Information processing device, information processing method and information processing program

Abstract

To provide an information processing device, an information processing method and an information processing program capable of retrieving an appropriate opinion sentence with a simple retrieval query.SOLUTION: An information processing device 10 is provided with at least one processor, and the processor retrieves a plurality of opinion candidates related to a retrieval query from an opinion sentence group including the plurality of opinion sentences, performs evaluation about each of the opinion sentence candidates on the basis of predetermined importance in each combination between diagnostic information included in the opinion sentence candidates and opinion information, and presents at least one opinion sentence candidate on the basis of an evaluation result.SELECTED DRAWING: Figure 5

Description

[Technical field]

[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, image diagnosis is performed using medical images obtained by imaging devices such as CT (Computed Tomography) devices and MRI (Magnetic Resonance Imaging) devices. A person who creates an image interpretation report, such as a doctor who reads the medical images, interprets the medical images and creates an image interpretation report that includes a statement of findings.

[0003] In order to support the creation of radiology reports, a method has been proposed for searching and presenting appropriate findings from a group of previously created findings. For example, Patent Document 1 discloses a method for executing a search process of a structured document database based on word-based information input by a user, and executing a process for generating a sentence explaining the morphological description of an image based on the input information.

[0004] For example, Patent Document 2 discloses a method for searching and outputting a reference reading report from among multiple reading reports created during previous readings, which are expressed in structured tag format, using input tag information as a search key. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2008-146220 A [Patent Document 2] JP 2006-155002 A Summary of the Invention [Problem to be solved by the invention]

[0006] When searching for a finding sentence, it is desirable to use a search query that is as concise as possible so that the desired finding sentence can be quickly reached. On the other hand, the more concise the search query, the greater the number and variations of finding sentences presented as search results, making it difficult for the user to quickly find what they are looking for. Therefore, there is a demand for a technology that allows a user to quickly reach a desired finding sentence even with a concise search query.

[0007] The present disclosure provides an information processing device, an information processing method, and an information processing program capable of searching for appropriate finding sentences with a concise search query. [Means for solving the problem]

[0008] A first aspect of the present disclosure is an information processing device including at least one processor, which searches for a plurality of candidate finding sentences related to a search query from a group of findings including a plurality of finding sentences, evaluates each of the candidate finding sentences based on a predetermined importance for each combination of diagnostic information and finding information included in the candidate finding sentences, and presents at least one candidate finding sentence based on a result of the evaluation.

[0009] In the first aspect, the processor may rearrange and present the multiple finding sentence candidates in order of the degree of importance evaluated to be high.

[0010] In the first aspect, the processor may divide the plurality of finding sentence candidates into a plurality of groups based on the type of diagnostic information contained in the finding sentence candidates, and present at least one finding sentence candidate for each group.

[0011] In the first aspect, the processor may rearrange and present the multiple finding sentence candidates for each group in order of the degree of importance evaluated to be high.

[0012] In the first aspect, the processor may present, for each group, one observation sentence candidate that is evaluated to have the highest importance.

[0013] In the first aspect, the processor may further divide the finding sentence candidates included in the group into subgroups based on a predetermined criterion, and present at least one finding sentence candidate for each subgroup.

[0014] In the first aspect, the predetermined criterion may be at least one of the number of types of diagnostic information included in the finding sentence candidate and the factuality of the diagnostic information included in the finding sentence candidate.

[0015] In the first aspect, the processor may rearrange the groups corresponding to the respective pieces of diagnostic information in descending order of frequency of the diagnostic information being included in the group of observation sentences.

[0016] In the first aspect, the importance level may be a value according to the frequency with which the combination is included in the group of observation sentences.

[0017] In the first aspect, the importance may be a value according to the degree of uniqueness of the finding information included in the combination, which is not included in combinations with other diagnostic information.

[0018] In the first aspect, the importance may be a value according to the frequency with which the combination is included in the group of findings and the degree of uniqueness of the finding information included in the combination that is not included in combinations with other diagnostic information.

[0019] In the first aspect, when the finding sentence candidates include a plurality of different combinations, the processor may perform evaluation based on the importance of each combination.

[0020] In the above first aspect, the importance is predetermined for each combination included in the group of observation sentences, and when the candidate observation sentence includes a combination for which the importance is not predetermined, the processor may correct the evaluation of the candidate observation sentence to be lowered.

[0021] In the first aspect, when there are a plurality of finding sentence candidates that include the same combination and have the same evaluation result, the processor may select and present any one of the finding sentence candidates.

[0022] In the first aspect, when there are multiple finding sentence candidates that include the same combination and have the same evaluation result, the processor may select and present the one of the finding sentence candidates that has the smallest amount of text.

[0023] In the first aspect, the processor may accept an input of a search query by a user.

[0024] In the first aspect, the processor may acquire an image and generate, based on the image, at least one of finding information and diagnosis information about the image as a search query.

[0025] In the first aspect, the finding information may indicate at least one of the type, characteristics, location, measurement values ​​and number of the region of interest, a phrase expressing a change in the region of interest, and a type of diagnostic information other than the diagnostic information that is paired with the region of interest.

[0026] A second aspect of the present disclosure is an information processing method in which a computer executes a process of searching for multiple candidate finding sentences related to a search query from a group of findings including multiple finding sentences, evaluating each of the candidate finding sentences based on a predetermined importance for each combination of diagnostic information and finding information included in the candidate finding sentences, and presenting at least one candidate finding sentence based on a result of the evaluation.

[0027] A third aspect of the present disclosure is an information processing program that causes a computer to execute a process of searching for multiple candidate finding sentences related to a search query from a group of findings including multiple finding sentences, evaluating each of the candidate finding sentences based on a predetermined importance for each combination of diagnostic information and finding information included in the candidate finding sentences, and presenting at least one candidate finding sentence based on a result of the evaluation.

[0028] According to the above aspects, the information processing device, the information processing method, and the information processing program disclosed herein can search for appropriate finding sentences using a concise search query. [Brief description of the drawings]

[0029] [Figure 1] FIG. 1 is a diagram illustrating an example of a schematic configuration of an information processing system. [Diagram 2] FIG. 1 is a diagram illustrating an example of a medical image. [Diagram 3] FIG. 1 is a diagram illustrating an example of a medical image. [Figure 4] FIG. 2 is a block diagram showing an example of a hardware configuration of an information processing device. [Diagram 5] FIG. 2 is a block diagram showing an example of a functional configuration of an information processing device. [Figure 6] FIG. 13 is a diagram illustrating an example of information registered in a report DB. [Figure 7] FIG. 13 illustrates an example of an importance table. [Figure 8] FIG. 13 is a diagram showing an example of a finding sentence candidate to be searched. [Figure 9] FIG. 13 is a diagram showing an example of a screen displayed on a display. [Figure 10] FIG. 13 is a diagram showing an example of a screen displayed on a display. [Figure 11] 11 is a flowchart illustrating an example of information processing. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0030] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0031] First, the configuration of an information processing system 1 to which an information processing device 10 of the present disclosure is applied will be described with reference to Fig. 1. Fig. 1 is a diagram showing a schematic configuration of the information processing system 1. The information processing system 1 photographs an examination target part of a subject and stores the photographed medical images based on an examination order from a doctor of a medical department using a known ordering system. It also enables an image interpretation doctor to interpret the medical images and create an image interpretation report, and enables a doctor of the requesting medical department to view the image interpretation report.

[0032] 1, the information processing system 1 includes an imaging device 2, an interpretation WS (WorkStation) 3 which is an interpretation terminal, a medical treatment WS 4, an image server 5, an image DB (DataBase) 6, a report server 7, and a report DB 8. The imaging device 2, the interpretation WS 3, the medical treatment WS 4, the image server 5, the image DB 6, the report server 7, and the report DB 8 are connected to each other via a wired or wireless network 9 in a state in which they can communicate with each other.

[0033] Each device is a computer in which an application program is installed to cause the device to function as a component of the information processing system 1. The application program may be recorded on a recording medium such as a DVD-ROM (Digital Versatile Disc Read Only Memory) or a CD-ROM (Compact Disc Read Only Memory) and distributed, and installed on the computer from the recording medium. Alternatively, the application program may be stored in a storage device or network storage of a server computer connected to the network 9 in an externally accessible state, and downloaded to the computer upon request and installed.

[0034] The imaging device 2 is a device (modality) that captures an image of a part of a subject to be diagnosed, thereby generating a medical image T representing the part to be diagnosed. Examples of the imaging device 2 include a plain X-ray device, a CT (Computed Tomography) device, an MRI (Magnetic Resonance Imaging) device, a PET (Positron Emission Tomography) device, an ultrasonic diagnostic device, an endoscope, and a fundus camera. The medical image generated by the imaging device 2 is transmitted to an image server 5 and stored in an image DB 6.

[0035] Fig. 2 is a diagram showing a schematic diagram of an example of a medical image acquired by the imaging device 2. The medical image T shown in Fig. 2 is, for example, a CT image consisting of a plurality of tomographic images T1 to Tm (m is 2 or more), each of which represents a cross-sectional plane from the head to the waist of a single subject (human body). The medical image T is an example of an image disclosed herein.

[0036] FIG. 3 is a diagram showing a schematic example of one of the tomographic images Tx among the multiple tomographic images T1 to Tm. The tomographic image Tx shown in FIG. 3 shows a tomographic plane including the lungs. Each of the tomographic images T1 to Tm may include a structure area SA showing various organs and organs of the human body (e.g., lungs and kidneys, etc.), and various organs and tissues constituting the organs (e.g., blood vessels, nerves, muscles, etc.). Each tomographic image may also include a lesion area AA such as a nodule, tumor, injury, defect, and inflammation. In the tomographic image Tx shown in FIG. 3, the lung area is the structure area SA, and the nodule area is the lesion area AA. Note that one tomographic image may include multiple structure areas SA and / or lesion areas AA. Hereinafter, at least one of the structure area SA included in the medical image and the lesion area AA included in the medical image is referred to as a "region of interest."

[0037] The image interpretation WS3 is a computer used by a medical professional such as a radiologist to interpret medical images and prepare image interpretation reports, and includes the information processing device 10 according to this embodiment. The image interpretation WS3 issues a request to view a medical image to the image server 5, performs various image processing on the medical image received from the image server 5, displays the medical image, and accepts input of text related to the medical image. The image interpretation WS3 also performs analysis processing on the medical image, supports the preparation of an image interpretation report based on the analysis result, requests the report server 7 to register and view the image interpretation report, and displays the image interpretation report received from the report server 7. These processes are performed by the image interpretation WS3 executing software programs for each process.

[0038] The medical treatment WS4 is a computer used by medical personnel such as doctors in a medical department to observe medical images in detail, view interpretation reports, and create electronic medical records, and is configured to include a processing device, a display device such as a display, and an input device such as a keyboard and a mouse. The medical treatment WS4 issues requests to the image server 5 to view medical images, displays medical images received from the image server 5, issues requests to the report server 7 to view interpretation reports, and displays interpretation reports received from the report server 7. These processes are performed by the medical treatment WS4 executing software programs for each process.

[0039] The image server 5 is a general-purpose computer installed with a software program that provides the functions of a database management system (DBMS). The image server 5 is connected to an image DB 6. The connection between the image server 5 and the image DB 6 is not particularly limited, and may be a connection via a data bus or a connection via a network such as a NAS (Network Attached Storage) or a SAN (Storage Area Network).

[0040] The image DB 6 is realized by a storage medium such as a hard disk drive (HDD), a solid state drive (SSD), a flash memory, etc. In the image DB 6, medical images acquired by the imaging device 2 and associated information attached to the medical images are registered in association with each other.

[0041] The incidental information may include, for example, identification information such as an image ID (identification) for identifying a medical image, a tomographic ID assigned to each tomographic image included in the medical image, a subject ID for identifying the subject, and an examination ID for identifying an examination. The incidental information may also include, for example, information related to imaging, such as an imaging method, imaging conditions, imaging purpose, and imaging date and time, related to imaging of a medical image. The "imaging method" and "imaging conditions" are, for example, the type of imaging device 2, the imaging site, imaging protocol, imaging sequence, imaging technique, whether or not a contrast agent is used, and slice thickness in tomography. The incidental information may also include information related to the subject, such as the subject's name, date of birth, age, and sex.

[0042] Furthermore, when the image server 5 receives a registration request for a medical image from the imaging device 2, it converts the medical image into a format for a database and registers it in the image DB 6. Furthermore, when the image server 5 receives a viewing request from the image interpretation WS 3 and the medical care WS 4, it searches for medical images registered in the image DB 6 and transmits the searched medical image to the image interpretation WS 3 and the medical care WS 4 that have sent the viewing request.

[0043] The report server 7 is a general-purpose computer installed with a software program that provides the functions of a database management system. The report server 7 is connected to a report DB 8. The connection between the report server 7 and the report DB 8 is not particularly limited, and may be a connection via a data bus or a connection via a network such as a NAS or a SAN.

[0044] The report DB 8 is realized by a storage medium such as a HDD, an SSD, a flash memory, etc. The report DB 8 registers the image interpretation reports created in the image interpretation WS 3 (details will be described later).

[0045] Furthermore, when the report server 7 receives a request to register an interpretation report from the image interpretation WS3, it converts the interpretation report into a format for a database and registers it in the report DB 8. Furthermore, when the report server 7 receives a request to view an interpretation report from the image interpretation WS3 and the medical care WS4, it searches for the interpretation report registered in the report DB8 and transmits the searched interpretation report to the image interpretation WS3 and the medical care WS4 that have made the request to view the interpretation report.

[0046] The network 9 is, for example, a network such as a LAN (Local Area Network) or a WAN (Wide Area Network). The imaging device 2, the interpretation WS3, the medical care WS4, the image server 5, the image DB6, the report server 7, and the report DB8 included in the information processing system 1 may be located in the same medical institution, or in different medical institutions. The number of each device of the imaging device 2, the interpretation WS3, the medical care WS4, the image server 5, the image DB6, the report server 7, and the report DB8 is not limited to the number shown in FIG. 1, and each device may be composed of a plurality of devices having similar functions.

[0047] Incidentally, when the interpretation WS3 interprets a medical image and creates an interpretation report, past interpretation reports (findings) registered in the report DB8 may be referred to for reference. In this case, a search query according to the medical image to be interpreted is used to search for past findings describing findings and / or diagnoses that are identical or similar to those of the medical image to be interpreted. For example, if the medical image to be interpreted contains a kidney nodule, a search is performed using "kidney" and "nodule" as the search query, and findings containing "kidney" and "nodule" are presented as the search results.

[0048] When searching for a finding sentence, it is desirable to use a search query that is as concise as possible so that the desired finding sentence can be quickly reached. The reason for using a concise search query is, for example, to reduce the time and effort required for the user to input the search query. In addition, for example, when a computer generates a search query by image analysis, the concise search query can be used to shorten the processing time for generating the search query and to eliminate the need to develop an advanced image analysis function.

[0049] On the other hand, the more concise the search query, the greater the number and variety of findings presented as search results, making it difficult for the user to quickly find what they want. Therefore, the information processing device 10 according to the present embodiment provides a function for searching for appropriate findings with a concise search query so that the user can quickly arrive at the desired finding even with a concise search query. The information processing device 10 will be described below. As described above, the information processing device 10 is included in the image interpretation WS3.

[0050] First, an example of a hardware configuration of the information processing device 10 according to the present embodiment will be described with reference to Fig. 4. As shown in Fig. 4, the information processing device 10 includes a CPU (Central Processing Unit) 21, a non-volatile storage unit 22, and a memory 23 as a temporary storage area. The information processing device 10 also includes a display 24 such as a liquid crystal display, an input unit 25 such as a keyboard and a mouse, and a network I / F (Interface) 26. The network I / F 26 is connected to a network 9 and performs wired and / or wireless communication. The CPU 21, the storage unit 22, the memory 23, the display 24, the input unit 25, and the network I / F 26 are connected to each other via a bus 28 such as a system bus and a control bus so that various information can be exchanged between them.

[0051] The storage unit 22 is realized by a storage medium such as an HDD, an SSD, or a flash memory. An information processing program 27 for the information processing device 10 is stored in the storage unit 22. The CPU 21 reads the information processing program 27 from the storage unit 22, expands it in the memory 23, and executes the expanded information processing program 27. The CPU 21 is an example of a processor of the present disclosure. An importance table 29 is also stored in the storage unit 22 (described in detail later). As the information processing device 10, for example, a personal computer, a server computer, a smartphone, a tablet terminal, a wearable terminal, or the like can be appropriately applied.

[0052] Next, an example of a functional configuration of the information processing device 10 according to the present embodiment will be described with reference to Fig. 5 to Fig. 9. As shown in Fig. 5, the information processing device 10 includes a registration unit 30, an acquisition unit 32, a search unit 34, an evaluation unit 36, and a display control unit 38. The CPU 21 executes the information processing program 27, causing the CPU 21 to function as each of the functional units of the registration unit 30, the acquisition unit 32, the search unit 34, the evaluation unit 36, and the display control unit 38.

[0053] (Structuring of radiology reports) First, a structuring process of an image reading report will be described as a pre-processing executed by the information processing device 10 prior to a search process of a finding statement. As described above, an image reading report that has already been created is registered in the report DB8. FIG. 6 shows an example of information included in an image reading report registered in the report DB8. As shown in FIG. 6, a plurality of finding statements and diagnosis information and finding information included in each finding statement are registered in the report DB8 in association with each other.

[0054] The finding sentences are registered in the report DB 8 by the report server 7 when each image interpretation report is created. The registration unit 30 specifies the diagnosis information and the finding information contained in each of the multiple finding sentences (hereinafter, referred to as a group of findings) registered in the report DB 8, and assigns them to the finding sentences (so-called structuring).

[0055] The diagnostic information is, for example, a presumed disease name diagnosed based on a medical image. The presumed disease name is an evaluation result presumed based on a lesion included in a medical image, and includes, for example, disease names such as "cancer" and "inflammation," as well as evaluation results regarding the disease name and characteristics such as "negative / positive," "benign / malignant," and "mild / severe." In FIG. 6, "angiomyolipoma," "renal cancer," "tumor," and "cyst" are exemplified as diagnostic information.

[0056] Furthermore, for example, one finding may include multiple suspected disease names, such as "renal cell carcinoma is suspected, but angiomyolipoma with a small amount of fat may also be present." In this case, the registration unit 30 may select one suspected disease name as the diagnosis information, and assign other suspected disease names, etc. that were not selected to the finding as the finding information.

[0057] The finding information is information indicating at least one of various findings such as the type (name), characteristics, position, measurement value and number of the region of interest, a phrase expressing a change in the region of interest, and a type of diagnostic information other than the diagnostic information to be paired, etc. As described above, the type of diagnostic information other than the diagnostic information to be paired is a presumed disease name that was not selected as the diagnostic information.

[0058] Examples of types (names) of a region of interest include names of structures such as "lung" and "liver" and names of lesions such as "nodule" and "ground-glass opacity". The properties of a region of interest mainly refer to the characteristics of the lesion. For example, in the case of a nodule, examples include absorption values ​​such as "solid", "low absorption" and "high absorption", margin shapes such as "clear / unclear", "smooth / irregular", "spicule", "lobulated" and "serrated", and findings indicating the overall shape such as "near-circular" and "irregular". Other examples include the relationship with surrounding tissues such as "protrusion", and findings regarding the presence or absence of contrast and washout.

[0059] The position of a region of interest means an anatomical position, a position in a medical image, and a relative positional relationship with other regions of interest such as "inside", "edge", and "surroundings". The anatomical position may be expressed by organ names such as "lung" and "kidney", or may be expressed by subdividing the kidney into "left kidney" and "superior segment".

[0060] The measurement value of the region of interest is a value that can be quantitatively measured from a medical image, and is, for example, at least one of the size and signal value of the region of interest. The size is expressed, for example, by the major axis, minor axis, area, and volume of the region of interest. The signal value is expressed, for example, by the pixel value of the region of interest and the CT value in units of HU. The finding information indicating the measurement value may be divided into predetermined classes (i.e., quantized), such as "0 mm or more and less than 5 mm", "5 mm or more and less than 10 mm", and "10 mm or more and less than 15 mm". In this case, for example, if the finding statement contains a statement of "12 mm", the finding information of "10 mm or more and less than 15 mm" is specified. The finding information indicating the measurement value may simply be information indicating whether or not there is a statement in the finding statement. This is because there may be a large variation in the measurement value or the statement may be omitted.

[0061] The number of regions of interest may be expressed as a specific number such as one or two, or may be expressed in relative terms such as "single / multiple" and "few / many." The phrases expressing changes in the regions of interest are phrases expressing changes over time in the characteristics, location, measurement values, number, etc., of the regions of interest when they are observed over time, and examples of such phrases include "appearance / disappearance," "increase / reduction," "worsening / improvement," and "metastasis."

[0062] Specifically, the registration unit 30 extracts named entities (words) from the finding sentences registered in the report DB 8, and identifies the diagnosis information or finding information corresponding to the extracted named entities. As a method for extracting named entities from the finding sentences, for example, a known named entity extraction method using a natural language processing model such as BERT (Bidirectional Encoder Representations from Transformers) can be appropriately applied.

[0063] In addition, the group of findings may contain different words with the same meaning (synonyms), such as "angiomyolipoma" and "AML" (Angiomyolipoma). In order to deal with variations in spelling due to such synonyms, when the group of findings contains synonyms, it is preferable that the registration unit 30 assigns the same diagnosis information or finding information to each of the finding sentences containing synonyms (so-called normalization).

[0064] Specifically, a dictionary that defines a correspondence between a named entity that may be included in a finding sentence and diagnostic information or finding information, in which synonymous named entities are associated with the same diagnostic information or finding information, may be stored in advance in the storage unit 22. For example, in the dictionary, the synonymous words "angiomyolipoma" and "AML" may each be associated with the same diagnostic information, "angiomyolipoma." The registration unit 30 may extract named entities from the finding sentence registered in the report DB8 and identify the diagnostic information or finding information included in the finding sentence by referring to the dictionary.

[0065] In addition, it is preferable that the registration unit 30 also specifies the factuality of the specified diagnostic information or finding information. "Factuality" is information indicating whether a finding is observed or not, and the degree of certainty, etc. This is because the radiology report may include not only findings that are clearly observed in medical images, but also findings that are not observed in medical images, and findings that are suspected but have a low degree of certainty. For example, since the presence or absence and the degree of fat components are used to differentiate between AML and renal cell carcinoma (RCC), the radiology report may include the statement that "fat components are not observed."

[0066] Furthermore, the finding information may be other diagnostic information or may modify the finding information. In this case, it is preferable that the registration unit 30 also identifies the modifying relationship between the finding information and the diagnostic information, or between the finding information itself. For example, "calcification", which is an example of the characteristics of a pulmonary nodule, may be described in detail, such as "microcalcification is observed in the center". In this case, the registration unit 30 may identify the finding information "center" and "micro" as other finding information that modifies the finding information "calcification". Examples of the finding information that modifies "calcification" include "micro", "coarse", "scattered", "center", "ring-shaped", and "complete".

[0067] For example, in the case of "renal cell carcinoma," which is an example of diagnostic information based on kidney nodules, the histological types such as "clear cell," "papillary," "chromophobe," and "multilocular cystic" may also be described in the finding text. The registration unit 30 may specify finding information indicating such histological types as other finding information that modifies the finding information "renal cell carcinoma."

[0068] Furthermore, when one finding statement includes diagnosis information or finding information related to a plurality of regions of interest (lesions), it is preferable that the registration unit 30 specifies the diagnosis information or finding information for each region of interest.

[0069] In addition, the finding statement may not include diagnostic information. In this case, the registration unit 30 may assign the diagnostic information of "undiagnosed" to the finding statement. For example, when a lesion (region of interest) included in a medical image is small and the findings can be interpreted but are below the diagnostic standard (i.e., are not important) that is predetermined in the guidelines, only the finding information may be recorded and not recorded as diagnostic information. In addition, when the region of interest is obviously benign, only the finding information may be recorded and not recorded as diagnostic information. In addition, for example, the creator of the finding statement may forget to write it, and the registration unit 30 may not be able to identify it due to the processing accuracy of the registration unit 30.

[0070] (Derivation of Importance) Next, a process of deriving importance using structured data registered in the report DB 8 will be described as a pre-processing executed by the information processing device 10 prior to the search process of the finding sentences. By the structuring process of the radiology report described above, a plurality of finding sentences and the diagnosis information and finding information included in each finding sentence are registered in the report DB 8 in association with each other.

[0071] A set of findings may include the same diagnosis but different findings, or the same findings but different diagnoses. For example, when a nodule is seen in a medical image of the kidney, if it has a fatty component, it is typically diagnosed as AML, and if it does not have a fatty component, it is typically diagnosed as RCC, but there are also cases where a nodule with a small fatty component is diagnosed as AML.

[0072] For example, among the group of findings, some contain findings that are important for diagnosis, some are comprehensively described including findings that are not important, and some even omit important findings. For example, there is a finding statement that simply says, "Nodules suspected of AML are observed," while there is also a finding statement that includes information on findings that are the basis for diagnosis, such as, "Nodules suspected of AML are observed, mainly consisting of fat concentration."

[0073] It is considered appropriate that the findings presented as search results include important findings without excess or deficiency. Therefore, the registration unit 30 derives the importance for each combination of diagnosis information and finding information as an index used for evaluating the findings.

[0074] 7 shows an example of the importance table 29 in which the importance is determined for each combination of diagnostic information and finding information. The importance table 29 also shows the frequency of diagnostic information included in the finding sentence group, and the frequency of combinations of diagnostic information and finding information included in the finding sentence group. The combinations are also classified according to the factuality of the finding information.

[0075] From the example in Figure 7, it can be seen that the group of findings contains 1000 finding sentences that contain "angiomyolipoma" and 517 finding sentences that contain "renal cell carcinoma". It can also be seen that the group of findings contains 719 finding sentences that contain the combination of "angiomyolipoma" and "fat concentration" as "present". It can also be seen that the group of findings contains 25 finding sentences that contain the combination of "angiomyolipoma" and "fat concentration" as "absent". It can also be seen that the group of findings contains 102 finding sentences that contain the combination of "renal cell carcinoma" and "fat concentration" as "absent".

[0076] Specifically, the registration unit 30 may derive the importance based on a value according to the frequency with which a combination of diagnostic information and finding information is included in a group of findings. The more frequently a combination of diagnostic information and finding information is included in a group of findings, the more typical the combination is, and the more likely it is that the user performing the search will desire it.

[0077] For example, the registration unit 30 may derive the importance for each combination of diagnostic information d and finding information t based on the following formula (1). f(d) is the frequency of diagnostic information d included in the group of findings, and f(t, d) is the frequency of the combination of diagnostic information d and finding information t included in the group of findings. According to formula (1), it can be said that the more frequently the finding information t is described in a finding text in combination with certain diagnostic information d, the higher the importance of the finding information t.

number

[0078] Furthermore, the registration unit 30 may derive the importance based on a value according to the degree of uniqueness of the finding information included in a combination of certain diagnostic information and finding information, which is not included in combinations with other diagnostic information. The degree of uniqueness indicates whether a certain finding information is rare and is used in combination with only some diagnostic information, or is universal and is used in combination with many diagnostic information. The more unique the finding information is, the more valuable it is as a basis for diagnosis, and the more likely it is that the user performing the search will desire it.

[0079] For example, the registration unit 30 may derive the importance level for each combination of diagnostic information d and finding information t based on the following formula (2): N is the number of types of all diagnostic information D included in the finding sentence group, and n t is the number of types of diagnostic information included in the group of findings in combination with finding information t among all diagnostic information D. According to formula (2), the fewer the number of types of diagnostic information described in combination with a certain finding information t (i.e., the higher the degree of specificity), the higher the importance is derived.

number

[0080] The registration unit 30 may also derive the importance based on a value corresponding to the frequency with which a combination of diagnostic information and finding information is included in a group of findings, and the degree of uniqueness of the finding information included in the combination, which is not included in combinations with other diagnostic information. For example, the registration unit 30 may derive the importance based on the following formula (3) that combines two indexes expressed by formulas (1) and (2). According to formula (3), when both the frequency and the degree of uniqueness are high, a high importance is derived.

number

[0081] In importance table 29 in Figure 7, the corresponding value of equation (1) for the combination of "angiomyolipoma" and "fat concentration" being "present" is derived as 0.719, since f(t, d) is 719 and f(d) is 1000.

[0082] In addition, in the importance table 29 of FIG. 7, the number of types N of all the diagnostic information D is 100, and the diagnostic information that can be combined with "fat concentration" as "present" is only one type, "angiomyolipoma" (i.e., n t In this case, the corresponding value of formula (2) for the combination of "angiomyolipoma" and "fat concentration" being "present" is derived as log(100 / (1+1))+1=2.70.

[0083] In the above case, the corresponding value of formula (3) is derived as 0.719×2.70=1.94. As an example, in FIG 7, the corresponding value of formula (3) is multiplied by 10 and shown as the importance.

[0084] The registration unit 30 may regard a combination of diagnostic information and finding information whose derived importance is equal to or lower than a predetermined threshold as noise and exclude it from the importance table 29. The registration unit 30 may also regard a combination of diagnostic information and finding information whose derived importance is relatively low (e.g., in the bottom 30%) as noise and exclude it from the importance table 29.

[0085] (Search for findings) Next, a process of searching for a finding sentence executed by the information processing device 10 will be described.

[0086] The acquisition unit 32 acquires a search query. For example, the acquisition unit 32 may accept a search query input by a user via the input unit 25. For example, the acquisition unit 32 may acquire a medical image to be interpreted from the image server 5, and generate at least one of the finding information and the diagnosis information for the medical image as a search query based on the medical image. The search query input by the user and the search query generated based on the medical image may be used in combination.

[0087] An example of a method for generating a search query based on a medical image will be described. For example, the acquisition unit 32 extracts at least one region of interest (e.g., a nodule region) included in the acquired medical image. As a method for extracting the region of interest, a method using a known CAD (Computer Aided Detection / Diagnosis) technology and an AI (Artificial Intelligence) technology can be appropriately applied. For example, the acquisition unit 32 may extract the region of interest from the medical image using a learning model such as a CNN (Convolutional Neural Network) that is trained to input a medical image and extract and output the region of interest included in the medical image.

[0088] The acquiring unit 32 then generates finding information and / or diagnosis information of the extracted region of interest. For example, the acquiring unit 32 may input the region of interest extracted from the medical image and generate the finding information and / or diagnosis information of the region of interest using a learning model such as CNN that has been trained in advance to output the finding information and / or diagnosis information of the region of interest. The acquiring unit 32 may use at least one of the finding information and / or diagnosis information thus generated as a search query.

[0089] The search unit 34 searches for a plurality of finding sentence candidates related to the search query acquired by the acquisition unit 32 from a group of finding sentences including a plurality of finding sentences registered in the report DB 8. As an example, Fig. 8 shows a search result when "nodule" is used as a search query.

[0090] The evaluation unit 36 ​​evaluates each of the finding sentence candidates searched by the search unit 34 based on the importance level predetermined for each combination of diagnostic information and finding information included in the finding sentence candidate. As described above, the importance level is predetermined for each combination of diagnostic information and finding information included in the finding sentence group by the registration unit 30 and stored in the storage unit 22 as the importance level table 29. In the example of FIG. 8, the evaluation value derived by the evaluation unit 36 ​​is shown in the "Evaluation" column.

[0091] Specifically, the evaluation unit 36 ​​refers to the importance table 29 and obtains the importance corresponding to the combination of the diagnosis information and the finding information included in the finding candidate. For example, the finding candidate No. 1 in Fig. 8 includes a combination of "angiomyolipoma" and "fat concentration" being "present". In this case, the evaluation unit 36 ​​obtains the importance of "19.4" corresponding to the combination of "angiomyolipoma" and "fat concentration" being "present" from the importance table 29 in Fig. 7, and assigns it as the evaluation value of the finding candidate No. 1 in Fig. 8.

[0092] Furthermore, when the finding sentence candidate includes a combination of multiple different diagnosis information and finding information, the evaluation unit 36 ​​may perform evaluation based on the importance of each combination. For example, the finding sentence candidate No. 2 in Fig. 8 includes a first combination of "angiomyolipoma" and "fat concentration" being "present" and a second combination of "angiomyolipoma" and "heterogeneity" being "present". In this case, the evaluation unit 36 ​​may obtain the importance corresponding to each of the first and second combinations from the importance table 29 in Fig. 7, and assign a representative value such as the sum, average, weighted average, or multiplication value thereof as the evaluation value of the finding sentence candidate No. 2 in Fig. 8.

[0093] Furthermore, when a combination of diagnostic information and finding information for which the importance is not predefined is included in a finding candidate, the evaluation unit 36 ​​may correct the evaluation of the finding candidate to be lowered. A combination of diagnostic information and finding information for which the importance is not predefined is a combination that is not included in a group of findings or occurs at a low frequency and is therefore not registered in the importance table 29. A finding candidate including such a combination is considered to have low versatility, and therefore it is preferable to lower the evaluation. For example, when a finding candidate includes a combination of diagnostic information and finding information that is not registered in the importance table 29, the evaluation unit 36 ​​may subtract a predefined value (e.g., 1) from the evaluation value.

[0094] The display control unit 38 presents at least one finding sentence candidate based on the result of the evaluation by the evaluation unit 36. For example, the display control unit 38 may rearrange and present the multiple finding sentence candidates in order of the evaluation value (i.e., importance) evaluated by the evaluation unit 36 ​​to be high.

[0095] The display control unit 38 may also divide the multiple finding sentence candidates into multiple groups based on the type of diagnostic information contained in the finding sentence candidates, and present at least one finding sentence candidate for each group. FIG. 9 shows an example of a screen D1 for presenting the finding sentence candidates, which is displayed on the display 24 by the display control unit 38. A text box 90 for the user to input a search query and a slider bar 92 for specifying the major axis and minor axis of the region of interest are displayed at the top of the screen D1. A multiple finding sentence candidates searched by the search unit 34 based on the input search query and evaluated by the evaluation unit 36 ​​are displayed at the bottom of the screen D1.

[0096] In the example of Fig. 9, one candidate finding sentence is presented for each of the three groups, "angiomyolipoma," "renal cancer," and "tumor." In this way, by presenting multiple candidate finding sentences for each group, the user can check candidate finding sentences that include a variety of diagnostic information.

[0097] Specifically, the display control unit 38 may present, for each group, one finding sentence candidate evaluated as having the highest importance by the evaluation unit 36. Furthermore, for example, the display control unit 38 may present, for each group, a plurality of finding sentence candidates sorted in order of the importance evaluated as having the highest importance.

[0098] Furthermore, when presenting at least one finding sentence candidate for each group, the display control unit 38 may rearrange the groups corresponding to each diagnostic information in descending order of frequency of diagnostic information being included in the finding sentence group. That is, while the groups are arranged in the order of "angiomyolipoma", "renal cancer", and "tumor" from the top in the example of FIG. 9, this order may be rearranged according to frequency of diagnostic information being included in the finding sentence group. The frequency of diagnostic information being included in the finding sentence group is, for example, registered in advance in the importance table 29 (see FIG. 7). The higher the frequency of diagnostic information being included in the finding sentence group, the more commonly seen the case is, and it is considered that the more likely it is that the user performing the search will desire it.

[0099] The display control unit 38 may further divide the finding sentence candidates included in the group into subgroups based on a predetermined criterion, and present at least one finding sentence candidate for each subgroup. FIG. 10 shows an example of a screen D2 for presenting finding sentence candidates, which is transitioned to and displayed on the display 24 by the display control unit 38 when the "Show more" button 94 for "angiomyolipoma" is selected on the screen D1. A plurality of finding sentence candidates for the selected "angiomyolipoma" are displayed on the screen D2. Furthermore, the evaluation value (importance) derived by the evaluation unit 36 ​​is displayed as a "score" on the screen D2.

[0100] In the example of Fig. 10, a finding candidate is presented for each of three groups, namely, "angiomyolipoma," "angiomyolipoma and one other diagnosis," and "angiomyolipoma and two other diagnoses." In this way, the display control unit 38 may divide the finding candidate into subgroups using the number of types of diagnostic information included in the finding candidate as a predetermined criterion. In general, the more diagnostic information included in a finding, the more ambiguous the finding is, so it is preferable to present subgroups with fewer types of diagnostic information at the top.

[0101] The criteria used for subgrouping are not limited to the number of types of diagnostic information. For example, the display control unit 38 may divide a plurality of finding candidates into subgroups based on the factuality of the diagnostic information contained in the finding candidates. For example, the finding candidates may be presented for each subgroup according to the factuality of "angiomyolipoma," such as "highly likely," "suspected," "possible," "cannot be denied," "cannot be determined," and "negative."

[0102] Furthermore, when there are multiple finding sentence candidates that include the same combination and have the same evaluation result, the display control unit 38 may select and present any one of the finding sentence candidates. For example, when there are multiple finding sentence candidates that include the same combination and have the same evaluation result, the display control unit 38 may select and present the one with the smallest amount of text among the finding sentence candidates. It is considered preferable that the finding sentence candidates presented as the search result include a variety of contents. Therefore, the display control unit 38 may prevent multiple finding sentence candidates with the same content from being presented.

[0103] Next, the operation of the information processing device 10 according to the embodiment will be described with reference to Fig. 11. In the information processing device 10, the CPU 21 executes the information processing program 27, thereby executing the information processing shown in Fig. 11. The information processing is executed, for example, when a command to start execution is given by a user via the input unit 25. It is assumed that the structuring process of the image interpretation report and the derivation process of importance described above have been executed in advance.

[0104] In step S10, the acquisition unit 32 acquires a search query. In step S12, the search unit 34 searches a group of findings including a plurality of findings registered in the report DB 8 for a plurality of finding sentence candidates related to the search query acquired in step S10.

[0105] In step S14, the evaluation unit 36 ​​evaluates each of the finding sentence candidates searched for in step S12 based on a predetermined importance (e.g., the importance registered in the importance table 29) for each combination of diagnosis information and finding information included in the finding sentence candidate. In step S16, the display control unit 38 controls the display 24 to display a screen presenting at least one finding sentence candidate based on the result of the evaluation in step S14, and ends this information processing.

[0106] As described above, the information processing device 10 according to one embodiment of the present disclosure includes at least one processor, which searches for a plurality of candidate finding sentences related to a search query from a group of findings including a plurality of finding sentences, evaluates each of the candidate finding sentences based on a predetermined importance for each combination of diagnostic information and finding information included in the candidate finding sentences, and presents at least one candidate finding sentence based on the evaluation result.

[0107] That is, according to the information processing device 10 of the present embodiment, since it is possible to preferentially present finding sentence candidates with high importance, it is possible to search for appropriate finding sentences with a concise search query. Therefore, it is possible to quickly present finding sentences by reducing the effort required for the user to input a search query. In addition, even when a computer generates a search query using CAD technology, it is only necessary to generate a concise search query, so that it is possible to shorten the processing time for generating the search query and to eliminate the need for the development of an advanced image analysis function.

[0108] In addition, in each of the above embodiments, the description has been given assuming the interpretation of medical images, but the present disclosure is not limited thereto. The information processing device 10 of the present disclosure is applicable to various images obtained by photographing a subject and including a region of interest. For example, the information processing device 10 may be applied to images obtained from equipment, buildings, pipes, welds, etc. as subjects in non-destructive inspections such as radiographic inspections and ultrasonic flaw detection inspections. In this case, the region of interest may indicate, for example, cracks, flaws, bubbles, foreign objects, etc.

[0109] In each of the above embodiments, the following various processors can be used as the hardware structure of the processing units that execute various processes, such as the registration unit 30, the acquisition unit 32, the search unit 34, the evaluation unit 36, and the display control unit 38. As described above, the above various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as a programmable logic device (PLD), which is a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), a dedicated electric circuit, which is a processor having a circuit configuration designed specifically for executing specific processes, such as an ASIC (Application Specific Integrated Circuit), etc.

[0110] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.

[0111] As an example of configuring multiple processing units with one processor, first, there is a form in which one processor is configured with a combination of one or more CPUs and software, as typified by computers such as client and server, and this processor functions as multiple processing units. Second, there is a form in which a processor is used that realizes the functions of the entire system including multiple processing units with one IC (Integrated Circuit) chip, as typified by System on Chip (SoC), etc. In this way, the various processing units are configured using one or more of the above various processors as a hardware structure.

[0112] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0113] In the above embodiment, the information processing program 27 is pre-stored (installed) in the storage unit 22, but the present invention is not limited to this. The information processing program 27 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The information processing program 27 may be downloaded from an external device via a network. Furthermore, the technology disclosed herein extends to a storage medium that non-temporarily stores an information processing program in addition to the information processing program.

[0114] The technology of the present disclosure can also be appropriately combined with the above-mentioned embodiment examples and examples. The above-mentioned description and illustrated contents are detailed descriptions of the parts related to the technology of the present disclosure, and are merely one example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the description and illustrated contents shown above, within the scope of the gist of the technology of the present disclosure.

[0115] The following supplementary notes are further disclosed regarding the above embodiment. [Appendix 1] at least one processor; The processor, Searching for multiple candidate finding sentences related to the search query from a group of finding sentences including multiple finding sentences; evaluating each of the candidate findings based on a predetermined importance for each combination of diagnosis information and finding information included in the candidate findings; presenting at least one of the candidate finding sentences based on a result of the evaluation; Information processing device. [Appendix 2] The processor, The plurality of candidate finding sentences are sorted and presented in order of the importance. 2. An information processing device according to claim 1. [Appendix 3] The processor, Dividing the plurality of finding sentence candidates into a plurality of groups based on the types of the diagnostic information contained in the finding sentence candidates; Presenting at least one of the candidate finding sentences for each of the groups. 3. An information processing device according to claim 1 or 2. [Appendix 4] The processor, For each group, the plurality of finding sentence candidates are sorted in order of the importance evaluated to be high and presented. 4. The information processing device according to claim 3. [Appendix 5] The processor, Presenting one of the candidate finding sentences that is evaluated as having the highest importance for each group. 4. The information processing device according to claim 3. [Appendix 6] The processor, The observation sentence candidates included in the group are further divided into subgroups based on a predetermined criterion; Presenting at least one of the candidate finding sentences for each of the subgroups. An information processing device according to any one of Supplementary Note 3 to Supplementary Note 5. [Appendix 7] The predetermined criterion is at least one of the number of types of the diagnostic information included in the candidate finding sentence and the factuality of the diagnostic information included in the candidate finding sentence. 7. The information processing device according to claim 6. [Appendix 8] The processor, The groups corresponding to the respective pieces of diagnostic information are rearranged in order of frequency of the diagnostic information being included in the group of observation sentences. 8. An information processing device according to any one of claims 3 to 7. [Appendix 9] The importance level is a value according to the frequency with which the combination is included in the group of observation sentences. An information processing device according to any one of Supplementary Note 1 to Supplementary Note 8. [Appendix 10] The importance is a value according to the degree of uniqueness of the finding information included in the combination, which is not included in combinations with other diagnostic information. An information processing device according to any one of Supplementary Note 1 to Supplementary Note 8. [Appendix 11] The importance is a value according to the frequency with which the combination is included in the group of findings and the degree of uniqueness of the finding information included in the combination that is not included in combinations with other diagnostic information. An information processing device according to any one of Supplementary Note 1 to Supplementary Note 8. [Appendix 12] The processor, When the finding sentence candidate includes a plurality of different combinations, the evaluation is performed based on the importance of each of the combinations. An information processing device according to any one of Supplementary Note 1 to Supplementary Note 11. [Appendix 13] the importance level is determined in advance for each of the combinations included in the group of observation sentences; The processor, When the candidate finding sentence includes the combination for which the importance is not previously determined, the evaluation of the candidate finding sentence is lowered. 13. An information processing device according to any one of claims 1 to 12. [Appendix 14] The processor, When there are a plurality of the finding sentence candidates that include the same combination and have the same evaluation result, one of the finding sentence candidates is selected and presented. 14. An information processing device according to any one of claims 1 to 13. [Appendix 15] The processor, When there are a plurality of the finding sentence candidates that include the same combination and have the same evaluation result, the finding sentence candidate that has the smallest amount of text is selected and presented. 15. The information processing device according to claim 14. [Appendix 16] The processor, Accepting input of the search query by a user 16. An information processing device according to any one of claims 1 to 15. [Appendix 17] The processor, Acquire an image, generating at least one of the finding information and the diagnosis information for the image as the search query based on the image; 17. An information processing device according to any one of claims 1 to 16. [Appendix 18] The finding information indicates at least one of the type, characteristics, position, measurement value, and number of the region of interest, a phrase indicating a change in the region of interest, and a type of diagnosis information other than the diagnosis information to be paired. 18. An information processing device according to any one of claims 1 to 17. [Appendix 19] Searching for multiple candidate finding sentences related to the search query from a group of finding sentences including multiple finding sentences; evaluating each of the candidate findings based on a predetermined importance for each combination of diagnosis information and finding information included in the candidate findings; presenting at least one of the candidate finding sentences based on a result of the evaluation; An information processing method in which processing is performed by a computer. [Appendix 20] Searching for multiple candidate finding sentences related to the search query from a group of finding sentences including multiple finding sentences; evaluating each of the candidate findings based on a predetermined importance for each combination of diagnosis information and finding information included in the candidate findings; presenting at least one of the candidate finding sentences based on a result of the evaluation; An information processing program that enables a computer to execute processing. [Explanation of symbols]

[0116] 1. Information Processing Systems 2. Imaging Device 3. Image Reading Workshop 4. Clinical Workshop 5 Image Server 6. Image Database 7 Report Server 8 Report DB 9 Network 10. Information processing device 21 CPU 22 Memory section 23 Memory 24 Display 25 Input section 26 Network Interface 27 Information Processing Programs 28 Bus 29 Importance Table 30 Registration Department 32 Acquisition Department 34 Search Section 36 Evaluation Section 38 Display control section 90 Text Box 92 Slider Bar 94 Buttons AA Lesion Area D1~D2 screen SA Structure Area T Medical Imaging T1~Tm, Tx Tomographic images

Claims

1. At least one processor; The processor, Searching for multiple candidate finding sentences related to the search query from a group of finding sentences including multiple finding sentences; evaluating each of the candidate findings based on a predetermined importance for each combination of diagnosis information and finding information included in the candidate findings; presenting at least one of the candidate finding sentences based on a result of the evaluation; Information processing device.

2. The processor, The plurality of candidate finding sentences are sorted and presented in order of the importance. The information processing device according to claim 1 .

3. The processor, Dividing the plurality of finding sentence candidates into a plurality of groups based on the types of the diagnostic information contained in the finding sentence candidates; Presenting at least one of the candidate finding sentences for each of the groups. The information processing device according to claim 1 .

4. The processor, For each group, the plurality of finding sentence candidates are sorted in order of the importance evaluated to be high and presented. The information processing device according to claim 3 .

5. The processor, Presenting one of the finding sentence candidates that is evaluated as having the highest importance for each of the groups. The information processing device according to claim 3 .

6. The processor, The observation sentence candidates included in the group are further divided into subgroups based on a predetermined criterion; Presenting at least one of the candidate finding sentences for each of the subgroups. The information processing device according to claim 3 .

7. The predetermined criterion is at least one of the number of types of the diagnostic information included in the candidate finding sentence and the factuality of the diagnostic information included in the candidate finding sentence. The information processing device according to claim 6.

8. The processor, The groups corresponding to the respective pieces of diagnostic information are rearranged in order of frequency of the diagnostic information being included in the group of observation sentences. The information processing device according to claim 3 .

9. The importance level is a value according to the frequency with which the combination is included in the group of observation sentences. The information processing device according to claim 1 .

10. The importance is a value according to the degree of uniqueness of the finding information included in the combination, which is not included in combinations with other diagnostic information. The information processing device according to claim 1 .

11. The importance is a value according to the frequency with which the combination is included in the group of findings and the degree of uniqueness of the finding information included in the combination that is not included in combinations with other diagnostic information. The information processing device according to claim 1 .

12. The processor, When the finding sentence candidate includes a plurality of different combinations, the evaluation is performed based on the importance of each of the combinations. The information processing device according to claim 1 .

13. the importance level is determined in advance for each of the combinations included in the group of observation sentences; The processor, When the candidate finding sentence includes the combination for which the importance is not previously determined, the evaluation of the candidate finding sentence is lowered. The information processing device according to claim 1 .

14. The processor, When there are a plurality of the finding sentence candidates that include the same combination and have the same evaluation result, one of the finding sentence candidates is selected and presented. The information processing device according to claim 1 .

15. The processor, When there are a plurality of the finding sentence candidates that include the same combination and have the same evaluation result, the finding sentence candidate that has the smallest amount of text is selected and presented. The information processing device according to claim 14.

16. The processor, Accepting input of the search query by a user The information processing device according to claim 1 .

17. The processor, Acquire an image, generating at least one of the finding information and the diagnosis information for the image as the search query based on the image; The information processing device according to claim 1 .

18. The finding information indicates at least one of the type, characteristics, position, measurement value, and number of the region of interest, a phrase indicating a change in the region of interest, and a type of diagnosis information other than the diagnosis information to be paired. The information processing device according to claim 1 .

19. Searching for multiple candidate finding sentences related to the search query from a group of finding sentences including multiple finding sentences; evaluating each of the candidate findings based on a predetermined importance for each combination of diagnosis information and finding information included in the candidate findings; presenting at least one of the candidate finding sentences based on a result of the evaluation; An information processing method in which processing is performed by a computer.

20. Searching for multiple candidate finding sentences related to the search query from a group of finding sentences including multiple finding sentences; evaluating each of the candidate findings based on a predetermined importance for each combination of diagnosis information and finding information included in the candidate findings; presenting at least one of the candidate finding sentences based on a result of the evaluation; An information processing program that enables a computer to execute processing.

Images