[go: up one dir, main page]

WO2025067273A1 - Procédé et appareil de recommandation de rapport d'image médicale, et dispositif et support de stockage - Google Patents

Procédé et appareil de recommandation de rapport d'image médicale, et dispositif et support de stockage Download PDF

Info

Publication number
WO2025067273A1
WO2025067273A1 PCT/CN2024/121217 CN2024121217W WO2025067273A1 WO 2025067273 A1 WO2025067273 A1 WO 2025067273A1 CN 2024121217 W CN2024121217 W CN 2024121217W WO 2025067273 A1 WO2025067273 A1 WO 2025067273A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
report
data
image report
graph
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2024/121217
Other languages
English (en)
Chinese (zh)
Inventor
董瑞智
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhan United Imaging Healthcare Co Ltd
Original Assignee
Wuhan United Imaging Healthcare Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Wuhan United Imaging Healthcare Co Ltd filed Critical Wuhan United Imaging Healthcare Co Ltd
Publication of WO2025067273A1 publication Critical patent/WO2025067273A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/903—Querying
    • G06F16/9035—Filtering based on additional data, e.g. user or group profiles
    • 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
    • G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
    • G06F16/367—Ontology
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90—Details of database functions independent of the retrieved data types
    • G06F16/907—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/02—Knowledge representation; Symbolic representation
    • G06N5/022—Knowledge engineering; Knowledge acquisition
    • 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
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS

Definitions

  • the present application relates to the technical field of medical image report processing, and in particular to a method, apparatus, computer equipment, storage medium and computer program product for recommending a medical image report.
  • Medical imaging reports are documents issued by doctors after patients have been examined with imaging scanning equipment, which contain images, imaging findings, and diagnostic conclusions.
  • imaging scanning equipment With the upgrading of examination equipment and the improvement of living standards, people are paying more and more attention to their physical health, and more and more people will undergo physical examinations, especially when public health emergencies occur, which generates a large number of imaging examination needs, which increases the workload of doctors in analysis and judgment and also brings great challenges.
  • a doctor may search the database for historical imaging reports similar to the current imaging report as a reference. If the retrieved historical imaging report has a low degree of similarity to the current imaging report, the doctor's report quality and work efficiency will be affected.
  • the present application provides a method for recommending a medical imaging report, comprising:
  • the image data is the data generated by the image scanning device after the image scanning device performs an image scanning on the scanned object;
  • a reference image report for the current image report is determined in the historical image report set.
  • the preset dimensions defined by the atlas ontology structure based on at least the medical consultation data and the imaging data, obtain the imaging report information atlas of the current imaging report, including:
  • an image report information map of the current image report is obtained.
  • determining the contents corresponding to the plurality of fields in the medical data and the image data to obtain the multi-tuple data of the preset dimension includes:
  • the content corresponding to the second category of fields is determined based on the content corresponding to the first category of fields
  • the multi-tuple data of the preset dimension is obtained.
  • the preset Dimensional multi-tuple data including:
  • the multi-tuple data of the preset dimension is obtained; the contents corresponding to the third category of fields are obtained by processing the scanned image obtained based on the image data.
  • the image report information graph of the current image report and the image report information graph of the historical image report are processed to obtain the similarity.
  • the image report information graph of the current image report and the image report information graph of the historical image report are processed using the graph analysis algorithm to obtain similarity, including:
  • the similarity is obtained according to the number of common nodes.
  • obtaining similarity according to the number of common nodes includes:
  • the sub-similarity of different preset dimensions is weighted to obtain the similarity.
  • the processing of the image report information map of the current image report and the image report information map of the historical image report to obtain the similarity includes:
  • the method for recommending a medical imaging report further includes:
  • the recommendation result includes a reference image report and/or user evaluation for the current image report;
  • the graph ontology structure is updated according to the feedback content.
  • updating the graph ontology structure includes:
  • the weight of each of the preset dimensions is updated.
  • the preset dimensions defined by the atlas ontology structure include at least: a patient information dimension and an image information dimension.
  • the method before determining a reference image report for the current image report in a historical image report set based on the similarity between the image report information map of the current image report and the image report information map of the historical image reports, the method further comprises:
  • the similarity is obtained according to the sub-similarity for the patient information dimension and the sub-similarity for the image information dimension.
  • the preset dimension defined by the graph ontology structure also includes a text information dimension, which corresponds to the text content seen in the image, and the entities under the image information dimension are associated with the entities under the text information dimension.
  • the image report information map of the current image report obtained based on the medical data and the image data according to the preset dimensions defined in the map ontology structure includes:
  • Content corresponding to the fields under the patient information dimension is extracted from the medical data and the image data.
  • the preset dimensions defined by the atlas ontology structure based on at least the medical consultation data and the imaging data, obtain the imaging report information atlas of the current imaging report, including:
  • the method for recommending a medical imaging report further includes:
  • the entity is normalized.
  • the standardizing the entity includes:
  • the entities are standardized according to an open source knowledge base or a knowledge graph.
  • Another aspect of the present application provides a device for recommending a reference image report, comprising:
  • a data acquisition module used to acquire the medical consultation data and image data corresponding to the current image report;
  • the image data is the data generated by the image scanning device after the image scanning device performs image scanning on the scanned object;
  • a reference report determination module is used to determine a reference image report for the current image report in a historical image report set based on the similarity between the image report information map of the current image report and the image report information map of the historical image reports.
  • the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the method for recommending a medical imaging report in any of the above embodiments.
  • the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for recommending a medical imaging report in any of the above embodiments is implemented.
  • the present application provides a computer program product having a computer program stored thereon, and when the computer program is executed by a processor, the method for recommending a medical imaging report in any of the above embodiments is implemented.
  • FIG1 is a diagram of an application environment of a method for recommending medical image reports in one embodiment
  • FIG2 is a schematic diagram of a graph body structure in one embodiment
  • FIG3 is a flow chart of a method for recommending a medical imaging report in another embodiment
  • FIG4 is a structural block diagram of a device for recommending medical image reports in one embodiment
  • FIG. 5 is a diagram showing the internal structure of a computer device in one embodiment.
  • the medical imaging report recommendation method provided in the present application may be executed by a computer device.
  • a recommendation switch may be provided to users such as doctors.
  • similar medical imaging reports may be recommended to the doctors or other users according to the method provided in the present application.
  • similar medical imaging reports may not be recommended to the doctors or other users.
  • Step S101 obtaining the medical consultation data and imaging data corresponding to the current imaging report.
  • the current image report may be an image report corresponding to the reference image report to be retrieved.
  • the current image report may include the diagnostic text content of the image findings written by the doctor. In this case, the current image report is a completed image report.
  • the current image report may not include the above-mentioned diagnostic text content of the image findings, or the included diagnostic text content of the image findings is not completed by the doctor. In this case, the current image report is an unfinished image report.
  • the medical data mainly includes the information of the scanned object, such as age, gender and other information; the medical data can be obtained before the image scanning device scans the scanned object; the image data is the data generated by the image scanning device after the image scanning device performs an image scanning on the scanned object.
  • the image scanning device can first obtain the medical data of the scanned object, and then perform an image scanning on the scanned object, thereby outputting the data generated by the device.
  • the data generated by the device can be in dicom (Digital Imaging and Communications in Medicine) format, and the data generated by the device can include medical data and image data.
  • the computer device can parse the above-mentioned medical data and image data from the device-generated data output by the image scanning device.
  • Step S102 according to the preset dimensions defined in the atlas ontology structure, an imaging report information atlas of the current imaging report is obtained based on at least the medical consultation data and the imaging data.
  • the graph ontology structure may include, for example, fields under preset dimensions and the contents of the fields.
  • this application constructs an imaging report information map for imaging reports (including the current imaging report and historical imaging reports), and retrieves historical imaging reports similar to the current imaging report based on the comparison of the imaging report information map.
  • the scanned object of the current imaging report is A
  • the scanned object of the historical imaging report is B
  • the features of the scanned objects A and B in other dimensions other than the imaging information dimension are similar (such as age, gender, height, weight, etc.)
  • the relevant information of other dimensions other than the imaging information dimension is generally in the medical data.
  • the graph ontology structure defined in this application may include, for example, the patient information dimension and the imaging information dimension; among them, the medical information dimension of the patient is similar to the image information dimension of the patient.
  • the human information dimension includes multiple entities, each entity includes one or more fields, and the content of the fields of each entity can be derived from medical data.
  • the image information dimension includes multiple entities, and the content of the fields of each entity can be derived from image data.
  • the device-generated data is parsed to extract the corresponding content from the medical data and image data.
  • the computer device can search for the patient information tag in the device-generated data in the dicom format, locate the patient information data area, obtain the patient data, use the pre-designed patient information processor to process the patient data, and extract the content corresponding to the fields under the patient information dimension in the atlas ontology structure, such as gender, age, etc.
  • the patient information processor here refers to a software module for analyzing and processing patient data.
  • the computer device can search for the image information tag in the device-generated data in the dicom format to obtain the image data, and obtain the scanned image based on the image data constituting the image in the image data; identify the key areas (such as the lesion area) in the scanned image based on the pre-built deep neural network model.
  • the computer device can use a pre-designed image information processor to process the image data, and extract the content in the image data corresponding to the fields under the image information dimension in the atlas ontology structure, such as the dimensions of the examination organ, examination location, lesion location, and lesion size.
  • the image information processor here refers to a software module that analyzes and processes the image data.
  • the computer device After the computer device extracts the corresponding content from the medical data and the imaging data, it fills each content into the node of the field according to the graph ontology structure to form an imaging report information graph of the current imaging report.
  • Step S103 determining a reference image report for the current image report in the historical image report set based on the similarity between the image report information map of the current image report and the image report information map of the historical image report.
  • the image report information map of historical image reports may be constructed in the same manner as the above-described method for forming the current image report information map.
  • the computer device After obtaining the image report information map of the current image report and the image report information map of the historical image reports, the computer device compares the similarity between the image report information map of the current image report and the image report information map of the historical image reports, and uses the historical image reports whose similarity is greater than a threshold or whose similarity ranks in the top N as reference image reports for the current image report and recommends them to the doctor.
  • the image report of the current image report can be compared with some historical image reports in the historical image report set in terms of information maps, and can also be compared with all historical image reports in the historical image report set in terms of information maps.
  • an imaging report information map of the current imaging report is generated based on at least two aspects of the medical data and the imaging data, and the imaging report information map of the historical imaging report is also constructed based on at least two aspects of the medical data and the imaging data.
  • a similarity comparison is performed based on the constructed imaging report information map, thereby retrieving historical imaging reports that are relatively similar to the current imaging report in at least two aspects of the medical data and the imaging data, and recommending them to doctors as a reference, thereby improving the quality of doctors' imaging reports and work efficiency.
  • step S102 obtains an imaging report information graph of the current imaging report based on at least medical data and imaging data according to the preset dimensions defined in the atlas ontology structure, including: obtaining a number of fields under the preset dimensions defined in the atlas ontology structure; determining the contents corresponding to a number of fields in the medical data and imaging data to obtain multi-tuple data of the preset dimensions; and obtaining the imaging report information graph of the current imaging report based on the multi-tuple data of the preset dimensions.
  • the historical imaging report has a certain reference role for the current imaging report, in addition to paying attention to the condition of the lesion itself, you can also pay attention to other conditions of the scanned object besides the lesion, such as age, gender, height, weight, etc.
  • the scanned object in the current image report is A
  • the scanned object in the historical image report is B
  • the features of the scanned objects A and B are similar in the image information dimension, and the features of the scanned objects A and B in other dimensions except the image information dimension are similar (for example If the historical image report of the scanned object B has certain reference value for the current image report of the scanned object A, then the historical image report of the scanned object B has certain reference value for the current image report of the scanned object A.
  • the preset dimensions defined by the atlas ontology structure may include the patient information dimension and the image information dimension.
  • the patient information dimension corresponds to other conditions of the scanned object except the lesion, and is mainly used to determine whether the features of other dimensions except the image information dimension are similar between the scanned objects;
  • the image information dimension corresponds to the condition of the lesion itself, and is mainly used to determine whether the features of the scanned objects in the image information dimension are similar.
  • the constructed imaging report information atlas of the current imaging report and the imaging report information atlas of the historical imaging reports include the above-mentioned two dimensions, thereby retrieving historical imaging reports with similar conditions other than the lesion and similar conditions to the lesion itself, which has a certain reference role for the current imaging report.
  • the preset fields under the patient information dimension such as age, gender, weight, etc.
  • the information of the same scanned object under the patient information dimension is mostly consistent within a certain period of time. Defining the patient information dimension in the graph ontology structure makes it more likely to find the historical imaging report of the same scanned object. The doctor can check the current image based on the historical imaging report of the scanned object, compare whether the situation has improved, and form a corresponding diagnosis conclusion.
  • Several fields under the patient information dimension may include gender, age, age group, weight, etc.
  • several fields under the image information dimension may include examination organ, examination location, lesion location, lesion size, lesion morphology, etc.
  • the computer device may process the patient data using the patient information processor, extract the contents of several fields under the patient information dimension, and represent them in the multi-tuple format of ⁇ patient, gender, age, ...>, thereby obtaining multi-tuple data of the patient information dimension.
  • the computer device may also process the image data using the deep neural network model and the image information processor, extract the contents of several fields under the image information dimension, and represent them in the multi-tuple format of ⁇ lesion, examination organ, examination location, lesion location, lesion size, ...>, thereby obtaining multi-tuple data of the image information dimension.
  • the computer device fills the multi-group data of the patient information dimension and the multi-group data of the imaging information dimension into the nodes of the fields under the corresponding dimensions according to the graph ontology structure, and obtains the imaging report information graph of the current imaging report.
  • the content corresponding to the field is extracted from the medical data and imaging data, it is represented in a multi-tuple format of a preset dimension, so that the corresponding content can be accurately filled into the node of the field under the corresponding dimension, thereby improving the accuracy of graph construction.
  • the contents corresponding to several fields in the medical data and the imaging data are determined to obtain multi-tuple data of preset dimensions, including: parsing the medical data and the imaging data to obtain the contents corresponding to the first category of fields; determining the contents corresponding to the second category of fields according to the contents corresponding to the first category of fields according to preset knowledge data expansion rules; and obtaining multi-tuple data of preset dimensions based on the contents corresponding to the first category of fields and the contents corresponding to the second category of fields.
  • Each preset dimension includes multiple fields, among which the content of some fields can be directly obtained by parsing the medical data and imaging data, and these fields can be called first-category fields; the content of some fields can be obtained by combining the preset knowledge data expansion rules and the content of the first-category fields, and these fields can be called second-category fields.
  • first-category fields the content of this field can be directly parsed from the medical data, so the "age” field belongs to the first-category field
  • the "age group” field under the patient information dimension the content of this field needs to be combined with the preset knowledge data expansion rules and the content of the "age” field, so the "age group” field belongs to the second-category field.
  • each second-category field, as well as the preset knowledge data expansion rules and the content of the first-category fields used to determine the content of the second-category fields are shown in Table 1.
  • the above embodiment combines preset knowledge data expansion rules to expand the knowledge data of the atlas to avoid missing historical imaging reports that can be used for reference.
  • obtaining multi-tuple data of a preset dimension according to the content corresponding to the first type of field and the content corresponding to the second type of field includes:
  • the contents corresponding to the first category of fields the contents corresponding to the second category of fields and the contents corresponding to the third category of fields, multi-tuple data of preset dimensions are obtained; the contents corresponding to the third category of fields are obtained by processing the scanned images obtained based on the image data.
  • third-category fields such as the "lesion area" field under the image information dimension.
  • the computer device After obtaining the image data, the computer device obtains a scanned image, inputs the scanned image into the deep neural network model, obtains the content of the third category field, and obtains multi-tuple data of preset dimensions according to the content corresponding to the first category field, the content corresponding to the second category field, and the content of the third category field.
  • the above-mentioned embodiment further expands the knowledge of the atlas based on the content of the third type of field obtained by processing the scanned image, enriches the atlas knowledge, and further avoids missing historical image reports that can be used for reference.
  • the method provided by the present application also includes: obtaining entities in the graph ontology structure; and standardizing the entities.
  • the entities are standardized, including: standardizing the entities according to an open source knowledge base or a knowledge graph.
  • open source knowledge bases such as ICD-10 (International Classification of Diseases maintained by the World Health Organization), UMLS (the integrated medical language system of a national medical library), SNOMED-CT (systematic clinical medical terminology maintained by the International Organization for the Development of Medical Terminology Standards), etc., as well as the Chinese Symptom Library (published by a university on the OpneKG website) and CMeKG (Chinese Medical Knowledge Graph) further expanded on the basis of these open source knowledge bases to obtain knowledge graphs.
  • ICD-10 International Classification of Diseases maintained by the World Health Organization
  • UMLS the integrated medical language system of a national medical library
  • SNOMED-CT systematic clinical medical terminology maintained by the International Organization for the Development of Medical Terminology Standards
  • Chinese Symptom Library published by a university on the OpneKG website
  • CMeKG Choinese Medical Knowledge Graph
  • entities can be represented in a standardized manner, and some additional knowledge, such as clinical symptoms, diagnosis and treatment techniques, can be added to complete the missing entity relationship data and increase the strength of the association between entities.
  • the method provided by the present application also includes: using a graph analysis algorithm to process the image report information map of the current image report and the image report information map of the historical image reports to obtain the similarity.
  • the graph analysis algorithm may include algorithms such as simRank and random walk. Through the graph analysis algorithm, the similarity between the image report information graph of the current image report and the image report information graph of the historical image report may be obtained.
  • the image report information map of the current image report and the image report information map of the historical image report are processed to obtain similarity, further including: obtaining multiple current image map nodes of the image report information map of the current image report and multiple historical image map nodes of the image report information map of the historical image report; based on the graph analysis algorithm, determining the common nodes among the multiple current image map nodes and each historical image map node to obtain the number of common nodes; and obtaining the similarity based on the number of common nodes.
  • the image report information map of the current image report includes multiple current image map nodes, each node has corresponding fields and content; the image report information map of the historical image report includes multiple historical image map nodes, each node has corresponding fields and content.
  • the two nodes are the same and are common nodes of the image report information map of the current image report (hereinafter referred to as the current map) and the image report information map of the historical image report (hereinafter referred to as the historical map).
  • the computer device can use the graph analysis algorithm to obtain the common nodes of the current graph and the historical graph, and obtain the number of common nodes; illustratively, the computer device can also obtain the number of nodes contained in the current graph, and refer to this number of nodes as the first number of nodes, and obtain the number of nodes of the historical graph, and refer to this number of nodes as the second number of nodes.
  • the computer device After adding the first number of nodes to the second number of nodes, subtract the number of common nodes to obtain the number of nodes of the union of the current graph and the historical graph; the computer device can use the number of common nodes as the number of nodes of the intersection of the current graph and the historical graph, and divide the number of nodes of the intersection by the number of nodes of the union to obtain the similarity between the current graph and the historical graph.
  • the historical atlases can be sorted in descending order of similarity, and the historical imaging reports of the top K historical atlases can be used as reference imaging reports and recommended to doctors. Doctors can browse the reference imaging reports and compare them with the current imaging reports being processed, and use the imaging findings and diagnostic conclusions of the reference imaging reports as a reference, thereby improving the processing efficiency of imaging reports.
  • similarity is obtained based on the number of common nodes, including: obtaining sub-similarity of different preset dimensions based on the number of common nodes under different preset dimensions; and performing weighted processing on the sub-similarity of different preset dimensions based on the weight of each preset dimension to obtain similarity.
  • the similarity between the current graph and the historical graph in the preset dimension D can be called sub-similarity, which can be recorded as sub_similar_score(R 1 ,D,R 2 ), where R 1 and R 2 represent the current graph and the historical graph respectively.
  • the numerator in the formula represents the number of common nodes between the current graph and the historical graph under the preset dimension D, that is, the number of intersection nodes
  • the denominator in the formula represents the number of union nodes between the current graph and the historical graph under the preset dimension D.
  • the computer device can obtain the sub-similarity of the current graph and the historical graph in each preset dimension.
  • each preset dimension [ ⁇ 1 , ⁇ 2 ... ⁇ n ]
  • the sub-similarity of each preset dimension is weighted and summed to obtain the similarity between the current graph and the historical graph.
  • the formula is as follows: The subscript of the weight indicates the preset dimension corresponding to the weight.
  • the method provided in the present application also includes: obtaining user feedback on the recommendation results; the recommendation results include reference image reports and/or user evaluations for the current image report; and based on the feedback content, updating the image information graph ontology structure, such as preset dimensions, fields or weights.
  • the recommended similar historical imaging reports belong to the reports of "age group: 20-25 years old, gender: female, examined organ: lung, lesion location: left lung lobe, lesion size: 0.25-0.3 cm nodule".
  • These historical imaging reports may be more referenceable than the historical imaging report of "age group: 40-45 years old, gender: male, examined organ: lung, lesion location: right lung lobe, lesion size: 0.1-0.15 cm nodule”.
  • doctors can score the recommendation results, which can include the text content of the evaluation, to strengthen the model to output more accurate results.
  • the specific operation can be divided into the following steps: obtain the doctor's feedback on the recommendation results, which can include the score and text content, filter the feedback content according to the pre-defined filtering model, and retain the feedback content with a validity higher than the threshold; wherein the filtering model can be a classification model trained by annotating a certain amount of feedback content. Then, based on the feedback content with a validity higher than the threshold, update the weights used for the graph or similarity calculation.
  • the weight used for similarity calculation is increased to improve the association strength of the graph between corresponding entities.
  • the text content of the doctor's evaluation is "This result is very good, especially the age group, which is very consistent.” It can be seen that this is a positive feedback, and the age group is a key field, so the weight of the field corresponding to the preset dimension is increased. If it is negative feedback, on the one hand, the weight used for similarity calculation can be reduced to weaken the association strength of the graph between corresponding entities.
  • the text content of the doctor's evaluation is "These reports are concentrated between 20 and 25 years old, the range is too small.” It can be seen that this is a negative feedback, and the age group is a key field, so the weight of the field corresponding to the preset dimension is reduced. On the other hand, according to the above text content, it can be seen that the doctor thinks that the age group range is too small, so the value range of the age group can be increased in the process of constructing the graph.
  • weights can be set for fields under each dimension.
  • the similarity is calculated based on the common nodes and the corresponding weights.
  • the weight of a specified field can be changed based on the doctor's evaluation content.
  • the result recommendation and graph optimization can be adapted to different users, that is, to achieve personalized recommendation effects.
  • the above-mentioned weight update operation or the expansion of the value range of the patient's age group is performed on the user side, without modifying the underlying complete graph.
  • the backend monitors the feedback content in real time.
  • the entire complete graph ontology structure can be further considered for update. For example, whether the value range of the "age field" should be narrowed or expanded. For example, remove fields that have no reference value, or add new fields.
  • an image report information graph of a current image report and an image report information graph of a historical image report are processed to obtain similarity, including determining preset dimensions and/or fields involved in similarity calculation from a graph ontology structure.
  • the preset dimensions and/or fields involved in the similarity calculation can be determined based on the doctor's choice, for example, to improve the efficiency of subsequent similarity calculations and historical imaging report recommendations. For example, from a specific atlas ontology structure, the doctor selects preset dimensions and/or fields with strong correlation based on the patient's condition to perform atlas comparison, and filters out preset dimensions and/or fields with weak correlation and low reference value. It is understandable that in other embodiments, the preset dimensions and/or fields involved in the comparison can be automatically determined based on the patient information without manual selection. Based on the determined preset dimensions and/or fields involved in the similarity comparison, the similarity calculation method introduced above is used to perform similarity calculation.
  • the preset dimensions defined in the atlas ontology structure include at least: patient information dimension, image information dimension, and text information dimension; entities under the image information dimension are associated with entities under the text information dimension.
  • the atlas ontology structure includes the patient information dimension, the image information dimension and the text information dimension;
  • the patient information dimension includes multiple preset fields: “gender”, “age” and “age group”, etc.;
  • the image information dimension includes the preset field “lesion”, and "lesion” includes multiple sub-preset fields: “examination organ”, “examination location”, “lesion location”, “lesion size” and “lesion morphology”, etc.
  • the text information dimension corresponds to the text content of the image written by the doctor, and the entities under the text information dimension have the association relationship shown in FIG2 with the entities under the image information dimension.
  • the method provided by the present application further includes: modifying the content of each field obtained based on the image data based on the text content seen in the image. For example, for the same field, when the content obtained based on the image data is inconsistent with the content determined by the text content seen in the image written by the doctor, the content determined by the text content seen in the image is used as the content of the field.
  • the method provided in the present application also includes: performing a similarity comparison on the contents of each preset field of the image report information map of the current image report and the image report information map of the historical image report under the patient information dimension to obtain a sub-similarity for the patient information dimension; performing a similarity comparison on the contents of each preset field of the image report information map of the current image report and the image report information map of the historical image report under the image information dimension to obtain a sub-similarity for the image information dimension; obtaining similarity based on the sub-similarity for the patient information dimension and the sub-similarity for the image information dimension.
  • the image report information map of the current image report is referred to as the current map for short; the image report information map of the historical image report is referred to as the historical map for short.
  • the sub-similarity between the current graph and the historical graph in the patient information dimension it can be done in the manner described in the above embodiment. Specifically, the number of intersection nodes and the number of union nodes of the current graph and the historical graph in the patient information dimension can be calculated, and the number of intersection nodes can be divided by the number of union nodes to obtain the sub-similarity of the patient information dimension.
  • the sub-similarity between the current graph and the historical graph in the image information dimension it can be done in the manner described in the above embodiment. Specifically, the number of intersection nodes and the number of union nodes of the current graph and the historical graph in the image information dimension can be calculated, and the number of intersection nodes can be divided by the number of union nodes to obtain the sub-similarity in the image information dimension.
  • the two sub-similarity can be weighted and summed according to the weight of the patient information dimension and the weight of the image information dimension to obtain the similarity between the current map and the historical map.
  • the constructed imaging report information graph also includes the contents corresponding to several preset fields of the text information dimension.
  • the computer device can use a pre-designed text information processor to perform entity recognition on the diagnostic text of imaging findings, and fill the recognized entities into the nodes of the corresponding fields according to the graph ontology structure to obtain imaging report information containing the text information dimension.
  • the text information processor here refers to a software module that analyzes and processes the diagnostic text seen in the image.
  • the sub-similarity of the current graph and the historical graph in the text information dimension can also be calculated.
  • the calculation process can be performed in the manner described in the above embodiment, that is, the image report information graph of the current image report and the image report information graph of the historical image report under the text information dimension are compared for similarity to obtain the sub-similarity for the text information dimension.
  • the number of intersection nodes and the number of union nodes of the current graph and the historical graph in the text information dimension can be calculated, and the number of intersection nodes is divided by the number of union nodes to obtain the sub-similarity of the text information dimension.
  • the three sub-similarity can be weighted and summed according to the weight of the text information dimension, the weight of the patient information dimension, and the weight of the image information dimension to obtain the similarity between the current graph and the historical graph.
  • the medical data and imaging data are extracted by the device generating data in DICOM format, and the imaging report information map is constructed based on the medical data, imaging data and the diagnostic text of the imaging findings written by the doctor.
  • this application example also combines customizable preset knowledge data expansion rules and open source knowledge base to expand the knowledge of the imaging report information map; based on the constructed imaging report information map, a graph analysis algorithm is used to retrieve similar imaging reports and output them.
  • Step S301 define the graph ontology structure.
  • Step S302 obtaining the medical consultation data, imaging data and diagnostic text of imaging findings written by the doctor of multiple imaging reports.
  • Step S303 using different processors to process the medical data, imaging data, and diagnostic text of imaging findings respectively, obtain multi-tuple data of each preset dimension according to the defined graph ontology structure, and store them in the graph database to generate an imaging report information graph.
  • the image report information map can be a virtual structure that reflects the organization and logic of data.
  • the content in the image report information map can be stored in the same way as data storage in a general database, such as a MySQL database.
  • Step S304 combining the preset knowledge data expansion rules and the open source knowledge base, performs data standardization and knowledge expansion on the imaging report information map.
  • step S304 the information dimension of the image report can be enriched and the quality of the atlas can be improved.
  • Step S305 obtain the information of the target image report, use the graph analysis algorithm to search and output similar reports in the image report information graph from multiple dimensions.
  • This application example can be divided into three parts: the first part is mainly to generate an imaging report information map, the second part is mainly to expand the knowledge of the imaging report information map, and the third part is mainly to recommend similar imaging reports.
  • Part 1 Generate an image report information map:
  • This application example constructs a graph ontology structure based on actual business needs and data granularity, as shown in Figure 2.
  • the ontology structure can be divided into three preset dimensions: patient information dimension, imaging information dimension, and text information dimension.
  • the fields under the patient information dimension include gender, age, age group, etc.
  • the fields under the imaging information dimension include examination organs, examination locations, lesion locations, lesion sizes, etc.
  • the fields under the text information dimension include examination organs, examination locations, lesion locations, lesion sizes, etc.; among them, the entities under the text information are associated with the entities under the imaging information dimension.
  • Get relevant data such as device-generated data in DICOM format and doctor-written diagnostic text of imaging findings.
  • the data is parsed according to the DICOM protocol.
  • the patient information tag is searched, and the patient information data area is located to obtain the patient data.
  • the patient information processor designed in advance is used to process the patient data, extract the patient's gender, age and other fields, and represent them in the ⁇ patient, gender, age, ...> multi-tuple format to obtain the multi-tuple data of the patient information dimension.
  • the data is parsed, and the image information label is searched in the device-generated data to obtain the image data; a deep neural network model is constructed, and the deep neural network model is trained using the scanned image to identify key areas (such as lesion areas) in the scanned image.
  • the image data is processed using a pre-designed image information processor, and the fields such as the examination organ, examination position, lesion location, and lesion size in the image data are extracted and represented in the ⁇ lesion, examination organ, examination position, lesion location, lesion size, ...> multi-tuple format.
  • a pre-designed text information processor is used to process the diagnostic text of imaging findings, extract fields such as examination organs, examination positions, lesion positions, lesion sizes, etc. in the diagnostic text of imaging findings, and represent them in the multi-tuple format of ⁇ text information, examination organs, examination positions, lesion positions, lesion sizes, ...> to obtain multi-tuple data of text information dimension.
  • the text information processor can be an entity recognition model, such as CRF (Conditional Random Fields), BiLSTM (Bi-directional Long Short-Term Memory) + CRF, BERT (Bidirectional Encoder Representations from Transformer, bidirectional encoder representation model in Transformer) + CRF and other models. There is no restriction here.
  • Some diagnostic text of imaging findings is collected, and the diagnostic text of imaging findings is analyzed.
  • the key fields in the text are annotated by entities.
  • the "posterior segment of the left upper lung apex" in the text "Multiple fibrous cords and patchy high-density shadows can be seen in the posterior segment of the left upper lung apex, and point-like calcifications are distributed inside with clear boundaries” is annotated as “lesion location”
  • multiple fibrous cords is annotated as “lesion morphology”
  • "patchy” is annotated as “lesion morphology”
  • "high-density shadows” are annotated as "density”
  • "point-like calcifications” are annotated as "lesion morphology”.
  • the image diagnosis text with entity annotations is then used as training data to train an entity recognition model.
  • the trained entity recognition model is used for entity recognition of the image diagnosis text, thereby extracting the content corresponding to the fields in the image diagnosis text
  • the multi-tuple data of the patient information dimension, image information dimension, and text information dimension are mapped to the corresponding nodes of the graph ontology structure, and the association between the nodes is established.
  • the data is stored in the graph database, thereby generating an image report information graph.
  • this application example combines preset knowledge data expansion rules and open source knowledge base to expand the knowledge of the map.
  • the open source knowledge base can include ICD-10 (International Classification of Diseases maintained by the World Health Organization), UMLS (the integrated medical language system of a national medical library), SNOMED-CT (systematic clinical medical terminology maintained by the International Medical Terminology Standard Development Organization), etc., as well as the Chinese symptom library (published on the OpneKG website by a university), CMeKG (Chinese Medical Knowledge Graph), etc., which are further expanded on the basis of these knowledge bases to obtain knowledge graphs.
  • ICD-10 International Classification of Diseases maintained by the World Health Organization
  • UMLS the integrated medical language system of a national medical library
  • SNOMED-CT systematic clinical medical terminology maintained by the International Medical Terminology Standard Development Organization
  • Chinese symptom library published on the OpneKG website by a university
  • CMeKG Choinese Medical Knowledge Graph
  • the imaging report information graph expanded by the second part is obtained for imaging report retrieval and similar imaging report recommendation.
  • the doctor enters a search statement, and the pre-trained intent recognition model and entity recognition model are used to obtain the doctor's search intent and keywords. Then, based on the search intent and keywords, as well as the defined graph ontology structure, a graph query statement is generated for graph query, and finally the query result, i.e., the relevant image report, is returned.
  • the search statement entered by the doctor is "children's COVID-19 imaging”.
  • the intent recognition model shows that the search intent of the search statement is to query imaging information.
  • the entity recognition model shows that the search statement contains the entities "age group: children", "disease: COVID-19", and "examination organ: lung".
  • the pre-trained intent recognition model can be a text classification model, and classification algorithms such as SVM (Support Vector Machine), LSTM (Long Short Term Memory), and BERT can be used.
  • SVM Small Vector Machine
  • LSTM Long Short Term Memory
  • BERT BERT
  • the entity recognition model is similar to the entity recognition model trained in the first part.
  • the obtained search statements can be labeled with entities first, and then the search statements with entity labels can be used as training data to train the entity recognition model to obtain a model that can recognize the entities of new search statements.
  • the dimensions used for the retrieval include the patient information dimension and the imaging information dimension; the other is to retrieve similar imaging reports in real time during the process of the doctor writing the diagnostic text of the imaging findings.
  • the dimensions used for the retrieval may include two or more of the patient information dimension, the imaging information dimension and the text information dimension.
  • the image scanning device when it completes the scan, it will generate device-generated data in the DICOM format of the target image report.
  • the patient information processor and the image information processor in the first part are used to parse the device-generated data in the DICOM format of the target image report to obtain multi-tuple data in the patient information dimension and multi-tuple data in the image information dimension.
  • the image report information graph of the target image report is obtained; the image report information graph of the target image report is compared with the image report information graph of the historical image report for similarity, and the historical image reports are sorted according to the similarity, and the top K historical image reports are used as the ones that are similar to the target image report.
  • the system can also generate similar historical imaging reports and output them for doctors’ reference.
  • the text information processor in the first part is also used to parse the diagnostic text of the image findings of the target image report, and then obtain multi-tuple data of the text information dimension.
  • the image report information graph of the target image report is obtained; the image report information graph of the target image report is compared with the image report information graph of the historical image report for similarity, the historical image reports are sorted according to the similarity, and the top K historical image reports are taken as historical image reports similar to the target image report and output for the doctor's reference.
  • this application example also provides a feedback mechanism.
  • a feedback mechanism is added for the doctor to score the recommended results. The higher the score, the more relevant the recommended result is to the retrieval requirement, and the lower the score, the less relevant the recommended result is to the user's requirement.
  • text descriptions can be added.
  • the recommended similar historical imaging reports belong to the reports of "age group: 20-25 years old, gender: female, examined organ: lung, lesion location: left lung lobe, lesion size: 0.25-0.3 cm nodule".
  • These historical imaging reports may be more referenceable than the historical imaging report of "age group: 40-45 years old, gender: male, examined organ: lung, lesion location: right lung lobe, lesion size: 0.1-0.15 cm nodule”.
  • doctors can score the recommendation results, which can include the text content of the evaluation, to strengthen the model to output more accurate results.
  • the specific operation can be divided into the following steps: obtain the doctor's feedback on the recommendation results, which can include the score and text content, filter the feedback content according to the pre-defined filtering model, and retain the feedback content with a validity higher than the threshold; wherein the filtering model can be a classification model trained by annotating a certain amount of feedback content. Then, according to the feedback content with a validity higher than the threshold, the weights used for the graph or similarity calculation are updated.
  • the weight used for similarity calculation is increased to improve the association strength of the graph between corresponding entities.
  • the text content of the doctor's evaluation is "This result is very good, especially the age group, which is very consistent.” It can be seen that this is a positive feedback, and the age group is a key field, so the weight of this field is increased. If it is negative feedback, on the one hand, the weight used for similarity calculation can be reduced to weaken the association strength of the graph between corresponding entities.
  • the text content of the doctor's evaluation is "These reports are concentrated between 20 and 25 years old, the range is too small.” It can be seen that this is a negative feedback, and the age group is a key field, so the weight of this field is reduced. On the other hand, according to the above text content, it can be seen that the doctor thinks that the age group range is too small, so the value range of the age group can be increased in the process of constructing the graph.
  • the result recommendation and graph optimization can be adapted to different users, that is, to achieve personalized recommendation effects.
  • the above-mentioned weight update operations or the expansion of the value range of the patient's age group are performed on the user side, without modifying the underlying complete graph.
  • the backend monitors the feedback content in real time. When a certain feedback content in the positive and negative feedback meets certain conditions, further consideration can be given to updating the entire complete graph, such as whether the value range of the "age field" is narrowed or expanded, and the complete graph is fully updated.
  • steps in the flowcharts of the embodiments described above are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a portion of the steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages, and these steps or stages are not necessarily executed and completed at the same time, but can be executed in a sequence of steps or stages. The steps or stages may be performed at different times, and the execution order of these steps or stages is not necessarily sequential, but may be performed in turn or alternation with other steps or at least part of the steps or stages in other steps.
  • a device for recommending a medical imaging report comprising:
  • the data acquisition module 401 is used to acquire the medical consultation data and image data corresponding to the current image report;
  • the image data is the data generated by the image scanning device after the image scanning device performs image scanning on the scanned object;
  • a graph acquisition module 402 configured to obtain an image report information graph of the current image report based on at least the medical consultation data and the image data according to a preset dimension defined in the graph ontology structure;
  • the reference report determination module 403 is used to determine a reference image report for the current image report in the historical image report set based on the similarity between the image report information map of the current image report and the image report information map of the historical image reports.
  • the atlas acquisition module 402 is also used to acquire several fields under a preset dimension defined by the atlas ontology structure; determine the contents corresponding to several of the fields in the medical data and the imaging data to obtain multi-tuple data of the preset dimension; and obtain the imaging report information atlas of the current imaging report based on the multi-tuple data of the preset dimension.
  • the atlas acquisition module 402 is also used to parse the medical data and the imaging data to obtain the content corresponding to the first category of fields; according to the preset knowledge data expansion rules, based on the content corresponding to the first category of fields, determine the content corresponding to the second category of fields; based on the content corresponding to the first category of fields and the content corresponding to the second category of fields, obtain the multi-tuple data of the preset dimension.
  • the atlas acquisition module 402 is also used to obtain the multi-tuple data of the preset dimension based on the content corresponding to the first category of fields, the content corresponding to the second category of fields, and the content corresponding to the third category of fields; the content corresponding to the third category of fields is obtained by processing the scanned image obtained based on the image data.
  • the device further includes a similarity comparison module for processing the image report information graph of the current image report and the image report information graph of the historical image report using the graph analysis algorithm to obtain similarity.
  • the similarity comparison module is also used to obtain multiple current image map nodes of the image report information map of the current image report, and multiple historical image map nodes of the image report information map of the historical image report; based on the graph analysis algorithm, determine the common nodes among the multiple current image map nodes and the multiple historical image map nodes to obtain the number of common nodes; and obtain the similarity based on the number of common nodes.
  • the similarity comparison module is further used to obtain sub-similarity of different dimensions according to the number of common nodes in different dimensions; and perform weighted processing on the sub-similarity of different dimensions according to the weight of each dimension to obtain similarity.
  • the device further includes an optimization module for obtaining user feedback on the recommendation result; the recommendation result includes a reference image report for the current image report; and the weight is updated according to the feedback content.
  • the preset dimensions defined in the graph ontology structure include at least: patient information dimension, image information dimension and text information dimension; entities under the image information dimension are associated with entities under the text information dimension.
  • the similarity comparison module is also used to perform a similarity comparison on the contents of each preset field of the image report information map of the current image report and the image report information map of the historical image report under the patient information dimension to obtain a sub-similarity for the patient information dimension; perform a similarity comparison on the contents of each preset field of the image report information map of the current image report and the image report information map of the historical image report under the image information dimension to obtain a sub-similarity for the image information dimension; obtain similarity based on the sub-similarity for the patient information dimension and the sub-similarity for the image information dimension.
  • the device further comprises an entity standardization processing module for obtaining entities in the graph ontology structure; The entities are standardized.
  • the entity standardization processing module is further used to perform standardization processing on the entity according to an open source knowledge base or a knowledge graph.
  • Each module in the above-mentioned device for recommending medical imaging reports can be implemented in whole or in part by software, hardware, and a combination thereof.
  • the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.
  • a computer device in one embodiment, is provided, and its internal structure diagram can be shown in Figure 5.
  • the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus.
  • the processor of the computer device is used to provide computing and control capabilities.
  • the memory of the computer device includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system and a computer program.
  • the internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium.
  • the communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies.
  • the computer device also includes an input and output interface, which is a connection circuit for exchanging information between the processor and the external device. They are connected to the processor through a bus, referred to as an I/O interface.
  • I/O interface a bus
  • the display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen
  • the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.
  • FIG. 5 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied.
  • the specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
  • a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above-mentioned various method embodiments when executing the computer program.
  • a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above-mentioned various method embodiments are implemented.
  • the computer-readable storage medium includes, for example, a non-volatile computer-readable storage medium.
  • a computer program product is provided, on which a computer program is stored, and the computer program is used by a processor to execute the steps in the above-mentioned various method embodiments.
  • user information including but not limited to user device information, user personal information, etc.
  • data including but not limited to data used for analysis, stored data, displayed data, etc.
  • any reference to memory, storage, database or other media used in the embodiments provided in the present application may include at least one of non-volatile and volatile memory.
  • Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical storage, etc.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory. (Dynamic Random Access Memory, DRAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Evolutionary Computation (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Primary Health Care (AREA)
  • Radiology & Medical Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Public Health (AREA)
  • Medical Informatics (AREA)
  • General Health & Medical Sciences (AREA)
  • Epidemiology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Animal Behavior & Ethology (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Library & Information Science (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

La présente demande concerne un procédé de recommandation d'un rapport d'image médicale, au moyen duquel un rapport d'image historique qui est relativement similaire au rapport d'image actuel peut être récupéré en tant que référence pour un médecin. Le procédé consiste à : acquérir des données de patient et des données d'image correspondant au rapport d'image actuel, les données d'image étant des données générées par un dispositif de balayage d'image après que le dispositif de balayage d'image effectue un balayage d'image sur un sujet balayé ; selon des dimensions prédéfinies définies par une structure d'ontologie de graphe, obtenir un graphe d'informations de rapport d'image du rapport d'image actuel sur la base au moins des données de patient et des données d'image ; et sur la base des similarités entre le graphe d'informations de rapport d'image du rapport d'image actuel et des graphes d'informations de rapport d'image de rapports d'image historiques, déterminer, à partir d'un ensemble de rapports d'image historiques, un rapport d'image de référence pour le rapport d'image actuel.
PCT/CN2024/121217 2023-09-25 2024-09-25 Procédé et appareil de recommandation de rapport d'image médicale, et dispositif et support de stockage Pending WO2025067273A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202311253469.1 2023-09-25
CN202311253469.1A CN117609575A (zh) 2023-09-25 2023-09-25 医学影像报告的推荐方法、装置、设备和存储介质

Publications (1)

Publication Number Publication Date
WO2025067273A1 true WO2025067273A1 (fr) 2025-04-03

Family

ID=89946796

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/121217 Pending WO2025067273A1 (fr) 2023-09-25 2024-09-25 Procédé et appareil de recommandation de rapport d'image médicale, et dispositif et support de stockage

Country Status (2)

Country Link
CN (1) CN117609575A (fr)
WO (1) WO2025067273A1 (fr)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117609575A (zh) * 2023-09-25 2024-02-27 武汉联影医疗科技有限公司 医学影像报告的推荐方法、装置、设备和存储介质
CN119296715A (zh) * 2024-12-11 2025-01-10 上海联影智能医疗科技有限公司 一种初始化报告确定方法、装置、存储介质及电子设备

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108897887A (zh) * 2018-07-10 2018-11-27 华南师范大学 一种基于知识图谱和用户相似度的教学资源推荐方法
CN112149759A (zh) * 2020-10-26 2020-12-29 北京明略软件系统有限公司 一种事件图谱的匹配方法、装置、电子设备及存储介质
CN112269901A (zh) * 2020-09-14 2021-01-26 合肥中科类脑智能技术有限公司 一种基于知识图谱的故障判别推理方法
CN112329964A (zh) * 2020-11-24 2021-02-05 北京百度网讯科技有限公司 用于推送信息的方法、装置、设备以及存储介质
CN112420167A (zh) * 2019-08-20 2021-02-26 阿里巴巴集团控股有限公司 影像报告的生成方法、装置及设备
US20210118536A1 (en) * 2019-10-18 2021-04-22 International Business Machines Corporation Automatic clinical report generation
CN115440335A (zh) * 2022-09-13 2022-12-06 青岛海信医疗设备股份有限公司 一种诊断报告生成方法、设备及装置
CN116564483A (zh) * 2023-04-14 2023-08-08 武汉联影医疗科技有限公司 医学影像报告生成方法、装置、计算机设备
CN116631584A (zh) * 2023-02-01 2023-08-22 赵可扬 通用型医学影像报告生成方法与系统、电子设备及可读存储介质
CN117609575A (zh) * 2023-09-25 2024-02-27 武汉联影医疗科技有限公司 医学影像报告的推荐方法、装置、设备和存储介质

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108897887A (zh) * 2018-07-10 2018-11-27 华南师范大学 一种基于知识图谱和用户相似度的教学资源推荐方法
CN112420167A (zh) * 2019-08-20 2021-02-26 阿里巴巴集团控股有限公司 影像报告的生成方法、装置及设备
US20210118536A1 (en) * 2019-10-18 2021-04-22 International Business Machines Corporation Automatic clinical report generation
CN112269901A (zh) * 2020-09-14 2021-01-26 合肥中科类脑智能技术有限公司 一种基于知识图谱的故障判别推理方法
CN112149759A (zh) * 2020-10-26 2020-12-29 北京明略软件系统有限公司 一种事件图谱的匹配方法、装置、电子设备及存储介质
CN112329964A (zh) * 2020-11-24 2021-02-05 北京百度网讯科技有限公司 用于推送信息的方法、装置、设备以及存储介质
CN115440335A (zh) * 2022-09-13 2022-12-06 青岛海信医疗设备股份有限公司 一种诊断报告生成方法、设备及装置
CN116631584A (zh) * 2023-02-01 2023-08-22 赵可扬 通用型医学影像报告生成方法与系统、电子设备及可读存储介质
CN116564483A (zh) * 2023-04-14 2023-08-08 武汉联影医疗科技有限公司 医学影像报告生成方法、装置、计算机设备
CN117609575A (zh) * 2023-09-25 2024-02-27 武汉联影医疗科技有限公司 医学影像报告的推荐方法、装置、设备和存储介质

Also Published As

Publication number Publication date
CN117609575A (zh) 2024-02-27

Similar Documents

Publication Publication Date Title
Wu et al. Comparison of chest radiograph interpretations by artificial intelligence algorithm vs radiology residents
US10929420B2 (en) Structured report data from a medical text report
RU2703679C2 (ru) Способ и система поддержки принятия врачебных решений с использованием математических моделей представления пациентов
US11670420B2 (en) Drawing conclusions from free form texts with deep reinforcement learning
US20190220978A1 (en) Method for integrating image analysis, longitudinal tracking of a region of interest and updating of a knowledge representation
Porturas et al. Forty years of emergency medicine research: Uncovering research themes and trends through topic modeling
WO2020123723A1 (fr) Système et procédé de fourniture d'informations de santé
WO2025067273A1 (fr) Procédé et appareil de recommandation de rapport d'image médicale, et dispositif et support de stockage
CN107403067A (zh) 基于医学知识库的智能分诊服务器、终端及系统
CN114765075A (zh) 药品推荐方法、装置及系统、电子设备及存储介质
JP2017174405A (ja) オープンデータ及び臨床医の入力を用いて患者の治療リスクを評価するシステム及び方法
CN116383413B (zh) 基于医疗数据提取的知识图谱更新方法和系统
US10936962B1 (en) Methods and systems for confirming an advisory interaction with an artificial intelligence platform
RU2720363C2 (ru) Способ формирования математических моделей пациента с использованием технологий искусственного интеллекта
US12300392B2 (en) Determining a next-best action across medical conditions
US12087442B2 (en) Methods and systems for confirming an advisory interaction with an artificial intelligence platform
US11386991B2 (en) Methods and apparatus for artificial intelligence informed radiological reporting and model refinement
Malgieri Ontologies, Machine Learning and Deep Learning in Obstetrics
CN111429985B (zh) 电子病历数据处理方法及系统
CN116737945A (zh) 一种患者emr知识图谱映射方法
US20240177818A1 (en) Methods and systems for summarizing densely annotated medical reports
CN119811656A (zh) 多维医疗大数据融合与疾病预测识别引擎的构建和应用
CN118069690A (zh) 用于从电子医疗记录数据库提供信息的方法和系统
CN110289065A (zh) 一种辅助生成医学电子报告的控制方法以及装置
CN117393099A (zh) 医学文书生成方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 24870817

Country of ref document: EP

Kind code of ref document: A1