Classifications

• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
  • G06F16/35—Clustering; Classification
  • G06F16/353—Clustering; Classification into predefined classes
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
  • G06F16/33—Querying
  • G06F16/3331—Query processing
  • G06F16/3332—Query translation
  • G06F16/3334—Selection or weighting of terms from queries, including natural language queries
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
  • G06F16/33—Querying
  • G06F16/3331—Query processing
  • G06F16/334—Query execution
  • G06F16/3344—Query execution using natural language analysis
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
  • G06F16/38—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
  • G06F16/383—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
• • G—PHYSICS
  • G06—COMPUTING OR CALCULATING; COUNTING
  • G06F—ELECTRIC DIGITAL DATA PROCESSING
  • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
  • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
  • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
  • G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof

Definitions

• the present disclosure relates to an information processing device, an information processing method, and an information processing program.
• image diagnosis is performed using medical images obtained by imaging devices such as CT (Computed Tomography) devices and MRI (Magnetic Resonance Imaging) devices.
• medical images are analyzed by CAD (Computer Aided Detection/Diagnosis) using discriminators trained by deep learning, etc., and regions of interest including structures and lesions included in medical images are detected and/or Diagnosis is being made.
• the medical image and the CAD analysis result are transmitted to the terminal of a medical worker such as an interpreting doctor who interprets the medical image.
• a medical professional such as an interpreting doctor interprets the medical image by referring to the medical image and the analysis result using his/her own terminal, and creates an interpretation report.
• Japanese Patent Application Laid-Open No. 2019-153250 discloses a technique for creating an interpretation report based on keywords input by an interpretation doctor and analysis results of medical images.
• sentences to be described in an interpretation report are created using a recurrent neural network trained to generate sentences from input characters.
• the present disclosure provides an information processing device, an information processing method, and an information processing program that can easily search for cases.
• a first aspect of the present disclosure is an information processing device comprising at least one processor, the processor extracting at least one word included in an observation sentence and classifying the word into a predetermined item. , a word is displayed for each item on the display, and medical information similar to the content of the remark statement is retrieved based on the word from among a plurality of recorded medical information.
• the processor may accept selection of at least one word used for medical information retrieval when a plurality of words are extracted from the finding sentence.
• the processor may cause the display to display an operation unit that accepts selection of at least one word used for medical information retrieval in association with the word.
• the processor based on at least one of synonyms and related words predetermined for each word, medical information can be searched.
• a fifth aspect of the present disclosure is the fourth aspect, wherein the processor retrieves the medical information based on the synonym if the number of medical information retrieved based on the word does not satisfy a predetermined threshold. You may search.
• a sixth aspect of the present disclosure is the fifth aspect, wherein if the number of medical information retrieved based on the synonym does not satisfy a predetermined threshold, the processor retrieves the medical information based on the related term can be searched.
• the processor based on the plurality of medical information, a plurality of Words may be identified as related terms.
• the processor obtains a plurality of observation sentences, and uses the plurality of observation sentences for searching medical information. A selection of at least one remark statement may be received.
• a ninth aspect of the present disclosure is the eighth aspect, wherein if the number of medical information retrieved based on words does not satisfy a predetermined threshold, the processor selects from among the plurality of finding sentences At least one word included in other observation sentences related to the observation sentence may be extracted, and medical information may be retrieved based on the words extracted from the other observation sentences.
• the processor may search for medical information based on a predetermined weight for each item.
• the processor may accept setting of weight for each item.
• the processor identifies factuality of the extracted word, and retrieves medical information based on the factuality. You may
• a thirteenth aspect of the present disclosure is any one of the first aspect to the twelfth aspect, wherein when the word indicates a numerical value, the processor accepts designation of a numerical range that is considered to be similar to the observation sentence. good.
• a fourteenth aspect of the present disclosure is any one of the first to thirteenth aspects, wherein the word indicates information about an abnormal shadow in a medical image, and the items include the name of the abnormal shadow, its properties, It may indicate at least one of the disease name, position, and measurement value.
• the processor may cause the retrieved medical information to be displayed on the display.
• a sixteenth aspect of the present disclosure is any one of the first to fifteenth aspects, wherein the processor derives a degree of similarity between the content of the finding sentence and the medical information, and derives the degree of similarity may be displayed on the display.
• a seventeenth aspect of the present disclosure is any one of the first aspect to the sixteenth aspect, wherein the medical information includes a medical image, an opinion statement about the medical image, and subject information about the subject of the medical image. , and biological information acquired from the subject.
• the medical information may indicate a statement of findings.
• a nineteenth aspect of the present disclosure is an information processing method, which extracts at least one word included in an observation sentence, classifies the word into predetermined items, displays the word on a display for each item, It includes processing for retrieving medical information similar to the content of the observation statement based on words from among a plurality of recorded medical information.
• a twentieth aspect of the present disclosure is an information processing program, which extracts at least one word included in an observation sentence, classifies the words into predetermined items, displays the words on a display for each item, This is for causing the computer to execute a process of retrieving medical information similar to the content of the observation statement based on words from among a plurality of pieces of recorded medical information.
• the information processing device, information processing method, and information processing program of the present disclosure can easily search for cases.
• FIG. 1 is a block diagram showing an example of a functional configuration of an information processing device;
• FIG. It is a figure which shows an example of the screen displayed on a display. It is a figure which shows an example of the screen displayed on a display. It is a figure which shows an example of a word.
• FIG. which shows an example of structured data. It is a figure which shows an example of the screen displayed on a display. It is a figure which shows an example of the screen displayed on a display. It is a figure which shows an example of the screen displayed on a display. It is a figure which shows an example of the screen displayed on a display. It is a figure which shows an example of the screen displayed on a display. It is a flow chart which shows an example of information processing. It is a figure which shows an example of the screen displayed on a display.
• FIG. 1 is a diagram showing a schematic configuration of an information processing system 1.
• An information processing system 1 shown in FIG. 1 performs imaging of an examination target site of a subject based on an examination order from a doctor of a clinical department using a known ordering system, and stores medical images obtained by the imaging.
• an interpretation doctor performs interpretation of medical images and creates an interpretation report, and a doctor of the department that requested the interpretation views the interpretation report.
• an information processing system 1 includes an imaging device 2, an image interpretation terminal (WorkStation) 3, a medical examination WS 4, an image server 5, an image DB (DataBase) 6, a report server 7, and a report DB 8. .
• the imaging device 2, interpretation WS 3, diagnosis WS 4, image server 5, image DB 6, report server 7, and report DB 8 are connected to each other via a wired or wireless network 9 so as to be able to communicate with each other.
• Each device is a computer installed with an application program for functioning as a component of the information processing system 1 .
• the application program may be recorded on a recording medium such as a DVD (Digital Versatile Disc) and a CD-ROM (Compact Disc Read Only Memory) for distribution, and may be installed in the computer from the recording medium.
• a recording medium such as a DVD (Digital Versatile Disc) and a CD-ROM (Compact Disc Read Only Memory) for distribution, and may be installed in the computer from the recording medium.
• a recording medium such as a DVD (Digital Versatile Disc) and a CD-ROM (Compact Disc Read Only Memory) for distribution, and may be installed in the computer from the recording medium.
• the imaging device 2 is a device (modality) that generates a medical image T representing the diagnosis target region by imaging the diagnosis target region of the subject. Specifically, it is a simple X-ray imaging device, a CT device, an MRI device, a PET (Positron Emission Tomography) device, and the like. A medical image generated by the imaging device 2 is transmitted to the image server 5 and stored in the image DB 6 .
• the interpretation WS3 is a computer used by a user such as an interpreting doctor in a radiology department to interpret medical images and create an interpretation report, and includes the information processing apparatus 10 according to this exemplary embodiment.
• the image interpretation WS3 requests the image server 5 to view medical images, performs various image processing on the medical images received from the image server 5, displays the medical images, and accepts input of sentences related to the medical images. Further, the interpretation WS 3 performs analysis processing on medical images, supports creation of interpretation reports based on the analysis results, requests registration and viewing of interpretation reports to the report server 7 , and displays interpretation reports received from the report server 7 . will be These processes are performed by the interpretation WS3 executing a software program for each process.
• the clinical WS 4 is a computer used by a user such as a doctor in a clinical department for detailed observation of medical images, viewing of interpretation reports, and creation of electronic medical charts. and an input device such as a mouse.
• a medical image viewing request to the image server 5 a medical image display received from the image server 5, an interpretation report viewing request to the report server 7, and an interpretation report received from the report server 7 are displayed.
• These processes are performed by the clinical WS 4 executing software programs for each process.
• the image server 5 is a general-purpose computer installed with a software program that provides the functions of a database management system (DBMS).
• DBMS database management system
• the image server 5 is connected with the image DB 6 .
• the form of connection between the image server 5 and the image DB 6 is not particularly limited, and may be a form of connection via a data bus, or a form of connection via a network such as NAS (Network Attached Storage) or SAN (Storage Area Network). It may be in the form of
• the image DB 6 is realized by storage media such as HDD (Hard Disk Drive), SSD (Solid State Drive) and flash memory.
• HDD Hard Disk Drive
• SSD Solid State Drive
• flash memory In the image DB 6, the medical images acquired by the imaging device 2 and the incidental information attached to the medical images are registered in association with each other.
• the incidental information includes, for example, 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 a subject, and a test identifying Identification information such as an examination ID for the purpose may be included.
• the incidental information may include, for example, imaging information related to imaging such as imaging method, imaging conditions, and imaging date and time regarding imaging of medical images.
• imaging method” and “imaging conditions” are, for example, the type of imaging device 2, imaging region, imaging protocol, imaging sequence, imaging technique, use/nonuse of contrast medium, slice thickness in tomography, and the like.
• the additional information may include subject information related to the subject, such as the subject's name, date of birth, age, and sex.
• the image server 5 when the image server 5 receives a registration request for a medical image from the imaging device 2 , the medical image is arranged in a database format and registered in the image DB 6 . In addition, upon receiving a viewing request from the interpretation WS3 and the medical care WS4, the image server 5 searches for medical images registered in the image DB 6, and transmits the retrieved medical images to the interpretation WS3 and the medical care WS4 that requested the viewing. do.
• 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 with the report DB 8 .
• the form of connection between the report server 7 and the report DB 8 is not particularly limited, and may be a form of connection via a data bus or a form of connection via a network such as NAS or SAN.
• the report DB 8 is realized, for example, by storage media such as HDD, SSD and flash memory. An interpretation report created in the interpretation WS3 is registered in the report DB8.
• the report server 7 when the report server 7 receives an interpretation report registration request from the interpretation WS 3 , it formats the interpretation report into a database format and registers it in the report DB 8 . In addition, when the report server 7 receives a viewing request for an interpretation report from the interpretation WS3 and the medical treatment WS4, it searches for the interpretation report registered in the report DB8, and sends the retrieved interpretation report to the interpretation WS3 and the medical treatment Send to WS4.
• the report server 7 also extracts words from observation sentences included in interpretation reports registered in the report DB 8, classifies the extracted words into predetermined items (so-called “structuring”), and stores them as structured data. (details will be described later) may be stored in the report DB 8 .
• FIG. 2 shows an example of structured data.
• the network 9 is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network).
• the imaging device 2, image interpretation WS 3, medical care WS 4, image server 5, image DB 6, report server 7, and report DB 8 included in the information processing system 1 may be located in the same medical institution, or may be located in different medical institutions. It may be placed in an institution or the like. Further, the number of each of the imaging device 2, interpretation WS 3, diagnosis WS 4, image server 5, image DB 6, report server 7 and report DB 8 is not limited to the number shown in FIG. It may consist of a single device.
• the information processing apparatus 10 has a function of retrieving past cases that are similar to the content of an observation based on a certain observation.
• a case is, for example, an interpretation report, an observation sentence, structured data (see FIG. 2), and the like recorded in the report DB 8 .
• a case is an example of the medical information of this disclosure.
• the information processing apparatus 10 is included in the interpretation WS3.
• the information processing apparatus 10 includes a CPU (Central Processing Unit) 21, a non-volatile storage section 22, and a memory 23 as a temporary storage area.
• the information processing apparatus 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 .
• a network I/F 26 is connected to the network 9 and performs wired 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 via a bus 28 such as a system bus and a control bus so that various information can be exchanged with each other.
• the storage unit 22 is realized by storage media such as HDD, SSD, and flash memory, for example.
• An information processing program 27 for the information processing apparatus 10 is stored in the storage unit 22 .
• the CPU 21 reads out the information processing program 27 from the storage unit 22 , expands it in the memory 23 , and executes the expanded information processing program 27 .
• CPU 21 is an example of a processor of the present disclosure.
• the information processing apparatus 10 includes an acquisition unit 30, an extraction unit 32, a classification unit 34, a control unit 36, and a search unit 38.
• FIG. By executing the information processing program 27 by the CPU 21 , the CPU 21 functions as an acquisition unit 30 , an extraction unit 32 , a classification unit 34 , a control unit 36 and a search unit 38 .
• the acquisition unit 30 acquires from the image server 5 at least one medical image for which an interpretation report is to be created.
• the acquisition unit 30 obtains, for example, a CT image composed of a plurality of tomographic images, and a plurality of medical images (for example, a simple CT image, a contrast-enhanced CT image, and an MRI image) with different types of imaging devices 2, imaging conditions, and imaging methods. combination), a plurality of medical images of the same subject may be acquired.
• the acquisition unit 30 may acquire supplementary information attached to the medical image.
• the acquisition unit 30 may acquire biological information acquired from the subject of the medical image for which the interpretation report is to be created.
• the biological information may be, for example, information indicating at least one of body temperature, heart rate, electrocardiogram, myoelectricity, blood pressure, arterial blood oxygen saturation (SpO2), blood sugar level, lipid level, and the like.
• the biological information is information indicating the result of at least one of various tests such as hematological tests, biochemical tests, pathological tests, immunological tests, genetic tests, bacterial tests, urinalysis tests, and infectious disease tests. There may be.
• the biometric information may be stored in advance in the storage unit 22, for example, or may be appropriately obtained from the image server 5 (image DB 6), the report server 7 (report DB 8), and other external devices (not shown). .
• a hematological test is, for example, a test that obtains test results such as white blood cell count, red blood cell count, and hemoglobin concentration.
• a biochemical test is, for example, a test that obtains various indexes related to enzymes, proteins, sugars, lipids, electrolytes, and the like as test results.
• a pathological examination is, for example, an examination that obtains, as examination results, the presence or absence and type of a lesion identified by observing cells, living tissue, and the like collected from a subject.
• An immunological test is a test that obtains, for example, results of detection of specific substances such as tumor markers, hormones, and allergies as test results.
• a genetic test is, for example, a test that obtains genetic information related to constitution and disease as test results by analyzing DNA (Deoxyribonucleic Acid).
• a bacteriological test is, for example, a test that obtains, as test results, the types and amounts of bacteria present in the body, on the surface of the body, and the like.
• a urinalysis is a test that obtains, for example, urinary sugar, urinary protein, and urinary occult blood as test results.
• the infectious disease test is, for example, a test that obtains the presence or absence of infection with various infectious diseases such as influenza infection and novel coronavirus infection as test results.
• the control unit 36 performs control to display the medical image, incidental information, and biological information acquired by the acquisition unit 30 on the display 24 .
• FIG. 5 shows an example of a screen D0 displayed on the display 24 by the controller 36.
• the screen D0 includes a medical image 62 acquired by the acquisition unit 30, imaging information 64A and subject information 64B as an example of incidental information, and sputum cytodiagnosis test results 66 as an example of biological information.
• the screen D0 also includes an observation sentence input button 90.
• the control unit 36 performs control to display the screen D1 shown in FIG.
• the screen D1 includes a text box 93 for receiving the input of the observation sentence 60.
• FIG. The control unit 36 accepts input of at least one remark 60 by the user through the text box 93 .
• a plurality of remarks may be entered in the text box 93 .
• the control unit 36 may receive selection of at least one observation sentence to be used for case retrieval from among the plurality of observation sentences.
• the control unit 36 may accept selection of a part of the observation sentences input to the text box 93 by operating the pointer 92 via the input unit 25 by the user.
• the selected remarks are shaded.
• the acquisition unit 30 acquires at least one observation sentence accepted on the screen D1.
• the acquisition unit 30 selects from among the plurality of observation sentences input in the text box 93, "A solid nodule of 25.3 mm with a spicule is found in the right lower lobe S6/10. .” is obtained.
• the extraction unit 32 extracts at least one word included in the observation sentence acquired by the acquisition unit 30 .
• FIG. 7 shows a list of words extracted from the observation text selected in FIG. As shown in FIG. 7, a word indicates information about an abnormal shadow in a medical image, for example.
• a technique for extracting words from observation sentences for example, a known named entity extraction technique using a natural language processing model such as BERT (Bidirectional Encoder Representations from Transformers) can be appropriately applied.
• BERT Bidirectional Encoder Representations from Transformers
• the extraction unit 32 preferably specifies the factuality of the extracted words.
• Factuality means the presence or absence and degree of certainty of lesions, properties, disease names, and the like. In the statement of findings, there may be cases where statements that are not certain, such as "pulmonary adenocarcinoma is suspected.” It's for.
• the classification unit 34 generates structured data of observation sentences by classifying (so-called "structuring") the words extracted by the extraction unit 32 into predetermined items. Specifically, the classification unit 34 preferably classifies words in the same manner as the items of the case structured data (see FIG. 2) recorded in the report DB 8 . As a method for classifying words, for example, a dictionary in which words that can be included in an observation sentence are classified by item is stored in advance in the storage unit 22 or the like, and the classifying unit 34 classifies the words extracted by the extracting unit 32 into Words may be classified by matching with a dictionary. Moreover, the classification unit 34 preferably normalizes the words extracted by the extraction unit 32 to generate structured data.
• Fig. 8 shows structured data obtained by classifying the words shown in Fig. 7 for each item.
• the predetermined items indicate at least one of lesions (that is, names of abnormal shadows), properties, disease names, positions, and measurement values included in the medical image, for example. be.
• a lesion is the name (type) of an abnormal shadow included in a medical image, such as "nodule”, “ground glass shadow”, and “cyst".
• the properties include absorption values such as “solid type” and “frosted glass type”, “clear/unclear”, “smooth/irregular”, “spicular”, “lobed” and “serrated”. , and general shapes such as 'nearly circular' and 'irregular'.
• the relationship with the surrounding tissue such as “pleural contact” and “pleural indentation”, the presence or absence of contrast enhancement, washout, and the like.
• a disease name is, for example, a disease name such as “cancer” or “inflammation”, and evaluation results such as “negative/positive”, “benign/malignant”, and “mild/severe” regarding the disease name and characteristics.
• a position is, for example, an anatomical position, a position in a medical image, and a relative positional relationship with other regions of interest such as “inside”, “marginal” and “surrounding”.
• Anatomical location may be represented by the names of organs and tissues such as “lung” and “liver”, and the lung may be referred to as “right lung", “upper lobe” and apical segment ("S1"). It may be represented by a subdivided expression such as
• a measured value is a value that can be quantitatively measured from a medical image. distance and the like. Also, the measured value may be represented by qualitative expressions such as “large/small” and “large/small”.
• the classification unit 34 may generate structured data by providing an item of factuality. Items to be included in the structured data are not limited to the above items, and other items may be added as appropriate. For example, as shown in FIGS. 2 and 8, the classification unit 34 may generate structured data by providing items indicating treatment details for lesions included in the structured data.
• the control unit 36 performs control to display the words classified by the classification unit 34 on the display 24 for each item.
• FIG. 9 shows an example of a screen D2 displayed on the display 24 by the controller 36. As shown in FIG. Based on the structured data of FIG. 8, words are classified and displayed on the screen D2 into items of position, lesion, property, and size (measurement value).
• the control unit 36 accepts selection of at least one word (hereinafter referred to as a “search word”) used for case search by the search unit 38. good.
• the control unit 36 may perform control to display on the display 24 an operation unit that accepts selection of at least one search word used to search for a case, in association with the word extracted from the finding sentence.
• the operation unit is a part that can be arbitrarily operated by the user on the screen displayed on the display 24, and is, for example, a GUI (Graphical User Interface) component.
• a check box 94 as an example of an operation unit is arranged for each word so that the user can select which word to use for searching.
• the control unit 36 may accept designation of a numerical range that is regarded as similar to the observation sentence acquired by the acquisition unit 30 (that is, included in the search result).
• Screen D2 displays a slider bar 96 for designating the range of nodule sizes to be included in the case search results.
• Two sliders 96A indicating the upper and lower limits of the numerical range and an icon 96B indicating the position of the search word "25.3 (mm)" extracted from the observation text are displayed on the slider bar 96. .
• the user specifies the range of nodule sizes to be included in the case search results by operating the slider 96A. In the example of FIG. 9, the range is specified so that the lower limit is "15.0 (mm)" and the upper limit is "30.0 (mm)".
• the screen D2 also includes a search start button 98.
• the search unit 38 selects a finding sentence similar to the content of the observation acquired by the acquisition unit 30 among the plurality of cases recorded in the report DB 8. Search for cases based on search terms.
• the search unit 38 refers to structured data recorded in the report DB 8 to search for cases containing the search word.
• Screen D2 also displays, as a search option, a check box 94 for selecting whether to perform a search including synonyms and related words.
• the search unit 38 may search for cases based on at least one of synonyms and related words predetermined for each search word. That is, the search unit 38 may search for cases based on synonyms and/or related terms of the search word in addition to or instead of the search word.
• Synonyms are words that differ in form but have the same or similar meaning. For example, in the case of "spicula”, they include “spicula”, “spinous process” and "fluff-like". A related word is another word that relatively often appears together with a certain word in an observation sentence. Synonyms and related words for each word may be stored in the storage unit 22 or the like in advance, for example.
• the retrieval unit 38 may retrieve cases based on synonyms. Furthermore, the search unit 38 may search for cases based on related terms when the number of cases retrieved based on synonyms does not meet a predetermined threshold. For example, each threshold may be stored in the storage unit 22 in advance, or may be arbitrarily set by the user.
• the search unit 38 may identify, as related terms, a plurality of words whose degree of co-occurrence is equal to or greater than a predetermined threshold based on a plurality of cases registered in the report DB 8. . For example, the search unit 38 determines that the number and/or ratio of finding sentences containing "adenocarcinoma" among a plurality of finding sentences containing "spicula” registered in the report DB 8 is equal to or greater than a threshold. In some cases, "spicula" and "adenocarcinoma" may be identified as related terms.
• the search unit 38 searches for cases based on factuality, regardless of whether search words, synonyms, or related words are used. This is because it is conceivable that cases with different factualities may not be similar in content even if the search words, synonyms, and related words match in form.
• the search unit 38 preferably derives the degree of similarity between the content of the finding sentence (that is, the search word) and the case.
• the search unit 38 may derive a degree of similarity according to how many search words are included in each piece of structured data recorded in the report DB 8 .
• the search unit 38 derives a degree of similarity according to how many search words are included in each item of the structured data, and calculates the average value of the degrees of similarity of all items as a comprehensive degree of similarity. can be derived.
• the control unit 36 performs control to display the cases retrieved by the retrieval unit 38 and the degree of similarity derived by the retrieval unit 38 on the display 24 .
• FIG. 10 shows an example of a screen D3 displayed on the display 24 by the controller 36. As shown in FIG. The screen D ⁇ b>3 includes the finding sentence 60 used for the search and the cases (finding sentences) found by the searching unit 38 that are similar to the finding sentence 60 . Further, the degree of similarity with the finding sentence 60 is displayed for each case (finding sentence).
• control unit 36 may perform control to display on the display 24 at least one of the medical image, incidental information, and biological information related to the finding text searched by the search unit 38 .
• FIG. 11 shows an example of screens D3 and D3P displayed on the display 24 by the controller 36. As shown in FIG. The screen D3P displays No. in the screen D3. This is a pop-up screen displayed when one case (observation sentence) is selected. No. is displayed on the screen D3P. A medical image 62 related to one case (finding statement) and subject information 64B as an example of incidental information attached to the medical image are displayed.
• FIG. 12 the information processing shown in FIG. 12 is executed by the CPU 21 executing the information processing program 27.
• FIG. Information processing is executed, for example, when a user gives an instruction to start execution via the input unit 25 .
• the acquisition unit 30 acquires at least one observation sentence.
• the remarks may be those input by the user via the input unit 25, or may be part of the remarks selected.
• the extraction unit 32 extracts at least one word included in the observation sentence obtained at step S10.
• the classification unit 34 classifies the words extracted in step S12 into predetermined items.
• step S16 the control unit 36 performs control to display the words classified in step S14 on the display 24 for each item.
• step S18 the control unit 36 accepts selection of at least one word used for case search from among the words displayed on the display 24 in step S16.
• step S20 the search unit 38 searches for cases similar to the content of the observation statement acquired in step S10 from among the plurality of cases recorded in the report DB 8, based on the words selected in step S18. .
• step S22 the search unit 38 determines whether or not the number of cases searched in step S20 is equal to or greater than a predetermined threshold. If the number of cases is less than the threshold (that is, negative determination is made in step S22), the process proceeds to step S24, and the search unit 38 searches again for cases based on synonyms of the word selected in step S18.
• step S26 the search unit 38 determines whether or not the number of cases searched in step S24 is equal to or greater than a predetermined threshold. If the number of cases is less than the threshold (that is, negative determination is made in step S26), the process proceeds to step S28, and the search unit 38 searches again for cases based on related terms of the word selected in step S18.
• step S30 the control unit 36 performs control to display the cases retrieved in steps S20, S24 and/or S28 on the display 24, and ends this information processing.
• the information processing device 10 includes at least one processor, and the processor extracts at least one word included in the observation sentence, classifies the word into a predetermined item, The words are classified, the words are displayed on the display for each item, and medical information similar to the contents of the observation statement is retrieved based on the words from among the plurality of recorded medical information.
• a case can be searched based on the finding sentence.
• the content of the observation sentences and search words can be easily confirmed. Therefore, for example, it is possible to omit the trouble of inputting search words and setting search conditions, and it is possible to easily search for cases.
• the finding text used for searching may be, for example, an finding text included in an interpretation report already recorded in the report DB 8, the storage unit 22, or the like. Alternatively, for example, it may be a finding sentence generated by machine learning based on the medical image acquired by the acquiring unit 30 .
• a method of generating an observation sentence by machine learning for example, a method using a recurrent neural network described in Japanese Patent Application Laid-Open No. 2019-153250 can be appropriately applied.
• control unit 36 causes the display 24 to display lesion detection results and/or diagnosis results obtained by analyzing medical images using a known CAD technique, so that the user can refer to the detection results and/or diagnosis results. Assistance may be provided for inputting observations in the
• a case is, for example, medical information indicating at least one of a medical image, an observation statement about the medical image, subject information about the subject of the medical image, and biological information obtained from the subject. good.
• the case may be a medical image recorded in the image DB 6, additional information (object information and imaging information) of the medical image, and the like.
• biometric information recorded in the storage unit 22, the image DB 6, the report DB 8, and other external devices may be used.
• control unit 36 may control the display 24 to display various types of medical information such as structured data, medical images, subject information, and biological information as case search results.
• the search unit 38 may search cases and derive similarities based on image feature amounts of medical images.
• the search unit 38 may search medical images recorded in the image DB 6 for medical images that include the image feature amount indicated by the search word.
• the image feature amount may be derived, for example, using a learning model such as a CNN (Convolutional Neural Network) trained in advance so that the input is the medical image and the output is the image feature amount of the medical image.
• CNN Convolutional Neural Network
• a search is first performed using a search word described in an observation sentence, then a synonym thereof, and then a related word is used to perform a search.
• a search word described in an observation sentence is not limited to For example, when "synonyms included” and/or "related terms included” are selected on screen D2 of FIG. 9, synonyms and/or related terms may be unconditionally used for retrieval. .
• a mode of performing a search based on an observation sentence selected from a plurality of observation sentences has been described, but the present invention is not limited to this. For example, if a sufficient number of cases cannot be found by searching based on the selected observations, search using words contained in other observations that have not been selected, as well as their synonyms and related terms. may be performed. For example, in the case of FIG. 6, a case may be retrieved based on the unselected observation statement "A tumor with a diameter of 4 cm is found in the right inner deep neck region.”
• the extraction unit 32 extracts a plurality of finding sentences At least one word included in other observation sentences related to the observation sentence selected from among may be extracted.
• the classification unit 34 may classify the words extracted by the extraction unit 32 into predetermined items.
• the search unit 38 may search for medical information based on words extracted from other observation sentences.
• the search unit 38 searches for cases based on predetermined weights for each item such as lesion, property, position, and measurement value. good too.
• the weight of the n-th item is wn and the degree of similarity between the search word and the case in the n-th item is sn
• the overall degree of similarity x may be used to search for cases.
• the weight for each item may be set in advance and stored in the storage unit 22, or may be set by the user.
• FIG. 13 shows an example of a screen D4 displayed on the display 24 by the control unit 36 for receiving weight setting.
• a slider bar 99 for setting a weight is displayed for each item. The user sets the weight of each item by operating the slider 99A on the slider bar 99.
• the hardware structure of a processing unit that executes various processes can use a variety of processors, including:
• the various processors include, in addition to the CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, circuits such as FPGAs (Field Programmable Gate Arrays), etc.
• Programmable Logic Device PLD which is a processor whose configuration can be changed, ASIC (Application Specific Integrated Circuit) etc. Circuits, etc. are included.
• One processing unit may be composed of one of these various processors, or a combination of two or more processors of the same or different type (for example, a combination of a plurality of FPGAs, or a combination of a CPU and an FPGA). combination). Also, a plurality of processing units may be configured by one processor.
• a single processor is configured by combining one or more CPUs and software.
• a processor functions as multiple processing units.
• SoC System on Chip
• a processor that realizes the function of the entire system including multiple processing units with a single IC (Integrated Circuit) chip. be.
• various processing units are configured using one or more of the above various processors as a hardware structure.
• 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), and a USB (Universal Serial Bus) memory. good.
• the information processing program 27 may be downloaded from an external device via a network.
• the technology of the present disclosure extends to a storage medium that non-temporarily stores an information processing program in addition to the information processing program.
• the technology of the present disclosure can also appropriately combine the exemplary embodiments described above.
• the above description and illustration are detailed descriptions of the parts related to the technology of the present disclosure, and are merely examples of the technology of the present disclosure.
• the above descriptions of configurations, functions, actions, and effects are descriptions of examples of the configurations, functions, actions, and effects of portions related to the technology of the present disclosure. Therefore, unnecessary parts may be deleted, new elements added, or replaced with respect to the above-described description and illustration without departing from the gist of the technology of the present disclosure. Needless to say.

Landscapes

• Engineering & Computer Science (AREA)
• Theoretical Computer Science (AREA)
• Databases & Information Systems (AREA)
• Data Mining & Analysis (AREA)
• Physics & Mathematics (AREA)
• General Engineering & Computer Science (AREA)
• General Physics & Mathematics (AREA)
• Computational Linguistics (AREA)
• Artificial Intelligence (AREA)
• Library & Information Science (AREA)
• Health & Medical Sciences (AREA)
• Epidemiology (AREA)
• General Health & Medical Sciences (AREA)
• Medical Informatics (AREA)
• Primary Health Care (AREA)
• Public Health (AREA)
• Medical Treatment And Welfare Office Work (AREA)

Priority Applications (2)

Applications Claiming Priority (2)

Related Child Applications (1)

Publications (1)

Family

ID=87578684

Family Applications (1)

Country Status (3)

Cited By (1)

Citations (4)

• 2023
  • 2023-02-17 WO PCT/JP2023/005843 patent/WO2023157956A1/ja not_active Ceased
  • 2023-02-17 JP JP2024501456A patent/JPWO2023157956A1/ja active Pending
• 2024
  • 2024-08-15 US US18/805,545 patent/US20240403342A1/en active Pending

Patent Citations (4)

Also Published As

Similar Documents

Legal Events