pass filters and low pass filters, averaging filters, Gaussian filters, Gabor filters, Canny filters, Sobel filters, Laplacian filters, median filters, and bilateral filters, blood vessel extraction processing using Hessian matrices, segmentation processing of a specific region (e.g., a disease region) using machine learning, trimming processing of the segmented region, declouding processing, super-resolution processing, low-resolution processing, and combinations thereof. By performing such pre-processing, it is possible to perform high definition, low resolution, region extraction, noise removal, edge enhancement, image correction, image conversion, and the like on each of the received medical images. Although not particularly illustrated, the processor 111 stores each pre-processed CT image in the subject management table as measurement data in association with subject ID information.

[0045] Next, the processor 111 accepts an operation input by an operator via the input interface 113 in order to select desired subject ID information for analyzing the medical image from among multiple subjects stored in the subject management table. Then, upon accepting the operation input, the processor 111 reads out the measurement data associated with the subject ID information from the subject management table, and stores the measurement data associated with the subject ID information as input information to be input to the trained analysis model. The processor 111 executes an analysis process by inputting the input information to the trained analysis model (S113). Details of the generation of the trained analysis model and the analysis process will be described later with reference to FIGS. 5 to 7C.

[0046] Next, when processor 111 acquires analysis result information from the trained analytical model in the analysis process, processor 111 stores the acquired result information in the subject management table in association with the subject ID information (S114).

[0047] Next, when the result information is acquired, the processor 111 generates medical information using the result information and the measurement data. The processor 111 stores the generated medical information in the subject management table in association with the subject ID information. The processor 111 also outputs the stored medical information to the display device 200 or the like via the output interface 114 (S115). At this time, the processor 111 identifies a pathology included in the measurement data, and generates medical information in a form that can be identified for each identified pathology. The generated medical information will be described later with reference to Figs. 7B to 10B and the like. As a method for identifying a pathology included in the measurement data, the processor 111 may identify a pathology with a high probability of existence based on the result information acquired in S114, or may identify a pathology according to an input indicating a pathology designated by an operator. When a pathology is designated by an operator, the operator operates the processing device 100 to designate a pathology to be noted, and the processor 111 acquires an input indicating the designated pathology after the processing of S112. This causes the processor 111 to finish the processing flow from acquisition of a medical image to output of medical information.

[0048] In this manner, in the process flow, medical information is generated in a manner that allows identification of each identified pathology. Therefore, the process flow enables, for example, medical personnel to quickly determine which pathology requires priority treatment based on the medical information.

[0049] Although not shown in the figure, the display device 200 that receives the medical information displays the received medical information on its display. Although the display device 200 is given as an example of an output destination of the medical information, the output destination may be any, such as a terminal device carried by an operator or other medical staff, or another processing device or other medical device in a medical institution.

[0050] Also, in Fig. 4, the case where the result information is acquired by inputting the input information to the trained analysis model has been described. However, using the trained analysis model is merely an example, and other methods may be used as a matter of course. For example, it is also possible to use other image analysis processes, such as a method of comparing the degree of agreement between a CT image acquired as measurement data and an image showing a pathological condition, or to use the trained analysis model and these other image analysis processes in combination.

[0051] 4, a case has been described in which the processor 111 of the processing device 100 acquires analysis result information by processing a medical image with a trained analysis model stored in the memory 112. However, this is not limiting, and the processor 111 may transmit input information to, for example, a server device, and the processor of the server device may process the input information with the trained analysis model stored in the server device to generate result information. Then, the processing device 100 may acquire the result information from the server device.

[0052] 5. Processing flow executed by the model generating device 300 Fig. 5 is a diagram showing a process flow executed in the model generating device 300 according to an embodiment of the present disclosure. Specifically, Fig. 5 is a diagram showing a process flow relating to generation of a trained analytical model used in the analysis process of S113 in Fig. 4. This process flow is mainly performed by the processor of the model generating device 300 reading and executing a program stored in a memory. In this embodiment, such a trained analytical model is generated in advance for each pathology that is a specific target.

[0053] According to Fig. 5, for example, a step of acquiring measurement data measured by the measuring device 400 as learning data may be executed (S211). For example, when a CT device is used as the measuring device 400, multiple CT images of the subject's entire body are used as the learning data. Note that the learning data may be CT images actually captured using the CT device as described above, or simulation images acquired by a simulation using image processing. The following describes the case where multiple CT images are used as learning data.

[0054] Next, a process is executed in which information (e.g., the presence or absence of bleeding, the location of bleeding, and the degree of bleeding) on ​​a pathology (e.g., bleeding) found in each of the multiple acquired learning data is labeled as disease information (S212). The labeling is performed by a medical professional such as a doctor inputting each pathology and its degree (e.g., severity), and position information of the body part where the pathology occurs (e.g., information indicating organs such as the liver, pancreas, and spleen, or coordinates in the learning data). Examples of the degree include "corresponding" or "not corresponding" to the pathology (bleeding), "level 1", "level 2", "level 3", or "level 4", "mild", "moderate", or "severe". Alternatively or in addition to this, CT images showing bleeding prepared in advance may be prepared, and the degree of agreement with these images may be calculated by image analysis processing, and labeling may be performed based on the degree of agreement.

[0055] When the multiple pieces of learning data and the corresponding label information are obtained, a step of performing machine learning of bleeding patterns using them is executed by the processor (S213). As an example, the machine learning is performed by providing a set of the learning data and the label information to a neural network configured by combining neurons, and repeating learning while adjusting the parameters of each neuron so that the output of the neural network is the same as the label information. Then, a step of acquiring a trained analysis model (for example, a neural network and parameters) is executed (S214). As a result, the processor ends the generation of the trained analysis model. Then, by a similar process / method, a labeling process is performed on the learning data for other pathologies (for example, fractures, infections, etc.), and machine learning of pathology patterns is executed using the learning data and the label information. Then, it is possible to generate a trained analysis model used to analyze each pathology. In this way, a trained analysis model is generated for each pathology, and each generated trained analysis model is acquired.

[0056] In this way, by generating a different trained analysis model for each pathology, it is possible to process the pathologies in order of priority, or to process each trained analysis model in parallel using multiple processing devices, thereby enabling more rapid output of medical information.

[0057] The acquired trained analysis model may be transmitted to the processing device 100 via a communication interface and stored in the memory 112 of the processing device 100. In addition, the trained analysis model may be stored in the memory of the model generation device 300, another processing device, a server device, or the like.

[0058] In the example of FIG. 5, a case where a trained analysis model is generated and acquired for each pathology has been described. However, this is not limited to the above, and multiple pathologies may be identified by one trained analysis model, and the location where each pathology occurs and its severity may be analyzed. In this trained analysis model, the learning data obtained in S211 is labeled with each identified pathology, position information of the body part where the pathology occurs (for example, information indicating organs or organs such as the liver, pancreas, and spleen, or coordinates in the learning data), and the degree of each pathology (for example, severity). Thereafter, the learning data and the label information are input to the model generating device 300, and machine learning of the pathology pattern is performed, thereby acquiring one trained analysis model capable of analyzing each pathology. In this way, by using one trained analysis model, it is possible to reduce the processing load related to the generation of the trained analysis model.

[0059] In the example of FIG. 5, a case where information on pathology (for example, the presence or absence of each pathology, the location where the pathology occurs, and the degree of the pathology) is used as label information for learning has been described. However, the label information is not limited to these, and it is also possible to include more detailed label information such as finding information for each pathology. For example, when the measurement data is labeled with "bleeding", the finding information of "bleeding point" and "new or old bleeding" is also labeled. When the measurement data is labeled with "fracture", the finding information of "fracture point", "fracture form", and "new or old fracture" is also labeled. Specifically, in the case of medical images such as CT images and MRI images, the bleeding area appears whiter than other areas (i.e., in the case of CT, it shows a higher CT value), so the finding of the bleeding point is obtained from the medical image. Similarly, when fresh bleeding appears whiter than old bleeding (i.e., in the case of CT, it shows a higher CT value), so the finding of new or old bleeding is obtained from the medical image. In addition, in the case of medical images such as X-ray images, CT images, and MRI images, findings of the location where the fracture has occurred (fracture point) and its form (for example, transverse fracture, oblique fracture, spiral fracture, or comminuted fracture) are obtained from the medical image. Similarly, in the case of a fresh fracture, because of leakage of liquid components due to the fracture, the fracture appears whiter than an old fracture, findings of the old and new fractures are obtained from the medical image. In this way, by adding the finding information for each pathology as label information and having the model generating device 300 learn, a trained analysis model is obtained that can output the finding information for each pathology in addition to identifying the presence or absence of each pathology, the location where the pathology has occurred, and its severity. For other pathologies, a similar trained analysis model is obtained by similarly training the finding information as label information.

[0060] 6. Measurement Data As described above, the measurement data is data indicating the state of the human body measured by the measuring device 400, and is information received from the measuring device 400 via the communication interface 115. Fig. 6 is a diagram conceptually illustrating an example of the measurement data according to an embodiment of the present disclosure. Fig. 6 illustrates a case in which a plurality of CT images taken by the measuring device 400 (e.g., a CT device) are used as the measurement data.

[0061] Such CT images are typically obtained by capturing cross sections in the thickness direction from the head to the legs of the body at a spatially constant interval (e.g., slice interval=5 mm) over a predetermined range (at least a plurality of sites (e.g., head, chest, abdomen, pelvis, etc.) or the entire body) of the human body. In FIG. 6, a plurality of CT images including at least CT images Dm-7 to Dm and CT images Dn-7 to Dn as measurement data are captured at a spatially constant interval (e.g., slice interval=5 mm) over a plurality of sites A to D (i.e., the entire body). Note that the sites shown in FIG. 6 are examples for convenience of explanation and do not necessarily accurately represent specific sites of the human body.

[0062] Since the multiple CT images thus obtained are taken at regular intervals as described above, for example, by referring to multiple consecutive CT images such as CT image Dm-7 to CT image Dm, it is possible to confirm the pathology occurring in the part included in each CT image. That is, by focusing on each CT image, it is possible to detect each pathology included in each CT image, the location where each pathology occurs on the cross section, and its severity. Furthermore, by focusing on multiple consecutive CT images, it is possible to grasp each pathology, the location where each pathology occurs on the cross section, and the transition of the severity. In the present disclosure, by performing an analysis process using a specific one or multiple (preferably one) CT images selected from the multiple CT images as input information, it is possible to obtain these pieces of information as result information. Furthermore, by performing the same process on multiple CT images having spatial continuity or association, it is possible to obtain spatial transition information of each pathology included in the CT image (i.e., transition information in the up-down direction when the body is in an upright position). In addition, "having spatial continuity or correlation" means not only that each CT image is taken at a regular interval (e.g., slice interval = 5 mm), but also that the images are taken by a series of measurement processes performed on the same subject using the measuring device 400.

[0063] Here, CT images are often used to determine the presence or absence of disease in emergency medical care. However, in such cases, CT images are taken at least across multiple parts (sometimes the whole body) at regular intervals, so medical personnel need to check a considerable number of CT images one by one to determine the presence or absence of disease. In the processing system 1 according to the present disclosure, it is possible to obtain result information using multiple CT images, which are the acquired measurement data, as input information, and output the result information as medical information. Therefore, the processing system 1 according to the present disclosure can be usefully used in determining the presence or absence of a pathology in emergency medical care, in diagnosis based on the result, and in subsequent processing. However, naturally, its use is not limited to the judgment in emergency medical care.

[0064] 7. Processing related to the generation of medical information 6, measurement data (e.g., CT images) captured by the measuring device 400 is transmitted to the processing device 100 and processed by the processor 111 of the processing device 100 to generate medical information. Fig. 7A is a diagram conceptually illustrating an example of a process in which medical information is generated by processing measurement data according to an embodiment of the present disclosure.

[0065] FIG. 7A shows that, as shown in FIG. 6, multiple CT images (CT images D1-1 to D1-n) taken by the measuring device 400 across a predetermined range of the body (e.g., multiple parts of the body or the entire body) are acquired as measurement data by the processing device 100.

[0066] Next, these multiple CT images are selected for each individual CT image (CT image E1-1, CT image E1-2 to CT image E1-n) by processing of the processor 111, and input as input information to the trained analysis model for each pathology (analysis processing). Note that all CT images D1-1 to D1-n (measurement data) taken in the measurement device 400 and acquired in the processing device 100 may be acquired as the individual CT images (CT image E1-1, CT image E1-2 to CT image E1-n) that are input information. Also, CT images selected at regular intervals (for example, every 5 images) from all CT images D1-1 to CT image D1-n (measurement data) may be acquired as the individual CT images (CT image E1-1, CT image E1-2 to CT image E1-n) that are input information. Furthermore, a CT image selected by the operator from all CT images D1-1 to D1-n (measurement data) may be acquired as individual CT images (CT image E1-1, CT image E1-2 to CT image E1-n) that are input information.

[0067] As described above, the CT images E1-1, E1-2 to E1-n are acquired as input information and input to the trained analysis model for each pathology, thereby generating result information for each pathology. That is, by inputting the CT image E1-1, each pathology contained in the image, the location where each pathology occurs, and its severity are acquired as result information. Also, by inputting the CT image E1-2, each pathology contained in the image, the location where each pathology occurs, and its severity are acquired as another result information. Also, by inputting the CT image E1-n, each pathology contained in the image, the location where each pathology occurs, and its severity are acquired as yet another result information. In this way, in the analysis process, each pathology, the location where each pathology occurs, and its severity are acquired as result information for each CT image acquired as input information. Then, the acquired information indicating each pathology, the location where each pathology occurs, and its severity is stored for each CT image as result information in the subject management table.

[0068] In the above, a case has been described in which each CT image is input as input information to the trained analysis model, but CT images may be prepared in groups of several images, for example, three images, and input to the trained analysis model for each group. In this case, the name of the disease acquired for each CT image, the location of the disease, and the average, maximum, and minimum values ​​of the severity of the disease may be obtained for each group, and these may be used as result information.

[0069] In the above, a case has been described in which result information on a plurality of pathologies is obtained using a trained analysis model prepared for each pathology. However, this is not limiting, and result information on a plurality of pathologies may be obtained using one trained analysis model. In such a case, the input information on the CT image E1-1, CT image E1-2 to CT image E1-n is input to the trained analysis model, and the presence or absence of each pathology, the location where each pathology occurs, and the severity of each pathology are obtained.

[0070] In addition, in the above, a case has been described in which information indicating each pathology, the location where each pathology occurs, and its severity is obtained as result information from the trained analysis model. However, this is not limited to this, and for example, by using a trained analysis model that has been trained with finding information for each pathology as label information, it is possible to obtain finding information in addition to these. Examples of such finding information include at least one of "bleeding point", "new or old bleeding", and "estimated amount of bleeding" from the area of ​​the site where bleeding is observed in the case of a "bleeding" pathology, and at least one of "fracture point", "fracture form", and "new or old fracture" in the case of a "fracture" pathology.

[0071] Next, according to FIG. 7A, medical information is generated by the processing of the processor 111 based on the obtained result information.

[0072] In this way, by using CT images E1-1 to E1-n as input information, each pathology contained in each CT image, the location where each pathology occurs, and its severity are obtained as separate result information. That is, the type of each pathology occurring from each CT image, the cross-sectional position where each pathology occurs, and its severity information are obtained. In addition, CT images E1-1 to E1-n are spatially continuous images in the vertical direction when the body is standing upright. Therefore, it is possible to obtain transition information of each pathology from each CT image, that is, information on the vertical position where each pathology occurs.

[0073] Here, Figures 7B and 7C are diagrams showing a processing flow executed in the processing system 1 according to an embodiment of the present disclosure. Specifically, Figures 7B and 7C show a processing flow executed in S113 to S115 in Figure 4 and the analysis processing and output processing using the trained analysis model in Figure 7A. The processing flow is mainly performed by the processor 111 of the processing device 100 reading and executing a program stored in the memory 112.

[0074] According to FIG. 7B, the processor 111 executes the process related to the process flow by acquiring input information generated by subjecting the measurement data to the pre-processing (S112) shown in FIG. 4. First, the processor 111 refers to a priority table stored in the memory 112 and reads the priority table (S211). The priority table is a table that specifies the order in which analysis processes are performed among a plurality of pathological conditions to be analyzed. As an example of the priority table, each pathological condition is stored in the order of high priority, namely, bleeding, fracture, infection, injury, inflammation, tumor, ischemia, abnormality in liquid components such as pleural effusion and ascites, and abnormal distribution of gas components associated with perforation of the digestive tract. In general, the analysis process according to this embodiment requires at least several milliseconds to several minutes for each trained analysis model. In the field of emergency medical care, extremely rapid judgment is required, and therefore it is essential to present information in a timely manner. Therefore, for example, by processing in order of pathological conditions that require urgent treatment, medical information can be output more quickly. Such a priority table may be stored according to predetermined priorities, or may be set according to priorities set by an operator or the like to reflect the workflow of a medical institution, etc.

[0075] Next, the processor 111 inputs the input information to a trained analytical model (first trained analytical model) for analyzing the pathology with the highest priority (first pathology) according to the read priority table (S212). Then, the processor 111 acquires the analysis result of the first pathology from the first trained analytical model as result information (S213). The acquired result information is stored in the subject management table.

[0076] When the result information of the first pathological condition is acquired, the processor 111 determines whether or not the severity of the acquired first pathological condition exceeds a predetermined threshold (S214). If it is determined that the severity exceeds the predetermined threshold, the processor 111 generates a display object for notifying the same. As an example, if the severity exceeds the predetermined threshold and is "severe," the processor 111 generates a display object for prompting the operator or a medical professional to immediately check the first pathological condition.

[0077] When the display object is generated, the processor 111 generates medical information including the display object for the first pathology based on the result information acquired in S213, and outputs the generated medical information to the display device 200 via the output interface 114 or the communication interface 115 (S216). Note that, when the severity of the first pathology does not exceed a predetermined threshold in S214, the processor 111 outputs the medical information in a form that does not include the display object.

[0078] Next, the processor 111 inputs the input information to a trained analytical model (second trained analytical model) for analyzing the pathology (second pathology) with the next highest priority according to the read priority table (S221). Then, the processor 111 acquires the analysis result of the second pathology from the second trained analytical model as result information (S222). The acquired result information is stored in the subject management table.

[0079] 7C, when the result information of the second pathology is acquired, the processor 111 judges whether or not the acquired severity of the second pathology exceeds a predetermined threshold (S223). If it is judged that the severity exceeds the predetermined threshold, the processor 111 generates a display object in a form different from the notification object of the first pathology to notify the fact.

[0080] When the display object is generated, the processor 111 generates medical information including the display object for the second pathology based on the result information acquired in S222, and outputs the generated medical information to the display device 200 via the output interface 114 or the communication interface 115 (S225). Note that, when the severity of the second pathology does not exceed a predetermined threshold in S223, the processor 111 outputs the medical information in a form that does not include the display object.

[0081] Next, the processor 111 repeats the same process up to the pathology with the last priority (nth) according to the read priority table. Specifically, the processor 111 inputs input information to a trained analysis model (nth trained analysis model) for analyzing the nth pathology (S231). Then, the processor 111 acquires the analysis result of the nth pathology from the nth trained analysis model as result information (S232). The acquired result information is stored in the subject management table.

[0082] When the result information of the nth pathology is acquired, the processor 111 judges whether or not the severity of the acquired nth pathology exceeds a predetermined threshold (S214). If it is judged that the severity exceeds the predetermined threshold, the processor 111 generates a display object in a form different from the notification objects of the first pathology and the second pathology to notify the fact.

[0083] When the display object is generated, the processor 111 generates medical information including the display object for the nth pathology based on the result information acquired in S213, and outputs the generated medical information to the display device 200 via the output interface 114 or the communication interface 115 (S216). Note that, if the severity of the nth pathology does not exceed a predetermined threshold in S214, the processor 111 outputs the medical information in a form that does not include the display object. This causes the processor 111 to end the analysis process for each pathology.

[0084] In this way, by inputting input information into a trained analysis model generated for each pathology based on predetermined priorities for multiple pathologies and acquiring the analysis results as result information, it is possible to acquire result information preferentially from pathologies with high treatment priorities, for example, and output medical information, which enables medical personnel to more quickly treat pathologies with high priorities.

[0085] In the examples of Fig. 7B and Fig. 7C, the same threshold is used as the predetermined threshold for the first pathology, the second pathology, and the nth pathology. However, this is not limited to this, and a different threshold may be used for each pathology. As an example, when the first pathology is bleeding, a display object may be generated only when the condition corresponds to "severe," and when the second pathology is a fracture, a display object may be generated for both "severe" and "moderate" conditions. In this way, by adjusting the threshold for each pathology, it is possible to flexibly output medical information according to the severity of each pathology.

[0086] 8. Medical information output <Example 1 of medical information output in an identifiable manner> 8A and 8B are diagrams showing an example of medical information output from the processing device 100 according to an embodiment of the present disclosure. Specifically, FIGS. 8A and 8B show an example of medical information including result information obtained by analysis based on measurement data (e.g., CT image) measured by the measurement device 400, displayed on a display or the like. According to FIG. 8A, subject ID information for identifying the subject is output at the top. Furthermore, tabs 23a to 23e are output for selecting a pathology to be output and corresponding medical information. The desired pathology is selected by the input interface 113 accepting instruction inputs from an operator, a medical professional, or the like to these tabs 23a to 23e. Such tabs include an "Overall" tab 23a for selecting medical information including information on all pathologies in an aggregated manner, a "Bleeding" tab 23b for selecting medical information on bleeding, a "Fracture" tab 23c for selecting medical information on fractures, a "Bleeding + Fracture" tab 23d for selecting medical information including information on bleeding and fractures in an aggregated manner, and an "Infection" tab 23e for selecting medical information on infectious diseases. The tab 23f is a tab for temporarily displaying tabs for selecting other pathologies that cannot be displayed (for example, tumor, ischemia, inflammation, etc.). In this way, medical information is classified and output by tab for each pathology, so that medical information is output in an identifiable manner for each pathology. In the example of FIG. 8A, the "Overall" tab 23a is displayed in a normal manner, and the other tabs are displayed in a different manner, decorated in gray. This indicates that the "Overall" tab 23a is currently selected. In each tab, generated medical information is added and output every time medical information of the corresponding pathology is generated in FIG. 7B and FIG. 7C. In addition, in each of the display screens shown in FIG. 8A to FIG. 9B, subject information may be output instead of or together with the subject ID information.

[0087] In FIG. 8A, various medical information is output in the output area of ​​the “whole” tab 23a. Specifically, the area 12a includes a switching button 22 for selecting a desired CT image from among a plurality of spatially continuous CT images. The processor 111 selects a specific CT image by receiving an operation input to the switching button 22 through the input interface 113, and outputs the CT image to the display area 21. The area 12b includes medical information corresponding to bleeding (first pathology), which is the pathology with the highest priority. As an example of the medical information, a graph is shown in which the horizontal axis indicates the imaging position of the CT image in the first direction from the head to the legs of the body, and the vertical axis indicates the value indicating the severity obtained from each CT image. In addition, the area 12b includes a display object 25a for notifying that a severity exceeding the threshold of S214 in FIG. 7B has been obtained in at least a part of the CT images used in the analysis. Area 12c includes medical information for a fracture (second pathology), which is the pathology with the second highest priority, and a display object 25b notifying that a severity level exceeding the threshold of S223 in Fig. 7C has been obtained. Area 12d includes medical information for an inflammation (fifth pathology), which is the pathology with the fifth highest priority, and a display object 25c notifying that a severity level exceeding a predetermined threshold has been obtained. Each of areas 12b to 12d is updated and output every time medical information to be output according to Figs. 7B and 7C is generated.

[0088] Here, as described above, medical information for bleeding (first pathology), fracture (second pathology), and inflammation (fifth pathology) is output in areas 12b to 12d, and medical information for infection (third pathology) and injury (fourth pathology), which have a higher priority than inflammation, is not output. This is because the severity of infection (third pathology) and injury (fourth pathology) has fallen below a predetermined threshold. In this way, by preferentially outputting pathologies that are highly severe and require immediate treatment in the "Overall" tab 23a, medical personnel and the like can refer to information more efficiently.

[0089] 8A, in the output area of ​​the "whole" tab 23a, together with the display objects 25a to 25c, medical information on the pathologies corresponding thereto is divided and output into areas 12b to 12d. That is, the display objects 25a to 25c and the areas 12b to 12d output medical information for each pathology in a manner that allows identification, even on the same screen. This allows medical personnel to refer to medical information on pathologies with high priority all at once on the same screen, or to refer to each pathology while comparing them.

[0090] In addition, in FIG. 8A, display objects 24a to 24c corresponding to severity are displayed superimposed on each of the tabs 23a to 23e. Each of the display objects 24a to 24c is output in a different manner for each pathological condition, similar to the display objects 25a to 25c, and each pathological condition can be identified by looking at each display object. That is, a medical worker who refers to the display object 25a can quickly select the "bleeding" tab 23b by searching for a display object 24a having the same manner as the display object 25a and inputting an instruction to the "bleeding" tab 23b to which the display object 24a is attached. Similarly, a medical worker who refers to the display object 25b can quickly select the "bone fracture" tab 23c by searching for a display object 24b having the same manner as the display object 25b and inputting an instruction to the "bone fracture" tab 23c to which the display object 24b is attached. Similarly, a medical worker who refers to the display object 25c can quickly select the "Other" tab 23f by searching for a display object 24c having the same aspect as the display object 25c and inputting an instruction to the "Other" tab 23f to which the display object 24c is attached. In this way, when a medical worker wants to see detailed information on a pathological condition with a high degree of severity, the medical worker can reach the information more quickly by using the display objects output in a distinguishable manner for each pathological condition.

[0091] Next, when the processor 111 accepts an instruction input to the "bleeding" tab 23b, the screen is switched to a screen that outputs medical information related to the pathology of "bleeding" as shown in FIG. 8B. That is, when an instruction input to a tab corresponding to a specific pathology such as the "bleeding" tab 23b or the "fracture" tab 23d is accepted, the screen is switched to a screen that outputs medical information for each pathology, so that the medical information for each pathology is output in an identifiable manner. According to FIG. 8B, the output area of ​​the "bleeding" tab 23b includes the area 13a and the area 13b, and each of them outputs more detailed information than the medical information output to the output area of ​​the "whole" tab 23a. The area 13a includes a switching button 22 for selecting a desired CT image from among a plurality of spatially continuous CT images. The processor 111 selects a specific CT image and outputs the CT image by accepting an operation input to the switching button 22 by the input interface 113. In addition, the CT image is output with the findings information acquired as one of the medical information superimposed thereon. Specifically, the "bleeding point" and "recency of bleeding" (information for distinguishing between fresh bleeding and old bleeding) acquired as bleeding finding information are output. In addition, in area 13b, information for assisting treatment of bleeding (for example, information on devices and equipment for treatment of pathological conditions and diseases related to the pathological conditions) is output as medical information.

[0092] In this way, medical information for each pathology can be identified by tabs prepared for each pathology, and by selecting a tab, the screen can be switched and output, making it possible to provide more detailed information to medical professionals.

[0093] Although a detailed description is not given of the case where another tab such as the "Fracture" tab 23b is selected, detailed medical information on the pathology corresponding to that tab is output by switching the screen, similar to the case where the "Bleeding" tab 23a is selected. In addition, the detailed medical information and screen layout output for each pathology are output differently. In other words, it is possible to output optimal medical information for each pathology in an optimal layout.

[0094] <Example 2 of medical information output in an identifiable manner> 9A and 9B are diagrams showing an example of medical information output from the processing device 100 according to an embodiment of the present disclosure. Specifically, Fig. 9A and 9B show another example in which medical information including result information obtained by analysis based on measurement data (e.g., CT image) measured by the measurement device 400 is displayed on a display or the like. According to Fig. 9A, subject ID information for identifying the subject is output at the top.

[0095] According to FIG. 9A, similarly to FIG. 8A, tabs 23a to 23e are output for selecting a pathology to be output and corresponding medical information. The desired pathology is selected by the input interface 113 receiving instruction inputs from an operator, a medical professional, or the like to these tabs 23a to 23e. FIG. 9A shows a case where the "whole" tab 23a is selected and medical information including information on all pathologies is output. Similarly to FIG. 8A, the area 14a includes a switching button for selecting a desired CT image from among a plurality of spatially continuous CT images. The processor 111 selects a specific CT image by receiving an operation input to the switching button via the input interface 113, and outputs the CT image to the display area.

[0096] Moreover, the region 14b includes a two-dimensional human body model object 32. As described above, the CT images are typically acquired by capturing cross sections in the thickness direction in a direction connecting the head and legs of the body (first direction) at spatially regular intervals over a predetermined range (at least a plurality of parts (e.g., head, chest, abdomen, pelvis, etc.) of the human body or the entire body). That is, by analyzing the presence or absence of a pathological condition, etc., as described above for the captured CT images, and further superimposing the captured CT images, it is possible to identify the position where each pathological condition has occurred in the first direction.

[0097] 9A, a two-dimensional human body model object 32 is generated by reproducing a human body model of a subject based on a plurality of CT images. Display objects 31a to 31c for notifying the position in the first direction where each pathology occurred are superimposed and output on the two-dimensional human body model object 32 reproduced from the CT images. Specifically, display object 31a indicates the position where the pathology of bleeding occurred, display object 31b indicates the position where the pathology of fracture occurred, and display object 31c indicates the position where the pathology of inflammation occurred. Each of display objects 31a to 31c has a different appearance and is output so as to be distinguishable for each pathology.

[0098] At this time, all analyzed pathologies may be output to the two-dimensional human body model object 32, but it is preferable to preferentially output only display objects corresponding to pathologies with higher severity. As described above, analysis is performed for each pathology in the order set in the priority table, and the severity of each pathology is acquired. Therefore, it is possible to preferentially output display objects corresponding to pathologies whose severity is determined to be higher than a predetermined threshold in S214, S223, S233, etc. in FIG. 7B and FIG. 7C. According to FIG. 9A, display objects 31a to 31c are output in correspondence with bleeding (first pathology), fracture (second pathology), and inflammation (fifth pathology), whose severity is determined to be higher than the threshold, respectively. This enables medical personnel to preferentially grasp the location where a pathology with a high priority for treatment is occurring.

[0099] Moreover, the display objects 31a to 31c do not need to be output at all positions corresponding to CT images in which a pathological condition is observed. As described above, the severity of each pathological condition is acquired and compared with a threshold value. Therefore, each of the display objects 31a to 31c may be configured to display only positions corresponding to CT images in which a severity exceeding the threshold value has been acquired. This allows medical personnel to quickly grasp important points.

[0100] In FIG. 9A, similarly to FIG. 8A, display objects 24a to 24c corresponding to the severity are displayed in a superimposed manner on each of the tabs 23a to 23e. The appearance of the display objects 24a to 24c corresponds to the appearance of the display objects 31a to 31c indicating the position where each pathology occurs in the first direction. That is, the display object 24a is output in an appearance corresponding to the display object 31a indicating the position where the pathology of bleeding occurs, the display object 24b is output in an appearance corresponding to the display object 31b indicating the position where the pathology of fracture occurs, and the display object 24c is output in an appearance corresponding to the display object 31c indicating the position where the pathology of inflammation occurs. As a result, when the position where the pathology to be checked with priority occurs is grasped, the tab of the pathology corresponding thereto can be found more quickly by searching for it based on the display objects 24a to 24c.

[0101] Next, when the processor 111 accepts an instruction input to the "bleeding" tab 23b, the screen is switched to one that outputs medical information related to the pathology of "bleeding" as shown in FIG. 9B. That is, when an instruction input to a tab corresponding to a specific pathology such as the "bleeding" tab 23b or the "fracture" tab 23d is accepted, the screen is switched to one that outputs medical information for each pathology, so that the medical information for each pathology is output in an identifiable manner. According to FIG. 9B, the output area of ​​the "bleeding" tab 23b includes areas 15a to 15c, and more detailed information than the medical information output to the output area of ​​the "whole" tab 23a is output. The area 15a includes a switching button 22 for selecting a desired CT image from among a plurality of spatially continuous CT images. The processor 111 accepts an operation input to the switching button 22 by the input interface 113, thereby selecting a specific CT image and outputting the CT image.

[0102] Also, in the region 15b, a display object 41a is outputted so as to be superimposed on the two-dimensional human body model object 32, as in FIG. 9A. The display object 41a indicates the position in the first direction where the pathological condition of bleeding has occurred. This allows the position in the first direction where the bleeding has occurred to be quickly grasped. Note that the display object 41a does not need to be outputted at all positions corresponding to CT images in which the pathological condition of bleeding is observed. As in FIG. 9A, only positions corresponding to CT images in which the severity exceeding a threshold value has been acquired may be indicated. This allows medical personnel to quickly grasp more important points.

[0103] Moreover, in the area 15c, information for assisting treatment for bleeding (for example, information on devices and equipment for treatment for a pathological condition or a disease related to the pathological condition) is output as medical information.

[0104] In this way, medical information for each pathology can be identified by tabs prepared for each pathology, and by selecting a tab, the screen can be switched and output, making it possible to provide more detailed information to medical professionals.

[0105] Although a detailed description is not given of the case where another tab such as the "Fracture" tab 23b is selected, detailed medical information on the pathology corresponding to that tab is output by switching the screen, similar to the case where the "Bleeding" tab 23a is selected. In addition, the detailed medical information and screen layout output for each pathology are output differently. In other words, it is possible to output optimal medical information for each pathology in an optimal layout.

[0106] Here, Fig. 10A is a diagram showing an example of medical information for each pathology output from the processing device 100 according to an embodiment of the present disclosure. Specifically, Fig. 10A shows another example of medical information output in a state superimposed on the two-dimensional human body model object 32 in the region 14b in Fig. 9A and the region 15b in Fig. 9B.

[0107] According to Fig. 10A, instead of the medical information output in the region 14b in Fig. 9A, the medical information shown in (a) can be output. Here, as described above, when measurement data acquired over the whole body, such as CT images, is used, it is possible to identify the position where the pathology has occurred in the direction connecting the head and legs of the body (first direction). Furthermore, when focusing on each CT image acquired in each cross section, it is possible to identify the position where the pathology has occurred in the direction perpendicular to the first direction (second direction: the lateral direction when the body is viewed from the front in the example of Fig. 10A). Therefore, by combining the positions in the first direction and the second direction, it is possible to output the position where the lesion has occurred so as to be identifiable in the second direction.

[0108] 10A(a), display objects 51a to 51c having different aspects according to the identified pathological condition are superimposed on the two-dimensional human body model object 32. Therefore, similar to FIG. 9A, the identified pathological condition can be identified by the display objects 51a to 51c. Moreover, the aspects of the display objects 51a to 51c correspond to the display objects 24a to 24c in FIG. 9A, respectively. Therefore, when a medical professional wishes to focus on a pathological condition based on the display objects 51a to 51c, the medical professional can more quickly select a tab by searching for the display object 24a to 24c having the corresponding aspect.

[0109] Next, instead of the medical information output in the area 15b in Fig. 9B, the medical information shown in Fig. 10A(b) can be output. That is, the medical information in Fig. 10A(b) is an example of medical information that is output as detailed information on bleeding when an instruction input to the "bleeding" tab 23b is accepted on the screen in Fig. 9A. According to (b), only a display object 51a indicating the position of bleeding is superimposed and output in correspondence with the selected tab.

[0110] As in FIGS. 9A and 9B, the display objects 51a to 51c do not need to be output for all positions where the pathological conditions have occurred, and may be output only for positions where the severity exceeds a threshold.

[0111] Furthermore, in the example of FIG. 10A, the display objects 51a to 51c happen to be output adjacent to each other, but if lesions occur at the same positions, they may be output overlapping each other.

[0112] Fig. 10B is a diagram showing an example of medical information for each pathology output from the processing device 100 according to an embodiment of the present disclosure. Specifically, Fig. 10B shows still another example of medical information output in a state superimposed on the two-dimensional human body model object 32 in the region 14b in Fig. 9A and the region 15b in Fig. 9B.

[0113] According to FIG. 10B, instead of the medical information output in the area 14b in FIG. 9A, the medical information shown in (a) can be output. Here, as the position information of each pathological condition, which is the result information acquired from the trained analysis model, instead of the coordinate information as shown in FIG. 9A, FIG. 9B, and FIG. 10A, information on organs and organs such as the liver, pancreas, and spleen can be used. Therefore, in FIG. 10B(a), instead of a two-dimensional human body model object reproduced from a CT image, a two-dimensional human body model object 62 in which each organ and each organ is divided into its subdivisions (for example, Couinaud's liver division classification) is output. That is, the two-dimensional human body model object 62 is a two-dimensional human body model object represented in an anatomical upright position, that is, a posture in which the palm faces forward and stands straight, and each organ and each organ's subdivisions are represented inside the two-dimensional human body model object.

[0114] According to (a) of FIG. 10B, display objects 61a to 61c in different modes according to the identified pathology are superimposed along each organ of the two-dimensional human body model object 62 or a region into which the organ is subdivided. Therefore, the display objects 61a to 61c can identify the organ or region in which the identified pathology occurs. Furthermore, each of the display objects 61a to 61c is output in a different mode for each pathology. Therefore, by checking the mode of the display object, the medical staff can identify the pathology. Furthermore, the modes of the display objects 61a to 61c correspond to the display objects 24a to 24c in FIG. 9A, respectively. Therefore, when there is a pathology that the medical staff wants to focus on based on the display objects 61a to 61c, the medical staff can select a tab more quickly by searching for the display object 24a to 24c in the corresponding mode.

[0115] Next, instead of the medical information output in the area 15b in Fig. 9B, the medical information shown in Fig. 10B(b) can be output. That is, the medical information in Fig. 10B(b) is an example of medical information that is output as detailed information on bleeding when an instruction input to the "Bleeding" tab 23b is accepted on the screen in Fig. 9A. According to (b), only a display object 61a indicating the organ or area where bleeding has occurred is output in a superimposed manner in response to the selected tab.

[0116] As in FIGS. 9A and 9B, each of the display objects 61a to 61c does not need to be output in all organs or areas where each pathological condition has occurred, and may be output by being superimposed only on an organ or area where a severity exceeding a threshold is observed.

[0117] In this way, by using a two-dimensional human body model object such as that shown in FIG. 10B, the organ or area in which each pathological condition occurs can be more directly grasped.

[0118] As described above, in the present embodiment, it is possible to provide a processing device, a processing program, a processing method, and a processing system that are capable of outputting medical information more effectively.

[0119] 9.Other In the above embodiment, the information output to the measurement data area and the pathological condition information area has been described by giving specific examples. However, in the present disclosure, it is sufficient to select an appropriate output mode for each identified pathological condition, and the information output in each output mode is not limited to these specific examples.

[0120] In the above embodiment, the case where several kinds of devices including a CT device are used as the measurement device 400 has been described. However, the present invention is not limited to these, and an MRI device, an X-ray device, an electrocardiograph device, an ultrasonic diagnostic device, an endoscope device, a blood pressure monitor device, an angiograph, or a combination thereof may be used as the measurement device 400, and an MRI image, three-dimensional measurement data, X-ray image data, electrocardiogram data, echo examination data, endoscope image data, blood pressure measurement data, blood sampling data, respiratory function data, angiography images, and other examination data, or a combination thereof, may be used as input information. For example, when blood pressure measurement data is used, local blood pressure measurement data at a certain time point or blood pressure measurement data that changes over time in a predetermined period of time may be used as input information.

[0121] In the above embodiment, result information (presence or absence of a pathological condition, the location where the pathological condition occurs, and its severity) is obtained based on the measurement data measured by the measuring device 400. However, result information may be obtained by combining, in addition to the measurement data measured by the measuring device 400, interview information, findings information, other measurement data (MRI images, three-dimensional measurement data, X-ray image data, electrocardiogram data, echocardiogram data, endoscopic image data, blood pressure measurement data, blood sampling data, respiratory function data, other test data, or a combination of these), etc.

[0122] The trained analysis model described in the above embodiment is generated using a neural network or a convolutional neural network. However, the trained analysis model is not limited to these, and can be generated using machine learning such as a nearest neighbor method, a decision tree, a regression tree, or a random forest.

[0123] In the above embodiment, the case where the two-dimensional human body model object 32 or the two-dimensional human body model object 62 is used has been described. However, with measurement data such as CT images, it is also possible to obtain position information in the depth direction (third direction: the depth direction when the body is viewed from the front in the example of FIG. 10A) in addition to the first direction and the second direction. Therefore, it is also possible to use a three-dimensional human body model instead of the two-dimensional human body model object 32 or the two-dimensional human body model object 62, and output each display object three-dimensionally by superimposing it on the three-dimensional human body model. Furthermore, in the example of FIG. 9A, each display object is output so as to indicate the position in the first direction, but this is not limited thereto, and the two-dimensional human body model object and each display object may be output so as to indicate the position in the second direction or the third direction. Furthermore, as long as the position where the lesion occurs in any of the first direction to the third direction can be indicated, medical information may be output in the form of a graph or the like having the position on the horizontal axis and the severity on the vertical axis instead of or in addition to the two-dimensional or three-dimensional human body model. In addition, it is possible to generate an image of a cross section of the body on an arbitrary plane by reconstructing the image using imaging data of a plurality of consecutive CT images of the body. Therefore, the processing device 100 may specify the occurrence position of each pathology in a direction different from the above-mentioned first to third directions (for example, a fourth direction that is neither parallel nor perpendicular to the first direction of the body axis) and output the position in an identifiable manner.

[0124] In the above embodiment, the pathology, its location, and its severity are output as one piece of medical information by various display objects in an identifiable manner. However, they may be output in an identifiable manner by other methods such as other figures, text, sound, vibration, etc., without being limited to the figures specifically depicted in each drawing.

[0125] In the above embodiment, the case where medical information is output in an identifiable manner using tabs for each pathology in Figures 8A to 9B etc. However, the present invention is not limited to this, and the medical information to be output may be switched by other methods such as switching windows or selecting menu items.

[0126] In the above embodiment, a case has been described in which the priority is set using a priority table in the order of highest priority pathological condition: bleeding, fracture, infection, injury, inflammation, tumor, ischemia, abnormality in liquid components such as pleural effusion and ascites, and abnormal distribution of gas components associated with gastrointestinal perforation, etc. However, such an order of priority is merely an example, and may be changed as appropriate based on the workflow of a medical institution, the selection of an operator, etc. Furthermore, the target pathological conditions are not limited to those described above, and other combinations of pathological conditions may be used.

[0127] The processes and procedures described in this specification can be realized not only by those explicitly described in the embodiments, but also by software, hardware, or a combination of these. Specifically, the processes and procedures described in this specification can be realized by implementing logic corresponding to the processes in a medium such as an integrated circuit, a volatile memory, a non-volatile memory, a magnetic disk, or an optical storage. In addition, the processes and procedures described in this specification can be implemented as computer programs and executed by various computers including a processing device and a server device.

[0128] Although the processes and procedures described herein are described as being executed by a single device, software, component, or module, such processes or procedures may be executed by multiple devices, multiple software, multiple components, and / or multiple modules. Furthermore, although the various information described herein is described as being stored in a single memory or storage unit, such information may be stored in multiple memories provided in a single device or multiple memories distributed across multiple devices. Furthermore, the software and hardware elements described herein may be realized by integrating them into fewer components or breaking them down into more components. [Explanation of symbols]

[0129] 1 Processing System 100 Processing equipment 200 Display device 300 Model Generator 400 Measuring Equipment

Claims

1. A processing device comprising at least one processor, The at least one processor: Acquire measurement data that measures the state of a person's body, acquiring medical information relating to each of a plurality of pathological conditions occurring in the body based on the measurement data; outputting the acquired medical information in a manner that allows identification of each pathology; 2. A processing device configured to perform processing for:

2. The processing device according to claim 1 , wherein the medical information is acquired by inputting the measurement data into a trained analysis model.

3. The processing device according to claim 1 , wherein the measurement data is acquired by a CT device, an MRI device, an X-ray device, an electrocardiograph device, an ultrasonic diagnostic device, an endoscope device, a blood pressure monitor device, an angiograph device, or a combination thereof.

4. The processing device of claim 3 , wherein the measurement data is a medical image.

5. The treatment device according to claim 1 , wherein the pathological condition is bleeding, fracture, infection, injury, inflammation, tumor, ischemia, abnormal distribution of gas components, or abnormality of liquid components.

6. The processing device according to claim 1 , wherein the medical information includes at least one of information indicating the presence or absence of each pathological condition, information indicating the severity of each pathological condition, and information indicating the location of occurrence of each pathological condition.

7. The processing device according to claim 1 , wherein the medical information is output so as to be displayed on the same screen in a manner that allows distinction according to pathology.

8. The processing device according to claim 1 , wherein the medical information is output so as to be displayed identifiable for each pathology by switching to a screen corresponding to each pathology.

9. The processing device according to claim 1 , wherein the medical information is output in a manner that enables identification of the location of occurrence of each of a plurality of pathological conditions in at least one of a first direction connecting the head and legs of the body and a second direction perpendicular to the first direction.

10. The processing device according to claim 1 , wherein the medical information is output in a form that enables identification of the location of occurrence of each of a plurality of pathologies on the two-dimensional or three-dimensional human body model.

11. In a computer having at least one processor, the at least one processor is Acquire measurement data that measures the state of a person's body, acquiring medical information relating to each of a plurality of pathological conditions occurring in the body based on the measurement data; outputting the acquired medical information in a manner that allows identification of each pathology; A processing program that makes it function as follows.

12. A processing method executed by at least one processor in a computer having the at least one processor, comprising: Obtaining measurement data that measures a physical condition of a human being; acquiring medical information relating to each of a plurality of pathological conditions occurring in the body based on the measurement data; outputting the acquired medical information in a manner that allows identification of each pathology; A processing method comprising:

13. A processing device according to claim 1 ; a display device connected to the processing device via a communication network and configured to receive medical information output from the processing device; 13. A processing system comprising:

Images