CN116959741A - Medical image report comparison method, device, electronic equipment and storage medium - Google Patents
Medical image report comparison method, device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116959741A CN116959741A CN202310994263.8A CN202310994263A CN116959741A CN 116959741 A CN116959741 A CN 116959741A CN 202310994263 A CN202310994263 A CN 202310994263A CN 116959741 A CN116959741 A CN 116959741A
- Authority
- CN
- China
- Prior art keywords
- medical
- vector
- medical image
- image report
- entity data
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 239000013598 vector Substances 0.000 claims abstract description 226
- 238000012545 processing Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 29
- 238000004590 computer program Methods 0.000 claims description 18
- 238000006243 chemical reaction Methods 0.000 claims description 15
- 238000010276 construction Methods 0.000 claims description 10
- 238000000605 extraction Methods 0.000 claims description 8
- 230000015572 biosynthetic process Effects 0.000 claims description 5
- 238000003786 synthesis reaction Methods 0.000 claims description 5
- 238000000691 measurement method Methods 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 19
- 238000003745 diagnosis Methods 0.000 abstract description 6
- 230000008569 process Effects 0.000 description 11
- 238000004891 communication Methods 0.000 description 8
- 230000003287 optical effect Effects 0.000 description 6
- 238000002059 diagnostic imaging Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000013075 data extraction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 description 1
- 238000010835 comparative analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- 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
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Databases & Information Systems (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention discloses a medical image report comparison method, a medical image report comparison device, electronic equipment and a storage medium. The method is characterized by comprising the following steps: acquiring a first medical image report and a second medical image report, and respectively extracting first medical entity data corresponding to the first medical image report and second medical entity data corresponding to the second medical image report according to a medical image report model; respectively constructing a prompt template for the first medical entity data and the second medical entity data according to a preset history vector library to obtain a first medical template corresponding to the first medical entity data and a second medical template corresponding to the second medical entity data; and inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result. The automatic comparison and analysis of the medical image report are realized, the analysis result of the medical image report is output, the medical image report can be processed efficiently, and the treatment efficiency of medical diagnosis is improved.
Description
Technical Field
The present invention relates to the field of medical image report processing, and in particular, to a medical image report comparison method, apparatus, electronic device, and storage medium.
Background
The medical image report is a report file generated according to medical images acquired by the medical image technology, and mainly comprises descriptions of lesions in medical images, detection processes and detection results of the medical detection technology and diagnostic comments given by the medical image technology and/or medical staff. Medical image reports are used as the basis of diagnosis of medical staff, professional medical staff is usually required to carry out manual analysis, and comparison analysis is also required to be carried out on a plurality of medical image reports; in the prior art, in the process of medical image imaging, analysis reports can be carried out aiming at medical images through image identification in a neural network, and medical staff is still required to carry out contrast analysis on a plurality of medical image reports, so that medical resources are wasted.
Disclosure of Invention
The invention provides a medical image report comparison method, a medical image report comparison device, electronic equipment and a storage medium, so as to realize the efficiency and reliability of medical image report comparison analysis.
According to an aspect of the present invention, there is provided a medical image report comparing method, including:
acquiring a first medical image report and a second medical image report, and respectively extracting first medical entity data corresponding to the first medical image report and second medical entity data corresponding to the second medical image report according to a medical image report model;
respectively constructing a prompt template for the first medical entity data and the second medical entity data according to a preset history vector library to obtain a first medical template corresponding to the first medical entity data and a second medical template corresponding to the second medical entity data;
and inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result.
According to another aspect of the present invention, there is provided a medical image report comparing apparatus comprising:
the medical text processing module is used for acquiring a first medical image report and a second medical image report, and respectively extracting first medical entity data corresponding to the first medical image report and second medical entity data corresponding to the second medical image report according to a medical image report model;
The prompt template construction module is used for respectively constructing the prompt templates of the first medical entity data and the second medical entity data according to a preset history vector library to obtain a first medical template corresponding to the first medical entity data and a second medical template corresponding to the second medical entity data;
and the data comparison module is used for inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the medical image report comparison method of any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute a medical image report comparison method according to any one of the embodiments of the present invention.
According to the technical scheme, the first medical entity data corresponding to the first medical image report and the second medical entity data corresponding to the second medical image report are respectively extracted according to the medical image report model, the medical image report is respectively subjected to data extraction through the medical image report model, interference data are removed, data quality is improved, and reliability of medical image report comparison is improved; respectively constructing a prompt template for the first medical entity data and the second medical entity data according to a preset history vector library to obtain a first medical template corresponding to the first medical entity data, and constructing a second medical template corresponding to the second medical entity data through the prompt template, so that better understanding and data processing of a medical image report model can be facilitated, and the processing performance and processing accuracy of the model can be improved; and inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result. The medical image report model is used for comparing and analyzing a plurality of medical image reports, so that the high-efficiency comparison medical image report is realized, and the technical problems of low medical image report comparison analysis efficiency and poor reliability in the prior art are solved. No professional medical staff is needed in the contrast analysis process, the medical image report can be processed efficiently, and the treatment efficiency of medical diagnosis is improved.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a medical image report comparing method according to an embodiment of the present invention;
FIG. 2 is a flowchart of another medical image report comparing method according to a second embodiment of the present invention;
FIG. 3 is a flowchart of another medical image report comparing method according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a medical image report comparing device according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device for implementing a medical image report comparison method according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
Example 1
Fig. 1 is a flowchart of a medical image report comparing method according to an embodiment of the present invention, which is applicable to performing a comparison analysis on a plurality of medical image reports and giving an analysis conclusion, the method may be performed by a medical image report comparing device, which may be implemented in the form of hardware and/or software, and the medical image report comparing device may be configured in an electronic device. As shown in fig. 1, the method includes:
s110, acquiring a first medical image report and a second medical image report, and respectively extracting first medical entity data corresponding to the first medical image report and second medical entity data corresponding to the second medical image report according to a medical image report model.
Wherein the first medical image report may be a medical image report generated by any medical imaging device or medical institution; the second medical image report may be a medical image report generated by any medical imaging device or medical institution. The first medical image report and the second medical image report may be medical image reports generated by the same medical imaging device or medical institution, medical image reports generated by different medical imaging devices or different medical institutions, or medical image reports generated by the medical imaging device and the medical institution, respectively.
Alternatively, the first medical image report and the second medical image report may be two medical image reports of the same patient at the same lesion location; or medical image reports of the same patient at different focus positions; medical image reports of different patients at the same focus position can also be provided; medical image reports of different patients at different focus positions can also be provided; each first medical image report has at least one corresponding second medical image report.
The medical image report model can be a pre-established medical image report contrast model; the medical image report model may be used for comparative analysis and processing of medical image reports.
The first medical entity data may be data corresponding to each entity, a relationship between entities, and an attribute of the entity and the relationship in the first medical image report. The first medical entity data is capable of effectively describing the first medical image report. The second medical entity data may be data corresponding to respective entities, relationships between entities, and attributes of the entities and relationships in the second medical image report.
Specifically, for a first medical image report and a second medical image report that need to be compared, the first medical image report and the second medical image report are respectively input into a medical image report model, first medical entity data of the first medical image report is extracted through the medical image report model, and second medical entity data of the second medical image report is extracted.
S120, respectively constructing prompt templates of the first medical entity data and the second medical entity data according to a preset history vector library to obtain a first medical template corresponding to the first medical entity data and a second medical template corresponding to the second medical entity data.
The historical vector library can be a preset database for storing corresponding vectors of historical medical image report data.
The first medical template and the second medical template can be vector information prompting medical image report comparison analysis. The first medical template may be used to analyze targeted cues for first medical entity data and the second medical template may be used to analyze targeted cues for second medical entity data.
Specifically, the first medical entity data and the second medical entity data are input into a preset history vector library for searching, and prompt template construction is carried out on the first medical entity data and the second medical entity data according to the searched history vector data, so that a first medical template corresponding to the first medical entity data and a second medical template corresponding to the second medical entity data are obtained.
Optionally, in another optional embodiment of the present invention, before the first medical entity data and the second medical entity data are respectively constructed according to a preset history vector library, the method includes:
acquiring a historical medical image report; performing vector conversion on the historical medical image report according to a preset vector conversion method to obtain a historical medical vector; and establishing the history vector library according to the history medical vector.
Wherein the historical medical image report may be a medical image report having a medical image report generation time greater than the first medical image report and the second medical image report. The historical medical image report may be used to analyze reported reference data for the medical image report.
The vector conversion method may be a method preset to vectorize the medical image report. The vector conversion method may be an information retrieval algorithm and a time-series similarity matching algorithm, for example.
Wherein the historical medical vector may be a data set representing a historical medical image report.
Specifically, a historical medical image report is collected, document processing is carried out on the historical medical image report, vectorization is carried out on the historical medical image report through a preset vector conversion method, a historical medical vector is obtained, a historical vector library is built, and the historical medical vector is sequentially stored in the historical vector library.
S130, inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result.
The target comparison result can be comparison result information output by the medical image report model aiming at the first medical template and the second medical template. The target comparison result can be used for helping medical staff to know the change and development of the disease condition of the patient, and the target comparison result can give personalized treatment suggestions for the patient.
Specifically, the first medical template and the second medical template are simultaneously input into a medical image report model, the medical image report model performs comparison analysis on the first medical template and the second medical template, and a target comparison result is output.
According to the technical scheme, the first medical entity data corresponding to the first medical image report and the second medical entity data corresponding to the second medical image report are respectively extracted according to the medical image report model, the medical image report is respectively subjected to data extraction through the medical image report model, interference data are removed, data quality is improved, and reliability of medical image report comparison is improved; respectively constructing a prompt template for the first medical entity data and the second medical entity data according to a preset history vector library to obtain a first medical template corresponding to the first medical entity data, and constructing a second medical template corresponding to the second medical entity data through the prompt template, so that better understanding and data processing of a medical image report model can be facilitated, and the processing performance and processing accuracy of the model can be improved; and inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result. The medical image report model is used for comparing and analyzing a plurality of medical image reports, so that the high-efficiency comparison medical image report is realized, and the technical problems of low medical image report comparison analysis efficiency and poor reliability in the prior art are solved. No professional medical staff is needed in the contrast analysis process, the medical image report can be processed efficiently, and the treatment efficiency of medical diagnosis is improved.
Example two
Fig. 2 is a flowchart of another medical image report comparing method according to the second embodiment of the present invention, and the relationship between the present embodiment and the above embodiments is a specific method for constructing a prompt template of a medical image report. As shown in fig. 2, the medical image report comparison method includes:
s210, acquiring a first medical image report and a second medical image report, and respectively extracting first medical entity data corresponding to the first medical image report and second medical entity data corresponding to the second medical image report according to a medical image report model.
Optionally, in another optional embodiment of the present invention, before extracting the first medical entity data corresponding to the first medical image report according to the medical image report model, the second medical entity data corresponding to the second medical image report includes:
acquiring medical image training data and medical map data; and inputting the medical image training data and the medical map data into a pre-established initial language model for fine tuning open source training to obtain the medical image report model.
The medical image training data may be medical image reports collected for training. The medical profile data may be knowledge-profile triplet data constructed from medical expertise.
Wherein the initial language model may be a large language model established in advance.
Optionally, in the process of training the large-scale language model, performing fine tuning treatment on the pre-trained large-scale language model aiming at different tasks and fields, adjusting parameters and configuration of the large-scale language model, performing freezing operation on part of parameters of the large-scale language model aiming at the tasks, training specific model parameters, adding new parameters into each layer of parameters in the training process, adding additional low-rank matrixes to the appointed parameters in parallel, and training only the parameters of the additional parallel low-rank matrixes in the model training process, thereby realizing fine tuning open-source training on the initial language model. The model fine-tuning open source is performed by a fine-tuning open source method. By way of example, the method of trimming the open source may include at least one of a P-tune (Pattern-Exploiting Training) method, a Lora (low-rankadapting) method, and a Freeze method.
Specifically, medical image training data and medical map data related to medical professional knowledge are acquired, the medical image training data and the medical map data are input into a pre-established initial language model for training, fine tuning is conducted on a medical image report in the training process, and model parameters of the initial language model are adjusted to obtain a medical image report model.
S220, vector conversion is carried out on the first medical entity data and the second medical entity data, a first medical vector corresponding to the first medical entity data is determined, and a second medical vector corresponding to the second medical entity data is determined.
The first medical vector may be a vector data set corresponding to the first medical entity data; the second medical entity data may be a vector data set corresponding to the second medical entity data.
Specifically, vectorizing the first medical entity data to obtain a first medical vector; and vectorizing the second medical entity data to obtain a second medical vector.
S230, respectively inputting the first medical vector and the second medical vector into a preset history vector database for data expansion to obtain a first expansion vector corresponding to the first medical vector and a second expansion vector corresponding to the second medical vector.
Wherein the first expansion vector may be a vector dataset comprising a first medical vector and expansion data; the second expansion vector may be a vector dataset comprising the second medical vector and expansion data.
Specifically, a first medical vector and a second medical vector are input into a preset history vector database, the first medical vector and the second medical vector are subjected to data expansion through the history vector database, the history medical vector in the history vector database is used as expansion data, the expansion data corresponding to the first medical vector and the first medical vector are subjected to data arrangement to obtain a first expansion vector, and the expansion data corresponding to the second medical vector and the second medical vector are subjected to data arrangement to obtain a second expansion vector.
Optionally, in another optional embodiment of the present invention, the inputting the first medical vector and the second medical vector into a preset history vector database for data expansion respectively, to obtain a first expansion vector corresponding to the first medical vector, and a second expansion vector corresponding to the second medical vector, includes:
inputting the first medical vector into a preset historical vector database for vector retrieval to obtain a first similarity sequence corresponding to the first medical vector, and determining a first expansion vector according to the first similarity sequence; and inputting the second medical vector into a preset historical vector database for vector retrieval to obtain a second similarity sequence corresponding to the second medical vector, and determining a second expansion vector according to the second similarity sequence.
The first similarity sequence may be a similarity ranking sequence of the historical medical vector and the first medical vector, and the first similarity sequence may be arranged in order of from big to small in similarity, or may be arranged in order of from small to big in similarity.
The second similarity sequence may be a similarity ranking sequence of the historical medical vector and the second medical vector, and the second similarity training may be set to rank in order from big to small in similarity, or may be set to rank in order from small to big in similarity.
Specifically, a first medical vector is input into a preset historical vector database for vector retrieval, the similarity between the historical medical vector and the first medical vector is calculated in sequence, the historical medical vectors are arranged in sequence according to the similarity to generate a first similarity sequence, and the historical medical vector arranged in the first similarity sequence in front is selected for vector expansion of the first medical vector to obtain a first expansion vector. And inputting the second medical vector into a preset historical vector database for vector retrieval, sequentially calculating the similarity between the historical medical vector and the second medical vector, sequentially arranging the historical medical vectors according to the similarity to generate a second similarity sequence, and selecting the historical medical vector which is arranged in the second similarity sequence and is arranged in front for vector expansion on the second medical vector to obtain a second expansion vector.
S240, constructing the first medical template according to the first medical image report and the first expansion vector, and constructing the second medical template according to the second medical image report and the second expansion vector.
Specifically, a first expansion vector corresponding to a first medical image report is obtained, and a first medical template is constructed according to the first medical image report and the first expansion vector; and obtaining a second expansion vector corresponding to the second medical image report, and constructing a second medical template according to the second medical image report and the second expansion vector.
Optionally, in another optional embodiment of the present invention, the constructing the first medical template according to the first medical image report and the first expansion vector includes:
performing abstract extraction processing on the first expansion vector to obtain a first abstract vector corresponding to the first expansion vector; and carrying out data synthesis on the first abstract vector and the first medical image report to obtain the first medical template.
The first summary vector may be a vector data set that retains key data and data entity relationships in the first extended vector.
Optionally, the first expansion vector is input to a medical image report model, and the medical image report model is used for extracting the data abstract of the first expansion vector, so as to keep the relationship data in the first expansion vector and the entity relationship between the data, and generate a first abstract vector.
Specifically, the medical image report model is used for abstracting the first expansion vector to obtain a first abstract vector corresponding to the first expansion vector, and the first abstract vector and the first medical image report are used for data synthesis to obtain a first medical template.
Optionally, the medical image report model performs abstract extraction processing on the second expansion vector to obtain a second abstract vector corresponding to the second expansion vector, and performs data synthesis on the second abstract vector and the second medical image report to obtain a second medical template. Wherein the second summary vector may be a vector dataset that retains key data and data entity relationships in the second extended vector
S250, inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result.
According to the technical scheme, a first medical image report and a second medical image report are acquired, and first medical entity data corresponding to the first medical image report and second medical entity data corresponding to the second medical image report are respectively extracted according to a medical image report model; vector conversion is carried out on the first medical entity data and the second medical entity data, a first medical vector corresponding to the first medical entity data is determined, and a second medical vector corresponding to the second medical entity data is processed in a vectorization mode, so that the data can be processed more easily, and the processing efficiency of the data is improved; the first medical vector and the second medical vector are respectively input into a preset historical vector database for data expansion, a first expansion vector corresponding to the first medical vector is obtained, a second expansion vector corresponding to the second medical vector is obtained, the processing performance of a model can be improved through data expansion, and the reliability and the efficiency of model processing are improved; constructing the first medical template according to the first medical image report and the first expansion vector, and constructing the second medical template according to the second medical image report and the second expansion vector; and inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result. The medical image report model is used for comparing and analyzing a plurality of medical image reports, so that the high-efficiency comparison medical image report is realized, and the technical problems of low medical image report comparison analysis efficiency and poor reliability in the prior art are solved. No professional medical staff is needed in the contrast analysis process, the medical image report can be processed efficiently, and the treatment efficiency of medical diagnosis is improved.
Optionally, fig. 3 is a flowchart of another medical image report comparing method according to an embodiment of the present invention. As shown in fig. 3: inputting the medical image training data and the medical map data into an initial language model for fine adjustment model training, and determining a medical image report model; respectively inputting the first medical image report and the second medical image report into a medical image report model to extract entity relation and output first medical entity data and second medical entity data; performing similarity retrieval on the first medical entity data and the second medical entity data through a history vector library to respectively obtain a first expansion vector and a second expansion vector; adding the first entity data and the first expansion vector to obtain a first medical template; adding the second entity data and the second expansion vector to obtain a second medical template; then the first medical template and the second medical template are input back to the medical image report model to obtain a target comparison result
Example III
Fig. 4 is a schematic structural diagram of a medical image report comparing device according to a third embodiment of the present invention. As shown in fig. 4, the apparatus includes: a medical text processing module 410, a prompt template construction module 420, and a data comparison module 430, wherein,
The medical text processing module 410 is configured to obtain a first medical image report and a second medical image report, and extract first medical entity data corresponding to the first medical image report and second medical entity data corresponding to the second medical image report according to a medical image report model;
the prompt template construction module 420 is configured to construct a prompt template for the first medical entity data and the second medical entity data according to a preset history vector library, so as to obtain a first medical template corresponding to the first medical entity data, and a second medical template corresponding to the second medical entity data;
the data comparison module 430 is configured to input the first medical template and the second medical template to the medical image report model to obtain a target comparison result.
According to the technical scheme, the first medical entity data corresponding to the first medical image report and the second medical entity data corresponding to the second medical image report are respectively extracted according to the medical image report model, the medical image report is respectively subjected to data extraction through the medical image report model, interference data are removed, data quality is improved, and reliability of medical image report comparison is improved; respectively constructing a prompt template for the first medical entity data and the second medical entity data according to a preset history vector library to obtain a first medical template corresponding to the first medical entity data, and constructing a second medical template corresponding to the second medical entity data through the prompt template, so that better understanding and data processing of a medical image report model can be facilitated, and the processing performance and processing accuracy of the model can be improved; and inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result. The medical image report model is used for comparing and analyzing a plurality of medical image reports, so that the high-efficiency comparison medical image report is realized, and the technical problems of low medical image report comparison analysis efficiency and poor reliability in the prior art are solved. No professional medical staff is needed in the contrast analysis process, the medical image report can be processed efficiently, and the treatment efficiency of medical diagnosis is improved.
Optionally, the prompt template construction module is specifically configured to:
optionally, the prompt template construction module is specifically configured to:
vector conversion is carried out on the first medical entity data and the second medical entity data, a first medical vector corresponding to the first medical entity data is determined, and a second medical vector corresponding to the second medical entity data is determined;
respectively inputting the first medical vector and the second medical vector into a preset history vector database for data expansion to obtain a first expansion vector corresponding to the first medical vector and a second expansion vector corresponding to the second medical vector;
and constructing the first medical template according to the first medical image report and the first expansion vector, and constructing the second medical template according to the second medical image report and the second expansion vector.
Optionally, the prompt template construction module is specifically further configured to:
performing abstract extraction processing on the first expansion vector to obtain a first abstract vector corresponding to the first expansion vector;
and carrying out data synthesis on the first abstract vector and the first medical image report to obtain the first medical template.
Optionally, the prompt template construction module is specifically further configured to:
inputting the first medical vector into a preset historical vector database for vector retrieval to obtain a first similarity sequence corresponding to the first medical vector, and determining a first expansion vector according to the first similarity sequence; the method comprises the steps of,
and inputting the second medical vector into a preset historical vector database for vector retrieval to obtain a second similarity sequence corresponding to the second medical vector, and determining a second expansion vector according to the second similarity sequence.
Optionally, the system further comprises a training data acquisition module and a model training module; wherein:
the training data acquisition module is used for acquiring medical image training data and medical map data;
the model training module is used for inputting the medical image training data and the medical map data into a pre-established initial language model to conduct fine tuning open source training, and the medical image report model is obtained.
Optionally, the medical text processing module is specifically configured to:
performing example extraction on the first medical image report according to a medical image report model and combining the text context of the first medical image report to obtain the first medical entity data;
And carrying out example extraction on the second medical image report according to the medical image report model and the text context of the second medical image report to obtain the second medical entity data.
Optionally, the system further comprises a historical data acquisition module, a vector conversion module and a database establishment module; wherein:
the historical data acquisition module is used for acquiring a historical medical image report;
the vector conversion module is used for carrying out vector conversion on the historical medical image report according to a preset vector conversion method to obtain a historical medical vector;
the database establishing module is used for establishing the history vector library according to the history medical vector.
The medical image report comparison device provided by the embodiment of the invention can execute the medical image report comparison method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 5 shows a schematic diagram of the structure of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 5, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the medical image report contrast method.
In some embodiments, the medical image report contrast method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more of the steps of the medical image report contrast method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the medical image report contrast method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for carrying out methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
Example five
The present embodiment provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of a medical image report comparison method as provided in any embodiment of the present invention, the method comprising:
acquiring a first medical image report and a second medical image report, and respectively extracting first medical entity data corresponding to the first medical image report and second medical entity data corresponding to the second medical image report according to a medical image report model;
respectively constructing a prompt template for the first medical entity data and the second medical entity data according to a preset history vector library to obtain a first medical template corresponding to the first medical entity data and a second medical template corresponding to the second medical entity data;
And inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
It will be appreciated by those of ordinary skill in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be centralized on a single computing device, or distributed over a network of computing devices, or they may alternatively be implemented in program code executable by a computer device, such that they are stored in a memory device and executed by the computing device, or they may be separately fabricated as individual integrated circuit modules, or multiple modules or steps within them may be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A medical image report contrast method, comprising:
acquiring a first medical image report and a second medical image report, and respectively extracting first medical entity data corresponding to the first medical image report and second medical entity data corresponding to the second medical image report according to a medical image report model;
respectively constructing a prompt template for the first medical entity data and the second medical entity data according to a preset history vector library to obtain a first medical template corresponding to the first medical entity data and a second medical template corresponding to the second medical entity data;
and inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result.
2. The method according to claim 1, wherein the performing, according to a preset history vector library, a prompt template construction on the first medical entity data and the second medical entity data respectively includes:
vector conversion is carried out on the first medical entity data and the second medical entity data, a first medical vector corresponding to the first medical entity data is determined, and a second medical vector corresponding to the second medical entity data is determined;
Respectively inputting the first medical vector and the second medical vector into a preset history vector database for data expansion to obtain a first expansion vector corresponding to the first medical vector and a second expansion vector corresponding to the second medical vector;
and constructing the first medical template according to the first medical image report and the first expansion vector, and constructing the second medical template according to the second medical image report and the second expansion vector.
3. The method of claim 2, wherein the constructing the first medical template from the first medical image report and the first expansion vector comprises:
performing abstract extraction processing on the first expansion vector to obtain a first abstract vector corresponding to the first expansion vector;
and carrying out data synthesis on the first abstract vector and the first medical image report to obtain the first medical template.
4. The method according to claim 2, wherein the inputting the first medical vector and the second medical vector into a preset history vector database for data expansion respectively, to obtain a first expansion vector corresponding to the first medical vector, and a second expansion vector corresponding to the second medical vector, includes:
Inputting the first medical vector into a preset historical vector database for vector retrieval to obtain a first similarity sequence corresponding to the first medical vector, and determining a first expansion vector according to the first similarity sequence; the method comprises the steps of,
and inputting the second medical vector into a preset historical vector database for vector retrieval to obtain a second similarity sequence corresponding to the second medical vector, and determining a second expansion vector according to the second similarity sequence.
5. The method of claim 1, comprising, prior to the extracting the first medical entity data corresponding to the first medical image report and the second medical entity data corresponding to the second medical image report, respectively, according to a medical image report model:
acquiring medical image training data and medical map data;
and inputting the medical image training data and the medical map data into a pre-established initial language model for fine tuning open source training to obtain the medical image report model.
6. The method of claim 1, wherein the extracting the first medical entity data corresponding to the first medical image report and the second medical entity data corresponding to the second medical image report according to the medical image report model, respectively, comprises:
Performing example extraction on the first medical image report according to a medical image report model and combining the text context of the first medical image report to obtain the first medical entity data;
and carrying out example extraction on the second medical image report according to the medical image report model and the text context of the second medical image report to obtain the second medical entity data.
7. The method of claim 1, comprising, prior to constructing the reminder templates for the first and second medical entity data, respectively, according to a pre-set history vector library:
acquiring a historical medical image report;
performing vector conversion on the historical medical image report according to a preset vector conversion method to obtain a historical medical vector;
and establishing the history vector library according to the history medical vector.
8. A medical image report contrast device, comprising:
the medical text processing module is used for acquiring a first medical image report and a second medical image report, and respectively extracting first medical entity data corresponding to the first medical image report and second medical entity data corresponding to the second medical image report according to a medical image report model;
The prompt template construction module is used for respectively constructing the prompt templates of the first medical entity data and the second medical entity data according to a preset history vector library to obtain a first medical template corresponding to the first medical entity data and a second medical template corresponding to the second medical entity data;
and the data comparison module is used for inputting the first medical template and the second medical template into the medical image report model to obtain a target comparison result.
9. An electronic device, the electronic device comprising:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the medical image report comparing method of any one of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the medical image reporting contrast measurement method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310994263.8A CN116959741A (en) | 2023-08-08 | 2023-08-08 | Medical image report comparison method, device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310994263.8A CN116959741A (en) | 2023-08-08 | 2023-08-08 | Medical image report comparison method, device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116959741A true CN116959741A (en) | 2023-10-27 |
Family
ID=88458223
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310994263.8A Pending CN116959741A (en) | 2023-08-08 | 2023-08-08 | Medical image report comparison method, device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116959741A (en) |
-
2023
- 2023-08-08 CN CN202310994263.8A patent/CN116959741A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110458217B (en) | Image recognition method and device, fundus image recognition method and electronic equipment | |
| CN113590645B (en) | Searching method, searching device, electronic equipment and storage medium | |
| CN112784778B (en) | Method, apparatus, device and medium for generating model and identifying age and sex | |
| CN113657289B (en) | Training method and device of threshold estimation model and electronic equipment | |
| CN114693934B (en) | Training method of semantic segmentation model, video semantic segmentation method and device | |
| WO2019118236A1 (en) | Deep learning on image frames to generate a summary | |
| US20230215136A1 (en) | Method for training multi-modal data matching degree calculation model, method for calculating multi-modal data matching degree, and related apparatuses | |
| CN114937025A (en) | Image segmentation method, model training method, device, equipment and medium | |
| JP2023060846A (en) | Model determination method, apparatus, electronic device, and memory | |
| CN113657249B (en) | Training method, prediction method, device, electronic equipment and storage medium | |
| CN111210022A (en) | Backward model selection method, device and readable storage medium | |
| CN115248890B (en) | User interest portrait generation method and device, electronic equipment and storage medium | |
| CN114529945A (en) | Emotion recognition method, device, equipment and storage medium | |
| CN113657411A (en) | Neural network model training method, image feature extraction method and related device | |
| CN115472257A (en) | Method and device for recruiting users, electronic equipment and storage medium | |
| CN116959741A (en) | Medical image report comparison method, device, electronic equipment and storage medium | |
| CN115665783A (en) | Abnormal index tracing method and device, electronic equipment and storage medium | |
| CN116982038A (en) | Image construction and visualization of multiple immunofluorescence images | |
| CN116258720B (en) | Image recognition method, device, electronic equipment and storage medium | |
| CN117649933B (en) | Online consultation assistance method and device, electronic equipment and storage medium | |
| CN115497633B (en) | Data processing method, device, equipment and storage medium | |
| US20240029416A1 (en) | Method, device, and computer program product for image processing | |
| CN116452915A (en) | Image processing method, device, electronic equipment and storage medium | |
| CN116303572A (en) | Data retrieval method, device, electronic equipment and storage medium | |
| CN117973479A (en) | Privacy training method, device, equipment and medium for reparameterizable model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |