Information processing device, information processing method, and information processing program

Abstract

To provide an information processing apparatus, an information processing method, and an information processing program capable of supporting the preparation of medical documents.SOLUTION: In an information processing system in which an imaging apparatus, an interpretation WS, a medical care WS, an image server, an image DB, a report server, and a report DB are connected to each other via a wired or wireless network in a communicable state, an information processing apparatus 10 included in the interpretation WS comprises at least one processor. The processor acquires a plurality of measurement values measured from the same subject at a plurality of different points in time, acquires a sentence corresponding to the measurement value, and selects at least some of the plurality of measurement values on the basis of a phrase related to the measurement value included in the sentence.SELECTED DRAWING: Figure 5

Description

Technical Field

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

Background Art

[0002] Conventionally, image diagnosis has been performed using medical images obtained by imaging devices such as CT (Computed Tomography) devices and MRI (Magnetic Resonance Imaging) devices. In addition, medical images are analyzed by CAD (Computer Aided Detection / Diagnosis) using a discriminator trained by deep learning or the like to detect and / or diagnose regions of interest including structures and lesions contained in the medical images. The medical images and the analysis results by CAD are transmitted to the terminals of medical staff such as radiologists who read the medical images. Medical staff such as radiologists use their own terminals to refer to the medical images and the analysis results, read the medical images, and create a reading report.

[0003] In addition, various methods for supporting the creation of reading reports have been proposed in order to reduce the burden of reading tasks. For example, Patent Document 1 discloses a technique for creating a reading report based on keywords input by a radiologist and the analysis results of medical images. In the technique described in Patent Document 1, a sentence for describing in the reading report is created using a recurrent neural network that has been trained to generate a sentence from the input characters.

[0004] In addition, for example, in regular medical examinations and follow-up observations after treatment, the same subject may be examined multiple times, and data at multiple time points may be accumulated for various measurement values such as the size of a lesion. Various methods have been proposed to make it possible to confirm the change over time of the measurement values using the accumulated multiple measurement values. For example, Patent Document 2 discloses presenting medical data in the form of plots and graphs, and highlighting the medical data in response to features received from the user. [Prior art documents] [Patent Documents]

[0005] [Patent Document 1] Japanese Patent Publication No. 2019-153250 [Patent Document 2] Japanese Patent Publication No. 2018-181340 [Overview of the project] [Problems that the invention aims to solve]

[0006] Incidentally, when creators and viewers of radiology reports actually check multiple measurement values, they sometimes focus on only a portion of the measurements for the same subject, rather than checking all of them. For example, if a measurement value was fine for a while initially but then deteriorated sharply in the most recent few measurements, they might focus on those most recent few measurements. Therefore, there is a need for a technology that allows for the selective checking of only a portion of multiple measurement values.

[0007] This disclosure provides an information processing device, an information processing method, and an information processing program that can assist in the creation of medical documents. [Means for solving the problem]

[0008] A first aspect of the present disclosure is an information processing apparatus comprising at least one processor, the processor acquires a plurality of measurements taken from the same subject at a plurality of different time points, acquires sentences corresponding to the measurements, and selects at least a portion of the plurality of measurements based on words related to the measurements contained in the sentences.

[0009] In the first embodiment described above, the processor may select at least some of a plurality of measurements based on phrases that describe the change in a measurement over time within a sentence.

[0010] In the first embodiment described above, the measured values ​​are accompanied by time information indicating the time of measurement, and the processor may use the measured values ​​and time information as variables to create a plot diagram that includes at least some of the selected measured values, and display the plot diagram on a display.

[0011] In the first embodiment described above, the processor may, upon receiving an instruction, create a plot diagram containing all of the acquired measurements and display the plot diagram on a display.

[0012] In the first embodiment described above, the measured values ​​are accompanied by time information indicating the time of measurement, and the processor may select the measured values ​​accompanied by time information indicating the time of measurement, which is determined based on a phrase related to the measured value.

[0013] In the first embodiment described above, the processor may select at least some of a plurality of measurements, depending on the number of measurements determined based on the words associated with the measurement.

[0014] In the first embodiment described above, the processor may select at least some of a plurality of measurements based on the words or phrases representing disease names contained in the sentence.

[0015] In the first embodiment described above, the processor may select at least some of a plurality of measurements based on words or phrases in the sentence that represent the purpose of the test.

[0016] In the first embodiment described above, the processor may decide whether or not to select a measurement value based on the result of comparing the measurement value contained in the statement with a predetermined threshold value.

[0017] In the first embodiment described above, the processor may decide whether or not to select at least two measured values ​​based on the result of comparing the difference between at least two measured values ​​contained in the statement with a predetermined threshold.

[0018] In the first aspect described above, the processor may select measurement values that satisfy predetermined conditions from among the plurality of measurement values.

[0019] In the first aspect described above, when the difference between at least two measurement values included in the plurality of measurement values satisfies a predetermined condition, the processor may select the at least two measurement values.

[0020] In the first aspect described above, time information indicating the measurement time is attached to the measurement values, and the processor may select at least a part of the plurality of measurement values that are consecutive in chronological order.

[0021] In the first aspect described above, time information indicating the measurement time is attached to the measurement values, and the processor may select at least a part of the plurality of measurement values that are discrete in chronological order.

[0022] In the first aspect described above, the measurement value may be at least one of the size of the lesion and the signal value at the lesion site of the medical image obtained by imaging the lesion.

[0023] The second aspect of the present disclosure is an information processing method, including acquiring a plurality of measurement values measured at a plurality of different time points from the same subject, acquiring a sentence corresponding to the measurement value, and selecting at least a part of the plurality of measurement values based on a phrase related to the measurement value included in the sentence.

[0024] The third aspect of the present disclosure is an information processing program for causing a computer to execute a process of acquiring a plurality of measurement values measured at a plurality of different time points from the same subject, acquiring a sentence corresponding to the measurement value, and selecting at least a part of the plurality of measurement values based on a phrase related to the measurement value included in the sentence.

Advantages of the Invention

[0025] According to the above aspect, the information processing apparatus, information processing method, and information processing program of the present disclosure can assist in creating a medical document.

Brief Description of Drawings

[0026] [Figure 1] It is a diagram showing an example of the schematic configuration of an information processing system. [Figure 2] It is a diagram showing an example of a medical image. [Figure 3] It is a diagram showing an example of a medical image. [Figure 4] It is a block diagram showing an example of the hardware configuration of an information processing apparatus. [Figure 5] It is a block diagram showing an example of the functional configuration of an information processing apparatus. [Figure 6] It is a diagram showing an example of a plurality of measurement values. [Figure 7] It is a diagram showing an example of a plot diagram including a plurality of measurement values. [Figure 8] It is a diagram showing an example of a screen according to the first embodiment. [Figure 9] It is a diagram showing an example of a screen according to the second embodiment. [Figure 10] It is a diagram showing an example of a screen according to the third embodiment. [Figure 11] It is a diagram showing an example of a screen according to the fourth embodiment. [Figure 12] It is a diagram showing an example of a screen according to the fifth embodiment. [Figure 13] It is a flowchart showing an example of information processing.

Modes for Carrying Out the Invention

[0027] Embodiments of this disclosure will be described below with reference to the drawings. First, the configuration of the information processing system 1 to which the information processing device of this disclosure is applied will be described. Figure 1 is a diagram showing the schematic configuration of the information processing system 1. The information processing system 1 shown in Figure 1 performs imaging of the area to be examined of a subject and stores the medical images obtained by imaging, based on examination orders from physicians in clinical departments using a known ordering system. It also performs medical image interpretation work by radiologists and the creation of interpretation reports, and allows physicians in the requesting clinical departments to view the interpretation reports.

[0028] As shown in Figure 1, the information processing system 1 includes an imaging device 2, an image interpretation terminal (Image Interpretation WS (WorkStation) 3, a medical examination WS 4, an image server 5, an image database (DB) 6, a report server 7, and a report database 8. The imaging device 2, image interpretation WS 3, medical examination WS 4, image server 5, image database 6, report server 7, and report database 8 are connected to each other via a wired or wireless network 9, enabling them to communicate with one another.

[0029] Each device is a computer on which an application program is installed to function as a component of the information processing system 1. The application program may be recorded and distributed on recording media such as DVD-ROM (Digital Versatile Disc Read Only Memory) and CD-ROM (Compact Disc Read Only Memory), and installed on the computer from that recording media. Alternatively, it may be stored in a storage device or network storage of a server computer connected to network 9 in an externally accessible state, and downloaded and installed on the computer upon request.

[0030] The imaging device 2 is a device (modality) that generates a medical image T representing the area to be diagnosed by imaging the area of ​​the subject to be diagnosed. Examples of imaging devices 2 include plain X-ray machines, CT (Computed Tomography) machines, MRI (Magnetic Resonance Imaging) machines, PET (Positron Emission Tomography) machines, ultrasound diagnostic machines, endoscopes, and fundus cameras. The medical images generated by imaging device 2 are transmitted to the image server 5 and stored in the image database 6.

[0031] The Image Interpretation WS3 is a computer used by medical professionals, such as radiologists in the radiology department, for interpreting medical images and creating interpretation reports, and it incorporates the information processing device 10 according to this embodiment. The Image Interpretation WS3 handles requests to view medical images from the image server 5, various image processing on medical images received from the image server 5, display of medical images, and acceptance of input of text related to medical images. The Image Interpretation WS3 also performs analysis processing on medical images, assists in creating interpretation reports based on the analysis results, requests registration and viewing of interpretation reports from the report server 7, and displays interpretation reports received from the report server 7. These processes are performed by the Image Interpretation WS3 executing software programs for each process.

[0032] The Clinical WS4 is a computer used by medical professionals, such as physicians in a clinical department, for tasks such as detailed observation of medical images, viewing of image interpretation reports, and creation of electronic medical records. It consists of a processing unit, display devices such as a display, and input devices such as a keyboard and mouse. The Clinical WS4 performs tasks such as requesting access to medical images from the image server 5, displaying medical images received from the image server 5, requesting access to image interpretation reports from the report server 7, and displaying image interpretation reports received from the report server 7. These processes are carried out by the Clinical WS4 executing software programs for each process.

[0033] Image Server 5 is a general-purpose computer with a software program installed that provides the functionality of a Database Management System (DBMS). Image Server 5 is connected to Image DB 6. The connection method between Image Server 5 and Image DB 6 is not particularly limited; it may be connected via a data bus, or via a network such as NAS (Network Attached Storage) or SAN (Storage Area Network).

[0034] The image database 6 is implemented using storage media such as an HDD (Hard Disk Drive), SSD (Solid State Drive), and flash memory. The image database 6 stores medical images acquired by the imaging device 2, along with associated information attached to those medical images.

[0035] The supplementary information may include identification information such as an image ID (identification) for identifying a medical image, a tomographic ID assigned to each tomographic image contained in the medical image, a subject ID for identifying the subject, and an examination ID for identifying the examination. The supplementary information may also include information related to the acquisition of the medical image, such as the acquisition method, acquisition conditions, and acquisition date and time. "Acquisition method" and "acquisition conditions" refer to, for example, the type of imaging device 2, the acquisition site, acquisition protocol, acquisition sequence, imaging technique, whether or not contrast agent was used, and the slice thickness in tomographic imaging. The supplementary information may also include information related to the subject, such as the subject's name, date of birth, age, and sex. The supplementary information may also include information related to the purpose of acquiring the medical image.

[0036] Furthermore, when the image server 5 receives a request to register a medical image from the imaging device 2, it formats the medical image into a database format and registers it in the image DB 6. Also, when the image server 5 receives a viewing request from the image interpretation WS3 and the medical treatment WS4, it searches for the medical image registered in the image DB 6 and sends the retrieved medical image to the image interpretation WS3 and the medical treatment WS4 that made the viewing request.

[0037] Report Server 7 is a general-purpose computer with software programs installed that provide the functionality of a database management system. Report Server 7 is connected to Report DB 8. The connection method between Report Server 7 and Report DB 8 is not particularly limited; it may be connected via a data bus, or via a network such as a NAS or SAN.

[0038] The report database (DB8) is implemented using storage media such as HDDs, SSDs, and flash memory. The report database (DB8) stores the image interpretation reports created in the image interpretation workstation (WS3).

[0039] Furthermore, when the report server 7 receives a request to register an image interpretation report from the image interpretation WS3, it formats the image interpretation report into a database format and registers it in the report DB8. Also, when the report server 7 receives a request to view an image interpretation report from the image interpretation WS3 and the medical WS4, it searches the report DB8 for the image interpretation report registered therein and sends the retrieved image interpretation report to the image interpretation WS3 and medical WS4 that made the viewing request.

[0040] Network 9 is, for example, a LAN (Local Area Network) and a WAN (Wide Area Network). The imaging device 2, image interpretation WS3, medical examination WS4, image server 5, image DB6, report server 7, and report DB8 included in the information processing system 1 may be located in the same medical institution or in different medical institutions. Furthermore, the number of each device, imaging device 2, image interpretation WS3, medical examination WS4, image server 5, image DB6, report server 7, and report DB8, is not limited to the number shown in Figure 1, and each device may consist of multiple devices with similar functions.

[0041] Figure 2 is a schematic diagram showing an example of a medical image acquired by imaging device 2. The medical image T shown in Figure 2 is a CT image consisting of multiple tomographic images T1 to Tm (where m is 2 or more), each representing a cross-sectional plane from the head to the waist of a single subject (human body).

[0042] Figure 3 schematically shows an example of one tomographic image Tx from among multiple tomographic images T1 to Tm. The tomographic image Tx shown in Figure 3 represents a tomographic plane including the lung. Each tomographic image T1 to Tm may include regions SA of structures showing various organs and tissues of the human body (e.g., lungs and liver, etc.) and various tissues that constitute these organs and tissues (e.g., blood vessels, nerves and muscles, etc.). In addition, each tomographic image may include regions AA of abnormal shadows showing lesions such as nodules, tumors, injuries, defects and inflammation. In the tomographic image Tx shown in Figure 3, the lung region is the region SA of structures, and the nodule region is the region AA of abnormal shadows. Note that a single tomographic image may contain multiple regions SA of structures and / or regions AA of abnormal shadows.

[0043] Incidentally, in cases such as regular health checkups and follow-up examinations after treatment, the same subject may be examined multiple times, and data on various measurements such as the size of lesions may be accumulated at multiple points in time. The information processing device 10 according to this embodiment has the function of supporting the creation of medical documents by selectively presenting measurement values ​​that are expected to be of interest to the user from among such measurement values ​​at multiple points in time. The information processing device 10 will be described below. As mentioned above, the information processing device 10 is included in the image interpretation WS3.

[0044] First, an example of the hardware configuration of the information processing device 10 according to this embodiment will be described with reference to Figure 4. As shown in Figure 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 mouse, and a network interface 26. The network interface 26 is connected to a network 9 and performs wired or wireless communication. The CPU 21, storage unit 22, memory 23, display 24, input unit 25, and network interface 26 are connected to each other via a bus 28 such as a system bus and a control bus, enabling the exchange of various types of information.

[0045] The storage unit 22 is implemented by a storage medium such as an HDD, SSD, or flash memory. The information processing program 27 of 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 into memory 23, and executes the expanded information processing program 27. The CPU 21 is an example of the processor of this disclosure. The information processing device 10 can be appropriately applied to, for example, a personal computer, a server computer, a smartphone, a tablet terminal, or a wearable terminal.

[0046] Next, an example of the functional configuration of the information processing device 10 according to this embodiment will be described with reference to Figures 5 to 12. As shown in Figure 5, the information processing device 10 includes an acquisition unit 30, a selection unit 32, a creation unit 34, and a control unit 36. The CPU 21 executes the information processing program 27, and the CPU 21 functions as the acquisition unit 30, the selection unit 32, the creation unit 34, and the control unit 36.

[0047] The acquisition unit 30 acquires multiple measurement values ​​taken from the same subject at multiple different time points. The measurement values ​​may be, for example, the size of the lesion and at least one of the signal values ​​at the site of the lesion in the medical image obtained by imaging the lesion. The size of the lesion is expressed, for example, by the major axis, minor axis, area, and volume of the abnormal shadow region AA contained in the medical image Tx. The signal values ​​are expressed, for example, by the pixel values ​​of the abnormal shadow region AA contained in the medical image Tx, and CT values ​​with units of HU.

[0048] Specifically, the acquisition unit 30 may acquire multiple medical images taken at multiple different time points from the image server 5 and obtain measurement values ​​by performing image analysis on the multiple medical images. For example, the acquisition unit 30 may derive measurement values ​​based on image features derived using a pre-trained model such as a CNN (Convolutional Neural Network) that takes medical images as input and outputs image features of the medical images.

[0049] Figure 6 shows an example of multiple measurements, representing the longest axis of the abnormal shadow area AA. As shown in Figure 6, the measurement is accompanied by time information indicating the time of measurement. The time information can be any information that allows multiple measurements to be arranged in the order they were measured (i.e., in chronological order), and may be information indicating the date and time as shown in Figure 6, or information indicating which measurement it was. In other words, the measurement is time-series data. Figure 7 shows plot P0, which includes all of the multiple measurement values ​​shown in Figure 6. Plot P0 is a line graph with the measurement values ​​on the vertical axis and the time information attached to the measurement values ​​on the horizontal axis.

[0050] Furthermore, the acquisition unit 30 acquires sentences corresponding to the multiple acquired measurement values. Specifically, sentences corresponding to measurement values ​​may include descriptions related to the measurement values, such as changes in the measurement values ​​over time, comparison results with reference values, disease names diagnosed based on the measurement values, and the purpose of the examination. Such sentences may include, for example, the findings and other supplementary information described in the image interpretation report.

[0051] Specifically, the acquisition unit 30 may acquire medical images from the image server 5, generate observation statements corresponding to measurement values ​​from the medical images using machine learning, and acquire these observation statements as sentences corresponding to measurement values. As a method for generating observation statements using machine learning, for example, the method using a recurrent neural network described in Patent Document 1 above can be appropriately applied. Alternatively, for example, the acquisition unit 30 may generate observation statements using a known method that generates observation statements using a predetermined template, and acquire these observation statements as sentences corresponding to measurement values.

[0052] The selection unit 32 identifies words related to the measured values ​​contained in the sentence acquired by the acquisition unit 30. "Words related to the measured values" include, for example, words that represent the change in the measured values ​​over time, words that represent the name of the disease diagnosed from the measured values, words that represent the purpose of the test, and words that represent the absolute value of the measured values. As a method for identifying words from a sentence, known named entity recognition methods using natural language processing models such as BERT (Bidirectional Encoder Representations from Transformers) can be appropriately applied.

[0053] Furthermore, the selection unit 32 selects at least some of the multiple measurement values ​​acquired by the acquisition unit 30 based on the words related to the identified measurement value. Specifically, the selection unit 32 may select a measurement value to which time information indicating the measurement time is attached, determined based on the words related to the measurement value. Alternatively, the selection unit 32 may select at least some of the multiple measurement values ​​depending on the number of measurement values ​​determined based on the words related to the measurement value. Which part of the multiple measurement values ​​to select may be predetermined for each word and stored in the storage unit 22.

[0054] The creation unit 34 uses the measured values ​​and the time information attached to those measured values ​​as variables and creates a plot diagram that includes at least some of the measured values ​​selected by the selection unit 32. The control unit 36 ​​controls the display 24 to display the plot diagram created by the creation unit 34. Below, examples of how the selection unit 32 selects some of the multiple measured values ​​and what kind of plot diagram the creation unit 34 creates will be described in the first to tenth embodiments.

[0055] (First embodiment) The first embodiment will be described with reference to Figure 8. Figure 8 is an example of screen D1 for creating an image interpretation report, which is displayed on the display 24 by the control unit 36. Screen D1 includes subject information 60, findings statement L1, medical image Tx, and plot diagram P1. Finding statement L1 is an example of a sentence corresponding to the measurement value acquired by the acquisition unit 30. The medical image Tx is acquired from the image server 5 by the acquisition unit 30. Subject information 60 is information including the subject ID and the subject's name, date of birth, age, sex, and purpose of examination, which is included in the supplementary information of the medical image Tx acquired by the acquisition unit 30.

[0056] The observation statement L1 includes the phrase, "Compared to the previous measurement, the major axis has increased by 5 mm," which describes the change in the measured value over time. When a user checks the measured value corresponding to this phrase, it is expected that they will focus on the most recent two to three measurements out of all the multiple measurements (see Figure 7).

[0057] Therefore, the selection unit 32 identifies phrases in the observation statement L1 that represent the change in the measured value over time. Based on the identified phrases that represent the change in the measured value over time, the selection unit 32 selects at least some of the multiple measured values ​​acquired by the acquisition unit 30. For example, as shown in plot diagram P1 of Figure 8, the selection unit 32 may select the three most recent measured values ​​in response to the phrase, "Compared to the previous measurement, the major axis has increased by 5 mm."

[0058] The creation unit 34 creates a plot diagram P1 that includes the measured values ​​selected by the selection unit 32. That is, the plot diagram P1 is a line graph that includes the measured values ​​related to the findings statement L1. The control unit 36 ​​controls the display 24 to display screen D1, which includes the plot diagram P1 created by the creation unit 34.

[0059] According to screen D1, the user can view the findings statement L1 generated by the acquisition unit 30 and the plot diagram P1 which includes the measured values ​​related to the findings statement L1. Therefore, the user can perform the image interpretation report creation work while viewing the plot diagram P1, which has better visibility than the plot diagram P0 (see Figure 7) which includes all measured values.

[0060] (Second example) The second embodiment will be described with reference to Figure 9. Figure 9 is an example of screen D2 for creating an image interpretation report, which is displayed on the display 24 by the control unit 36. Screen D2 differs from screen D1 of the first embodiment in the content of the findings text L2 and plot diagram P2, but is otherwise the same, so redundant explanations will be omitted.

[0061] The L2 observation statement includes the phrase, "The major axis is gradually increasing," which describes the change in the measured value over time. When a user checks the measured value corresponding to this phrase, it is expected that they will focus on the portion of the multiple measured values ​​(see Figure 7) that is showing an increasing trend.

[0062] Therefore, as shown in plot diagram P2, the selection unit 32 may select measurement values ​​in the portion where the change in the increasing direction is large, corresponding to the phrase "the major axis is gradually increasing." A portion where the change is large may, for example, be a portion where the difference between two consecutive measurement values ​​is greater than or equal to a predetermined threshold. Alternatively, for example, it may be a portion where the difference between the maximum and minimum values ​​in a predetermined range (for example, a range including five measurement values) that includes two or more consecutive measurement values ​​is greater than or equal to a predetermined threshold. In order to improve the visibility of plot diagram P2, it is preferable to select approximately two to five measurement values.

[0063] (Third embodiment) A third embodiment will be described with reference to Figure 10. Figure 10 is an example of screen D3 for creating an image interpretation report, which is displayed on the display 24 by the control unit 36. Screen D3 differs from screen D1 of the first embodiment in the content of the findings text L3 and plot diagram P3, but is otherwise the same, so redundant explanations will be omitted.

[0064] The observation statement L3 includes the phrase, "The major axis has increased by more than 10 mm since six months ago," which describes the change in the measured value over time. When a user checks the measured value corresponding to this phrase, it is expected that they will focus on the measured values ​​from six months ago and the most recent measurement among all of the multiple measured values ​​(see Figure 7).

[0065] Therefore, as shown in plot figure P3, the selection unit 32 may select measurement values ​​from six months ago to the present in response to the phrase, "The major axis has increased by 10 mm or more since six months ago." In other words, the selection unit 32 may select measurement values ​​to which time information indicating the measurement point, determined based on phrases related to the measurement values, is attached.

[0066] (Fourth embodiment) The selection unit 32 may select at least some of the multiple measurement values ​​obtained by the acquisition unit 30 based on the words representing disease names contained in the sentences obtained by the acquisition unit 30. In other words, the selection unit 32 may vary the way it selects measurement values ​​depending on the words representing disease names contained in the sentences. This is because the point in time at which to focus on measurement values ​​may differ depending on the nature of the disease.

[0067] For example, the selection unit 32 may select the two most recent measurement values ​​if the sentence acquired by the acquisition unit 30 contains a phrase representing the disease name "diffuse panbronchiolitis," and select all of the multiple measurement values ​​if the sentence contains a phrase representing "pneumonia."

[0068] (Fifth example) The selection unit 32 may select at least some of the multiple measurement values ​​obtained by the acquisition unit 30 based on the words or phrases that represent the inspection purpose contained in the sentence obtained by the acquisition unit 30. In other words, the selection unit 32 may vary the way it selects the measurement values ​​depending on the words or phrases that represent the inspection purpose contained in the sentence, because depending on the content of the inspection, the point in time at which the measurement value should be focused may differ.

[0069] For example, the selection unit 32 may select the five most recent measurement values ​​if the sentence acquired by the acquisition unit 30 contains the phrase "regular health checkup" which indicates the purpose of the examination, and select the three most recent measurement values ​​if the sentence contains the phrase "postoperative follow-up."

[0070] (Sixth embodiment) As shown in the findings statement L1 in Figure 8, the statement acquired by the acquisition unit 30 may include a phrase that represents the absolute value of the measured value ("major diameter 25 mm"). In this case, the selection unit 32 may decide whether or not to select the measured value based on the comparison result between the measured value included in the statement and a predetermined threshold. For example, the selection unit 32 may select a measured value if the statement contains a phrase that represents a measured value above a predetermined threshold, for a measured value that means the condition is worse in proportion to the magnitude of the numerical value.

[0071] On the other hand, the selection unit 32 does not have to select a measurement value if the sentence contains a phrase that represents a measurement value below a predetermined threshold. Also, if no measurement value is selected by the selection unit 32, the creation unit 34 may or may not create a plot diagram that includes all of the multiple measurement values ​​acquired by the acquisition unit 30. This is because if no measurement value is selected by the selection unit 32, there is a possibility that no measurement value of interest exists.

[0072] (Seventh Example) The sentence acquired by the acquisition unit 30 may contain multiple phrases that represent the absolute value of the measured value (e.g., "major diameter 20 mm", "major diameter 25 mm"), such as "Last time the major diameter was 20 mm, but this time it has increased to 25 mm." In this case, the selection unit 32 may decide whether or not to select the at least two measured values ​​based on the comparison result between the difference between at least two measured values ​​contained in the sentence and a predetermined threshold.

[0073] For example, the selection unit 32 may select two measurement values ​​if the difference between the two measurement values ​​included in the sentence is greater than or equal to a predetermined threshold, indicating a large variation. Alternatively, for example, if the sentence includes three or more measurement values, the selection unit 32 may select three or more measurement values ​​if the difference between the maximum and minimum values ​​among the three or more measurement values ​​is greater than or equal to a predetermined threshold, indicating a large variation.

[0074] (Eighth example) In the first to third embodiments (see Figures 8 to 10), an example was described in which the selection unit 32 selects at least a portion of multiple measurement values ​​that are consecutive in chronological order, but it is not limited to this. In this embodiment, an example is described in which the selection unit 32 selects at least a portion of multiple measurement values ​​that are discrete in chronological order.

[0075] The eighth embodiment will be described with reference to Figure 11. Figure 11 is an example of screen D4 for creating an image interpretation report, which is displayed on the display 24 by the control unit 36. Screen D4 differs from screen D1 of the first embodiment in the content of the findings text L4 and plot diagram P4, but is otherwise the same, so redundant explanations will be omitted.

[0076] The findings statement L4 includes the phrase, "Compared to the initial examination, the longest diameter has increased by 20 mm," which describes the change in the measured value over time. When a user checks the measured value corresponding to this phrase, it is expected that they will focus on the initial and most recent measured values ​​among all of the multiple measured values ​​(see Figure 7).

[0077] Therefore, as shown in plot figure P4, the selection unit 32 may select the first two measurements (i.e., the initial measurement), the most recent three measurements, and five discrete measurements in chronological order, corresponding to the phrase, "The major axis has increased by 20 mm compared to the initial measurement." In this case, the creation unit 34 may create plot figure P4 using ellipsis lines (wavy lines) to indicate that intermediate measurements have been omitted.

[0078] (9th example) In the above embodiment, a form was described in which the selection unit 32 selects some of a plurality of measurement values ​​based on various words related to the measurement values ​​contained in the sentence, but it is not limited to this. The selection unit 32 may select additional measurement values ​​in addition to the measurement values ​​selected based on words related to the measurement values. For example, the selection unit 32 may select at least two measurement values ​​if the difference between at least two measurement values ​​included in the plurality of measurement values ​​satisfies a predetermined condition.

[0079] The ninth embodiment will be described with reference to Figure 12. The ninth embodiment is a modification of the first embodiment, and is an example in which, in addition to the three most recent measurement values ​​selected based on the phrase "The major axis has increased by 5 mm compared to the previous measurement" included in the findings statement L1, the measurement value as of September 2021 is also selected. Figure 12 is an example of screen D5 for creating the image interpretation report, which is displayed on the display 24 by the control unit 36. Screen D5 differs in content from screen D1 of the first embodiment and plot diagram P5, but other elements, including the findings statement L1, are the same, so redundant explanations will be omitted.

[0080] Similar to the first embodiment, the selection unit 32 first selects the three most recent measurement values ​​in response to the phrase "The major axis has increased by 5 mm compared to the previous measurement" contained in the observation statement L1. Subsequently, the selection unit 32 may select a portion of the multiple measurement values ​​that shows large fluctuations, such as when the difference between two consecutive measurement values ​​is greater than or equal to a predetermined threshold. In the example in Figure 6, if the threshold is 5, the difference between the measurement value in September 2021 and the measurement value immediately following it in November 2021 is 5. Therefore, the selection unit 32 may add the measurement value in September 2021 to the three most recent measurement values ​​and select them.

[0081] Alternatively, the selection unit 32 may select a portion of the range with large fluctuations where the difference between the maximum and minimum values ​​in a predetermined range (for example, a range including five measurements) that includes two or more consecutive measurements is greater than or equal to a predetermined threshold.

[0082] This format allows for the inclusion of highly variable measurements in the plot, even if not explicitly stated in the text. In other words, it allows for the presentation of a plot that includes measurements at a point in time when a rapid deterioration or improvement in the patient's condition is suspected, thus reducing the likelihood of overlooking important details.

[0083] (Tenth example) Similar to the ninth embodiment, the selection unit 32 may further select measurement values ​​that satisfy predetermined conditions from among multiple measurement values, in addition to the measurement values ​​selected based on various terms related to the measurement values. For example, the selection unit 32 may select measurement values ​​that are above a predetermined threshold for measurement values ​​that indicate a worsening of the disease condition in proportion to the magnitude of the numerical value.

[0084] This format allows for the inclusion of particularly poor values ​​in the plot, even if not explicitly stated in the text. In other words, it allows for the presentation of a plot that includes measurements at a point in time when the patient's condition is suspected to be particularly bad, thus reducing the likelihood of overlooking important information.

[0085] Next, the operation of the information processing device 10 according to this embodiment will be explained with reference to Figure 13. In the information processing device 10, the CPU 21 executes the information processing program 27, thereby executing the information processing shown in Figure 13. The information processing is executed, for example, when the user issues an instruction to start execution via the input unit 25.

[0086] In step S10, the acquisition unit 30 acquires multiple measurement values ​​taken from the same subject at multiple different time points. In step S12, the acquisition unit 30 acquires sentences corresponding to the measurement values ​​acquired in step S10. In step S14, the selection unit 32 identifies words corresponding to the measurement values ​​from the sentences acquired in step S12. In step S16, the selection unit 32 selects at least some of the multiple measurement values ​​acquired in step S10 based on the words corresponding to the measurement values ​​identified in step S14.

[0087] In step S18, the creation unit 34 creates a plot diagram that includes at least some of the measurements selected in step S16. In step S20, the control unit 36 ​​controls the display 24 to display the plot diagram created in step S18, and then terminates this information processing.

[0088] As described above, an information processing device 10 according to one aspect of the present disclosure comprises at least one processor, which acquires a plurality of measurement values ​​measured from the same subject at multiple different time points, acquires sentences corresponding to the measurement values, and selects at least a portion of the plurality of measurement values ​​based on words related to the measurement values ​​contained in the sentences.

[0089] In other words, the information processing device 10 according to this embodiment can selectively present measurement values ​​that are expected to attract the user's attention from among multiple measurement values. Therefore, measurement values ​​can be presented in a form that is highly visible during tasks such as creating image interpretation reports, thereby supporting the creation of medical documents.

[0090] In the above embodiment, the acquisition unit 30 was described as deriving measurement values ​​by performing image analysis on medical images, but it is not limited to this. For example, the acquisition unit 30 may acquire measurement values ​​that have been pre-stored in the storage unit 22, image server 5, image DB 6, report server 7, report DB 8, and other external devices. Alternatively, for example, the acquisition unit 30 may acquire measurement values ​​that have been manually entered by the user via the input unit 25.

[0091] Furthermore, although the above embodiment describes a configuration in which the acquisition unit 30 generates sentences corresponding to measurement values ​​from medical images using machine learning, the system is not limited to this configuration. For example, the acquisition unit 30 may acquire sentences that are pre-stored in the report DB 8, storage unit 22, and other external devices. Alternatively, the acquisition unit 30 may acquire sentences that are manually entered by the user via the input unit 25.

[0092] Furthermore, although the above embodiment was described using a measurement value representing the longest diameter of a single lesion, it is not limited to this. For example, if there are multiple lesions in the same subject, the acquisition unit 30 may acquire measurement values ​​at multiple time points for each of the multiple lesions, and the selection unit 32 may select some of the measurement values ​​for each of the multiple lesions. Alternatively, for example, the acquisition unit 30 may acquire multiple types of measurement values ​​(e.g., longest diameter and signal value) at multiple time points for the same lesion, and the selection unit 32 may select some of the measurement values ​​for each of the multiple types of measurement values. In these cases, the creation unit 34 may combine the measurement values ​​for multiple lesions, and / or multiple types of measurement values, into a single plot.

[0093] Furthermore, a user who has viewed a plot diagram containing some of the measured values ​​created in the above embodiment may subsequently wish to view a plot diagram containing all the measured values ​​(see Figure 7). Therefore, the control unit 36 ​​may receive a user instruction to display a plot diagram containing all the measured values ​​via the input unit 25. The creation unit 34 may also create a plot diagram for multiple measured values ​​when the control unit 36 ​​receives an instruction to display a plot diagram containing all the measured values. The control unit 36 ​​may also control the display 24 to display the plot diagram containing all the measured values ​​created by the creation unit 34, either in place of or in addition to the plot diagram containing some of the measured values.

[0094] Furthermore, although the above embodiment describes a configuration assuming the creation of an image interpretation report in the image interpretation WS3, it is not limited to this configuration. For example, the information processing device 10 may, in the viewing of an image interpretation report in the image interpretation WS3 and / or medical WS4, present a plot diagram that selectively includes some of the multiple measurement values ​​based on the text contained in the image interpretation report being viewed. With such a configuration, regardless of what kind of plot diagram the creator was looking at in the creation of the image interpretation report, the plot diagram can be presented in a form that is easy for viewers of the image interpretation report to see, thereby improving the visibility of the image interpretation report.

[0095] Furthermore, while the above embodiment describes a form assuming an interpretation report of medical images, the invention is not limited to this. The information processing device 10 of this disclosure is applicable to the creation and / or viewing of various medical documents including text and measurement values. For example, the information processing device 10 may be applied to the creation and / or viewing of a report on the results of a periodic health checkup.

[0096] Furthermore, in the above embodiment, the hardware structure of the processing unit that executes various processes, such as the acquisition unit 30, the selection unit 32, the creation unit 34, and the control unit 36, can be the various processors shown below. As mentioned above, these various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as programmable logic devices (PLDs), such as FPGAs (Field Programmable Gate Arrays), which are processors whose circuit configuration can be changed after manufacturing, and dedicated electrical circuits, such as ASICs (Application Specific Integrated Circuits), which are processors with circuit configurations specifically designed to execute specific processes.

[0097] A single processing unit may consist of one of these various processors, or it may consist of 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). Alternatively, multiple processing units may be composed of a single processor.

[0098] Examples of configuring multiple processing units with a single processor include, firstly, a configuration where one or more CPUs and software combine to form a single processor, which then functions as multiple processing units, as exemplified by client and server computers. Secondly, a configuration using a processor that realizes the functions of the entire system, including multiple processing units, on a single IC (Integrated Circuit) chip, as exemplified by System on Chip (SoC). Thus, various processing units are configured, in terms of hardware structure, using one or more of the above-mentioned processors.

[0099] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits, which are combinations of circuit elements such as semiconductor devices.

[0100] Furthermore, although the above embodiment describes an embodiment in which the information processing program 27 is pre-stored (installed) in the storage unit 22, the invention is not limited to this. The information processing program 27 may be provided in the form of a recording medium such as a CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), and USB (Universal Serial Bus) memory. Alternatively, the information processing program 27 may be provided in the form of a download from an external device via a network. Moreover, the technology of this disclosure extends not only to the information processing program but also to storage media for non-temporarily storing the information processing program.

[0101] The technology of this disclosure can also be appropriately combined from the above-described embodiments and examples. The descriptions and illustrations shown above are detailed explanations of the parts relating to the technology of this disclosure and are merely examples of the technology of this disclosure. For example, the above-described explanation of the configuration, function, operation, and effect is an explanation of an example of the configuration, function, operation, and effect of the parts relating to the technology of this disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements added, or replaced from the descriptions and illustrations shown above, as long as they do not depart from the spirit of the technology of this disclosure. [Explanation of symbols]

[0102] 1. Information Processing System 2. Imaging device 3 Image Interpretation Workshop 4. Medical Workshop 5 Image Server 6 Image Database 7. Report Server 8 Report Database 9 Network 10 Information Processing Devices 21 CPU 22 Memory section 23 memory 24 displays 25 Input section 26 Network Interface 27 Information Processing Programs 28 buses 30 Acquisition Department 32 Selection Section 34 Creation Section 36 Control Unit 60 Subject Information AA Area of ​​abnormal shadows D1~D5 screen L1~L4 Observations P0-P5 Plot Diagram Area of ​​SA structures T Medical Images T1-Tm, Tx tomographic images

Claims

1. Equipped with at least one processor, The aforementioned processor, By obtaining multiple measurements taken from the same subject at multiple different time points, The sentence corresponding to the aforementioned measurement value is obtained, Based on the words related to the measured values ​​contained in the preceding sentence, and the predetermined selection conditions for each word, at least a portion of the plurality of measured values ​​is selected. The aforementioned measurement value is a value measured based on a medical image obtained by photographing the subject, The aforementioned statement is at least one of the findings statement generated based on the medical image and the supplementary information of the medical image. Information processing device.

2. The aforementioned processor, Based on the words in the preceding sentence that describe the change in the measured values ​​over time, at least a portion of the plurality of measured values ​​are selected. The information processing apparatus according to claim 1.

3. The aforementioned measurement value is accompanied by time information indicating the time of measurement. The aforementioned processor, Using the measured values ​​and time information as variables, create a plot diagram that includes at least some of the selected measured values. Display the plot diagram on the screen. The information processing apparatus according to claim 1 or claim 2.

4. The aforementioned processor, Upon receiving instructions, create the plot diagram containing all of the acquired multiple measurement values. Display the plot diagram on the screen. The information processing apparatus according to claim 3.

5. The aforementioned measurement value is accompanied by time information indicating the time of measurement. The aforementioned processor, Select the measured value to which time information indicating the measurement point is attached, determined based on the words related to the measured value. An information processing apparatus according to any one of claims 1 to 4.

6. The aforementioned processor, Depending on the number of measurements determined based on the words related to the measurement, at least a portion of the plurality of measurements are selected. An information processing apparatus according to any one of claims 1 to 5.

7. The aforementioned processor, Based on the words representing the disease name included in the above sentence, select at least some of the multiple measurement values. An information processing apparatus according to any one of claims 1 to 6.

8. The aforementioned processor, Based on the words or phrases in the preceding sentence that represent the purpose of the test, select at least some of the multiple measurement values. An information processing apparatus according to any one of claims 1 to 7.

9. The aforementioned processor, Based on the comparison result between the measured value included in the preceding sentence and a predetermined threshold, it is determined whether or not to select the measured value. An information processing apparatus according to any one of claims 1 to 8.

10. The aforementioned processor, Based on the comparison result between the difference between at least two of the aforementioned measurement values ​​included in the preceding sentence and a predetermined threshold, it is determined whether or not to select the at least two measurement values. An information processing apparatus according to any one of claims 1 to 9.

11. The aforementioned processor, From the aforementioned multiple measurement values, select the measurement value that satisfies the predetermined conditions. An information processing apparatus according to any one of claims 1 to 10.

12. The aforementioned processor, If the difference between at least two of the aforementioned multiple measurement values ​​satisfies a predetermined condition, then those at least two measurement values ​​are selected. An information processing apparatus according to any one of claims 1 to 11.

13. The aforementioned measurement value is accompanied by time information indicating the time of measurement. The aforementioned processor, Select at least a portion of the aforementioned multiple measurement values ​​in a continuous time-series order. An information processing apparatus according to any one of claims 1 to 12.

14. The aforementioned measurement value is accompanied by time information indicating the time of measurement. The aforementioned processor, Select at least a portion of the aforementioned multiple measurements that are discretely arranged in chronological order. An information processing apparatus according to any one of claims 1 to 13.

15. The measured value is at least one of the size of the lesion and the signal value at the site of the lesion in the medical image obtained by photographing the lesion. An information processing apparatus according to any one of claims 1 to 14.

16. By obtaining multiple measurements taken from the same subject at multiple different time points, The sentence corresponding to the aforementioned measurement value is obtained, Based on the words related to the measured values ​​contained in the preceding sentence, and the predetermined selection conditions for each word, at least a portion of the plurality of measured values ​​is selected. The aforementioned measurement value is a value measured based on a medical image obtained by photographing the subject, The aforementioned statement is at least one of the findings statement generated based on the medical image and the supplementary information of the medical image. An information processing method in which a computer performs the processing.

17. By obtaining multiple measurements taken from the same subject at multiple different time points, The sentence corresponding to the aforementioned measurement value is obtained, Based on the words related to the measured values ​​contained in the preceding sentence, and the predetermined selection conditions for each word, at least a portion of the plurality of measured values ​​is selected. The aforementioned measurement value is a value measured based on a medical image obtained by photographing the subject, The aforementioned statement is at least one of the findings statement generated based on the medical image and the supplementary information of the medical image. An information processing program that causes a computer to perform a task.

Images