CN115270779B - Method and system for generating ulcerative colitis structured report - Google Patents
Method and system for generating ulcerative colitis structured report Download PDFInfo
- Publication number
- CN115270779B CN115270779B CN202210759471.5A CN202210759471A CN115270779B CN 115270779 B CN115270779 B CN 115270779B CN 202210759471 A CN202210759471 A CN 202210759471A CN 115270779 B CN115270779 B CN 115270779B
- Authority
- CN
- China
- Prior art keywords
- focus
- content
- entity
- focus entity
- ulcerative colitis
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 206010009900 Colitis ulcerative Diseases 0.000 title claims abstract description 50
- 201000006704 Ulcerative Colitis Diseases 0.000 title claims abstract description 50
- 238000013145 classification model Methods 0.000 claims abstract description 31
- 230000003902 lesion Effects 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 238000003745 diagnosis Methods 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 208000025865 Ulcer Diseases 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 231100000397 ulcer Toxicity 0.000 claims description 5
- 230000000740 bleeding effect Effects 0.000 claims description 4
- 230000003628 erosive effect Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 206010015150 Erythema Diseases 0.000 claims description 3
- 206010056626 Pseudopolyp Diseases 0.000 claims description 3
- 231100000321 erythema Toxicity 0.000 claims description 3
- 238000002372 labelling Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000002269 spontaneous effect Effects 0.000 claims description 3
- 230000002792 vascular Effects 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 8
- 208000037062 Polyps Diseases 0.000 description 6
- 210000004877 mucosa Anatomy 0.000 description 5
- 206010009944 Colon cancer Diseases 0.000 description 4
- 208000032843 Hemorrhage Diseases 0.000 description 4
- 208000029742 colonic neoplasm Diseases 0.000 description 4
- 208000034158 bleeding Diseases 0.000 description 3
- 238000000225 bioluminescence resonance energy transfer Methods 0.000 description 2
- 210000004204 blood vessel Anatomy 0.000 description 2
- 210000001072 colon Anatomy 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 210000000664 rectum Anatomy 0.000 description 2
- 210000001599 sigmoid colon Anatomy 0.000 description 2
- 208000004998 Abdominal Pain Diseases 0.000 description 1
- 206010012735 Diarrhoea Diseases 0.000 description 1
- 206010058838 Enterocolitis infectious Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 208000022559 Inflammatory bowel disease Diseases 0.000 description 1
- 208000005374 Poisoning Diseases 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 210000001815 ascending colon Anatomy 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001574 biopsy Methods 0.000 description 1
- 208000027503 bloody stool Diseases 0.000 description 1
- 210000004534 cecum Anatomy 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 210000001731 descending colon Anatomy 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000001839 endoscopy Methods 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 208000035861 hematochezia Diseases 0.000 description 1
- 210000003405 ileum Anatomy 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 208000027139 infectious colitis Diseases 0.000 description 1
- 230000002458 infectious effect Effects 0.000 description 1
- 230000002757 inflammatory effect Effects 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000000968 intestinal effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000009885 systemic effect Effects 0.000 description 1
- 210000003384 transverse colon Anatomy 0.000 description 1
- 230000036269 ulceration Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Medical Treatment And Welfare Office Work (AREA)
- Machine Translation (AREA)
Abstract
The invention belongs to the technical field of medical treatment, and provides a method and a system for generating a ulcerative colitis structural report. The method comprises the steps of obtaining report text content of ulcerative colitis; based on the report text content, determining focus entity positions and focus entity contents by adopting a focus entity identification model; based on the focus entity position and focus entity content, a multi-label text classification model is adopted to obtain focus category; based on the focus category, adopting a text content recognition model to obtain text content so as to generate an ulcerative colitis structured report; the determining the focus entity content specifically comprises the following steps: starting with the sentence of the identified focus entity content, detecting whether the next sentence has focus entity content, if not, using the focus entity content as the focus entity content of the sentence, and filling the front end of the sentence.
Description
Technical Field
The invention belongs to the technical field of medical treatment, and particularly relates to a method and a system for generating a ulcerative colitis structural report.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Ulcerative colitis (ulcerative colitis, UC) is a chronic nonspecific inflammation with recurrent episodes of abdominal pain and diarrhea, mucopurulent bloody stool as the main clinical manifestations, lesions often appear in a continuous distribution, can involve multiple intestinal segments of the rectum, sigmoid colon and the whole colon, and severe patients can have systemic infection poisoning symptoms, even endangering life. The UC patient has strong individuation characteristics, related guidelines at home and abroad and various and complicated documents, diagnosis and treatment are required to be based on a plurality of complex clinical scores and types, and multidimensional consideration is carried out, so that a case library of inflammatory bowel patients is necessary to be established, and finally intelligent recognition diagnosis and treatment decision of the inflammatory bowel diseases is realized.
However, UC lacks the gold standard for diagnosis, and is mainly comprehensively analyzed by combining clinical manifestations, laboratory examinations, imaging examinations, endoscopy examinations and histopathological manifestations, diagnosis is performed on the basis of eliminating infectious and other non-infectious colitis, and the case library formed based on the above data is numerous and complicated in content, so that the establishment of a case is time-consuming and labor-consuming and the correctness cannot be ensured.
And extracting the attribute values of the entities from the unstructured text to form structured data. Because the content seen under the diagnostic report mirror has the characteristics of few text sentences and large information quantity, the traditional entity relation extraction is mainly of a given relation type, is limited by manually defined relation types and limited by training corpus, and is difficult to be applied to the conversion of the diagnostic report text into a structured report.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides a method and a system for generating ulcerative colitis structural reports, which adopt a multi-label text classification method, obtain the category to which each piece of text content belongs through a multi-label text classification model, and respectively identify the text content aiming at a text content identification model corresponding to each category to obtain a corresponding structural identification result.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a first aspect of the invention provides a method of generating a structured report of ulcerative colitis.
A method of generating a structured report of ulcerative colitis, comprising:
acquiring report text content of ulcerative colitis;
based on the report text content, determining focus entity positions and focus entity contents by adopting a focus entity identification model;
based on the focus entity position and focus entity content, a multi-label text classification model is adopted to obtain focus category;
based on the focus category, adopting a text content recognition model to obtain text content so as to generate an ulcerative colitis structured report;
wherein, the determining the focus entity content specifically includes: starting with the sentence of the identified focus entity content, detecting whether the next sentence has focus entity content, if not, using the focus entity content as the focus entity content of the sentence, and filling the front end of the sentence.
Further, before the lesion entity identification model is adopted, the method further comprises: and preprocessing the report text content, wherein the preprocessing comprises text word segmentation on the report text content and word processing is stopped.
Still further, after the preprocessing, vectorizing the preprocessed report text content.
Still further, feature extraction is performed on the report text content of the vectorized representation to reduce feature dimensions.
Further, after determining the location of the focal entity and the content of the focal entity, further comprising: and taking texts before and after the focus entity position as a context, and performing focus entity text filling processing on adjacent texts.
Further, the lesion category includes: lesion sites, mucosal erythema, mucosal vascular texture, mucosal fragility, erosive ulcers, spontaneous bleeding, and pseudopolyps.
Further, the multi-label text classification model adopts a BRET model.
Further, after obtaining the focus category, the method further comprises the step of verifying the multi-label text classification model, wherein the specific process is as follows:
performing focus part classification on historical image data acquired in the ulcerative colitis inspection process, and training a part classification model;
labeling focus data and preparing training sample data; training a focus recognition model;
and calling a part classification model and a focus identification model for the image data acquired in the ulcerative colitis inspection process, and performing secondary verification on a focus diagnosis result obtained through the multi-label text classification model.
A second aspect of the invention provides a system for generating a structured report of ulcerative colitis.
A system for generating a structured report of ulcerative colitis, comprising:
a data acquisition module configured to: acquiring report text content of ulcerative colitis;
an entity identification module configured to: based on the report text content, determining focus entity positions and focus entity contents by adopting a focus entity identification model;
a classification module configured to: based on the focus entity position and focus entity content, a multi-label text classification model is adopted to obtain focus category;
a report generation module configured to: based on the focus category, adopting a text content recognition model to obtain text content so as to generate an ulcerative colitis structured report;
wherein, the determining the focus entity content specifically includes: starting with the sentence of the identified focus entity content, detecting whether the next sentence has focus entity content, if not, using the focus entity content as the focus entity content of the sentence, and filling the front end of the sentence.
A third aspect of the present invention provides a computer-readable storage medium.
A computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps in the method of generating a structured report of ulcerative colitis as described in the first aspect above.
A fourth aspect of the invention provides a computer device.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in a method of generating a structured report of ulcerative colitis according to the first aspect above when the program is executed.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the diagnosis report of the natural language is prepared, and then the diagnosis report of the natural language is processed to form the structured ulcerative colitis structured report, so that the case library is constructed, the generation speed of the case library is improved, and meanwhile, the accuracy of each ulcerative colitis structured report is improved.
The invention adopts a multi-label text classification method, obtains the category to which each text content belongs through a multi-label text classification model, respectively identifies the text content aiming at the text content identification model corresponding to each category, obtains the corresponding structured identification result, and provides the accuracy of converting unstructured content into structured content.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a flow chart of a method of generating a structured report of ulcerative colitis, shown in an embodiment of the invention;
fig. 2 is a schematic diagram of a classifier shown in an embodiment of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is illustrative and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
It is noted that the flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and systems according to various embodiments of the present disclosure. It should be noted that each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the logical functions specified in the various embodiments. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by special purpose hardware-based systems which perform the specified functions or operations, or combinations of special purpose hardware and computer instructions.
Example 1
As shown in fig. 1, this embodiment provides a method for generating a ulcerative colitis structural report, where the method is applied to a server for illustration, and it is understood that the method may also be applied to a terminal, and may also be applied to a system and a terminal, and implemented through interaction between the terminal and the server. The server can be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, and can also be a cloud server for providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network servers, cloud communication, middleware services, domain name services, security services CDNs, basic cloud computing services such as big data and artificial intelligent platforms and the like. The terminal may be, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, a smart speaker, a smart watch, etc. The terminal and the server may be directly or indirectly connected through wired or wireless communication, which is not limited herein. In this embodiment, the method includes the steps of:
acquiring report text content of ulcerative colitis;
based on the report text content, determining focus entity positions and focus entity contents by adopting a focus entity identification model;
based on the focus entity position and focus entity content, a multi-label text classification model is adopted to obtain focus category;
based on the focus category, adopting a text content recognition model to obtain text content so as to generate an ulcerative colitis structured report;
wherein, the determining the focus entity content specifically includes: starting with the sentence of the identified focus entity content, detecting whether the next sentence has focus entity content, if not, using the focus entity content as the focus entity content of the sentence, and filling the front end of the sentence.
For the specific solution of this embodiment, reference may be made to the following implementation:
step 1: and collecting the real report text content related to ulcerative colitis with large data volume, extracting the text content seen under the lens, and splitting the text content segment by segment and sentence by sentence. Because the content seen under the diagnostic report mirror has the characteristics of fewer text sentences and large information quantity, for example: the mucosal vessel texture is blurred and disturbed. For another example: enters the far end of ileum, can be scattered on the ulcer erosion surface, and takes 2 biopsies. This text has both the focal area and the ulceration feature and the number of ulcers. Text recognition is performed by using a multi-tag text classification method, namely, a text to be classified is given a plurality of tags by a specific classifier, and the tags have certain association and have no association. Suppose d= { (x) i ，y i ) The samples in the training set are learned to a mapping f using the designed model: x->Y, where x i ∈X，y i E Y is instance x i The corresponding category labels are shown in fig. 2.
1.1, text preprocessing, text word segmentation is carried out on unstructured content, and word processing is stopped. The vectorization representation is carried out after the pretreatment, and the characteristics obtained after the text vectorization treatment are sparse and have higher dimensionality. And the feature extraction is to remove useless features on the premise of ensuring the completeness of text semantic expression, retain effective features and perform feature dimension reduction.
1.2 identification of focal entities in text
Because the content seen under the diagnosis report mirror has the characteristics of less text sentences and large information quantity, focus entity identification and filling processing are carried out on the report text content so as to solve the problem that the relevance of entity content context is lacking after the diagnosis report content clause is split.
Defining a plurality of lesion entity labels: ulcerative colitis, bleeding, polyps, early colon cancer, advanced colon cancer, focus entity recognition models are trained based on CRF (conditional random field). And calling a focus entity recognition model to obtain a focus entity position of each sentence of text, and filling the focus entity text into the adjacent text by taking the text before and after the focus entity position as a context. So that the subsequent classification model can extract more knowledge points. The focus entity identification model can adopt the existing neural network.
Splitting the diagnosis content according to sentences, and calling a focus entity recognition model to obtain focus entity content. Starting with the sentence of the identified entity content, detecting whether the next sentence has entity content, if not, using the entity content as the entity content of the sentence, and filling the sentence to the front end.
Such as a piece of diagnostic content: "1 colon 20cm from the anal verge has flat polyps about 0.2x0.3cm in size, smooth surface, and similar to surrounding mucosa. The lesions are completely resected under the endoscope, and the process is smooth in the operation. After the focus entity recognition model is called, the first sentence of the text recognizes the focus entity of polyp; and if no focus entity is identified in the second sentence, performing focus entity filling treatment. The adjusted content is modified as follows: there were 1 flat polyp of about 0.2x0.3cm in size at 20cm from the anal verge, with smooth surface and similar color to surrounding mucosa. The polyp completely resects the lesion under the endoscope, and the process is smooth in the operation.
1.3 training a Multi-Label text Classification model
And sending the preprocessed text (training set) into a specific classifier (model) for training to obtain the multi-label text classification model. The classifier uses a BRET model to carry out multi-label text classification training, and classification categories are as follows in sequence: lesion, mucosal erythema, mucosal vascular texture, mucosal fragility, erosive ulcers, spontaneous bleeding, and pseudopolyps. The classification types and rules for characterizing the corresponding types are determined by combining clinical guidelines and a large number of historical diagnostic reports, such as that the mucosa brittleness is classified into smooth, slightly fragile and obviously fragile.
Step 2: the category to which each text content belongs is obtained through the multi-label text classification model, and next, the text content is identified by the text content identification model corresponding to each category, so that a corresponding structural identification result is obtained. For example: the mucosal vessel texture is blurred and disturbed. The text uses BERT classification model to identify the type of the mucosal vessel texture in the multi-label type. Training a text content recognition model corresponding to the mucosa blood vessel texture category, dividing the text content recognition model into normal, reduced and disappeared, recognizing the text content recognition model as reduced, and filling the text content recognition model into a column of the structured report mucosa blood vessel texture. The FastText text classification algorithm is used here, i.e. the classification time is greatly shortened with guaranteed accuracy.
Step 3: and (5) a secondary verification process based on image recognition. And acquiring original image data acquired in the ulcerative colitis inspection process, and respectively training an enteroscopy part recognition model and a focus recognition model.
3.1, classifying the parts of the acquired images, wherein the classification is as follows: the classification model of the part is trained by the classification of cecum, ascending and descending colon, transverse colon, sigmoid colon, rectum, unknown and the like.
3.2, marking focus data and manufacturing training sample data; training a lesion recognition model can be divided into: lesion categories such as ulcerative colitis, hemorrhage, polyps, early colon cancer, advanced colon cancer, etc.
3.3 a secondary verification process of the text classification model. The location of the lesion and the type of lesion. And (3) calling a part classification model and a focus identification model for the acquired image, and performing secondary verification on a focus diagnosis result obtained by the multi-label text classification model in the step (2).
Example two
The embodiment provides a system for generating a ulcerative colitis structural report.
A data acquisition module configured to: acquiring report text content of ulcerative colitis;
an entity identification module configured to: based on the report text content, determining focus entity positions and focus entity contents by adopting a focus entity identification model;
a classification module configured to: based on the focus entity position and focus entity content, a multi-label text classification model is adopted to obtain focus category;
a report generation module configured to: based on the focus category, adopting a text content recognition model to obtain text content so as to generate an ulcerative colitis structured report;
wherein, the determining the focus entity content specifically includes: starting with the sentence of the identified focus entity content, detecting whether the next sentence has focus entity content, if not, using the focus entity content as the focus entity content of the sentence, and filling the front end of the sentence.
It should be noted that the data acquisition module, the entity identification module, the classification module, and the report generation module are the same as the examples and application scenarios implemented by the steps in the first embodiment, but are not limited to the disclosure in the first embodiment. It should be noted that the modules described above may be implemented as part of a system in a computer system, such as a set of computer-executable instructions.
Example III
The present embodiment provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps in the method of generating a structured report of ulcerative colitis as described in the above embodiment one.
Example IV
The present embodiment provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps in the method for generating a structured report of ulcerative colitis according to the above embodiment.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored on a computer readable storage medium, which when executed may comprise the steps of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random access Memory (Random AccessMemory, RAM), or the like.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. A method of generating a structured report of ulcerative colitis, comprising:
acquiring report text content of ulcerative colitis;
based on the report text content, determining focus entity positions and focus entity contents by adopting a focus entity identification model;
based on the focus entity position and focus entity content, a multi-label text classification model is adopted to obtain focus category;
based on the focus category, adopting a text content recognition model to obtain text content so as to generate an ulcerative colitis structured report;
wherein, the determining the focus entity content specifically includes: starting from the sentence of the identified focus entity content, detecting whether the next sentence has focus entity content, if not, using the focus entity content as the focus entity content of the sentence, and filling the focus entity content into the front end of the sentence;
after determining the lesion entity location and the lesion entity content, further comprises: calling a focus entity recognition model to obtain focus entity positions of each sentence of text, and filling focus entity texts into adjacent texts by taking texts before and after the focus entity positions as contexts;
after the focus category is obtained, the method also comprises the step of verifying the multi-label text classification model, wherein the specific process is as follows:
performing focus part classification on historical image data acquired in the ulcerative colitis inspection process, and training a part classification model;
labeling focus data and preparing training sample data; training a focus recognition model;
and calling a part classification model and a focus identification model for the image data acquired in the ulcerative colitis inspection process, and performing secondary verification on a focus diagnosis result obtained through the multi-label text classification model.
2. The method of claim 1, further comprising, prior to employing the lesion entity recognition model: and preprocessing the report text content, wherein the preprocessing comprises text word segmentation on the report text content and word processing is stopped.
3. The method of claim 2, wherein the pre-processing includes vectorizing the pre-processed report text content.
4. A method of generating a structured report of ulcerative colitis according to claim 3, characterised in that feature extraction is performed on the report text content of the vectorised representation to reduce feature dimensions.
5. The method of generating a structured report of ulcerative colitis of claim 1, wherein the lesion classification comprises: lesion sites, mucosal erythema, mucosal vascular texture, mucosal fragility, erosive ulcers, spontaneous bleeding, and pseudopolyps.
6. A system for generating a structured report of ulcerative colitis, comprising:
a data acquisition module configured to: acquiring report text content of ulcerative colitis;
an entity identification module configured to: based on the report text content, determining focus entity positions and focus entity contents by adopting a focus entity identification model;
a classification module configured to: based on the focus entity position and focus entity content, a multi-label text classification model is adopted to obtain focus category;
a report generation module configured to: based on the focus category, adopting a text content recognition model to obtain text content so as to generate an ulcerative colitis structured report;
wherein, the adopting focus entity recognition model to determine focus entity content specifically comprises: starting from the sentence of the identified focus entity content, detecting whether the next sentence has focus entity content, if not, using the focus entity content as the focus entity content of the sentence, and filling the focus entity content into the front end of the sentence;
after determining the lesion entity location and the lesion entity content, further comprises: calling a focus entity recognition model to obtain focus entity positions of each sentence of text, and filling focus entity texts into adjacent texts by taking texts before and after the focus entity positions as contexts;
after the focus category is obtained, the method also comprises the step of verifying the multi-label text classification model, wherein the specific process is as follows:
performing focus part classification on historical image data acquired in the ulcerative colitis inspection process, and training a part classification model;
labeling focus data and preparing training sample data; training a focus recognition model;
and calling a part classification model and a focus identification model for the image data acquired in the ulcerative colitis inspection process, and performing secondary verification on a focus diagnosis result obtained through the multi-label text classification model.
7. A computer readable storage medium, having stored thereon a computer program, which when executed by a processor, implements the steps in the method of generating a structured report of ulcerative colitis according to any one of claims 1-5.
8. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor, when executing the program, implements the steps in the method of generating a structured report of ulcerative colitis as claimed in any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210759471.5A CN115270779B (en) | 2022-06-30 | 2022-06-30 | Method and system for generating ulcerative colitis structured report |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210759471.5A CN115270779B (en) | 2022-06-30 | 2022-06-30 | Method and system for generating ulcerative colitis structured report |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115270779A CN115270779A (en) | 2022-11-01 |
| CN115270779B true CN115270779B (en) | 2024-04-12 |
Family
ID=83764829
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210759471.5A Active CN115270779B (en) | 2022-06-30 | 2022-06-30 | Method and system for generating ulcerative colitis structured report |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115270779B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110688855A (en) * | 2019-09-29 | 2020-01-14 | 山东师范大学 | Chinese medical entity identification method and system based on machine learning |
| CN111048170A (en) * | 2019-12-23 | 2020-04-21 | 山东大学齐鲁医院 | Digestive endoscopy structured diagnosis report generation method and system based on image recognition |
| CN112712879A (en) * | 2021-01-18 | 2021-04-27 | 腾讯科技（深圳）有限公司 | Information extraction method, device, equipment and storage medium for medical image report |
| CN113268569A (en) * | 2021-07-19 | 2021-08-17 | 中国电子科技集团公司第十五研究所 | Semantic-based related word searching method and device, electronic equipment and storage medium |
| CN114330267A (en) * | 2021-12-02 | 2022-04-12 | 华中科技大学同济医学院附属协和医院 | Structural report template design method based on semantic association |
-
2022
- 2022-06-30 CN CN202210759471.5A patent/CN115270779B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110688855A (en) * | 2019-09-29 | 2020-01-14 | 山东师范大学 | Chinese medical entity identification method and system based on machine learning |
| CN111048170A (en) * | 2019-12-23 | 2020-04-21 | 山东大学齐鲁医院 | Digestive endoscopy structured diagnosis report generation method and system based on image recognition |
| CN112712879A (en) * | 2021-01-18 | 2021-04-27 | 腾讯科技（深圳）有限公司 | Information extraction method, device, equipment and storage medium for medical image report |
| CN113268569A (en) * | 2021-07-19 | 2021-08-17 | 中国电子科技集团公司第十五研究所 | Semantic-based related word searching method and device, electronic equipment and storage medium |
| CN114330267A (en) * | 2021-12-02 | 2022-04-12 | 华中科技大学同济医学院附属协和医院 | Structural report template design method based on semantic association |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115270779A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10831762B2 (en) | Extracting and denoising concept mentions using distributed representations of concepts | |
| US10740678B2 (en) | Concept hierarchies | |
| CN110705206B (en) | Text information processing method and related device | |
| CN112632225B (en) | Semantic searching method and device based on case and event knowledge graph and electronic equipment | |
| US20230130006A1 (en) | Method of processing video, method of quering video, and method of training model | |
| CN110188359B (en) | Text entity extraction method | |
| EP4361843A1 (en) | Neural network searching method and related device | |
| CN112434718B (en) | New coronary pneumonia multi-modal feature extraction fusion method and system based on depth map | |
| CN114328919A (en) | Text content classification method and device, electronic equipment and storage medium | |
| CN110969005B (en) | Method and device for determining similarity between entity corpora | |
| CN115270779B (en) | Method and system for generating ulcerative colitis structured report | |
| CN115457329B (en) | Training method of image classification model, image classification method and device | |
| CN114637852B (en) | Entity relation extraction method, device, equipment and storage medium of medical text | |
| Vijayaraju | Image retrieval using image captioning | |
| CN112800244B (en) | Method for constructing knowledge graph of traditional Chinese medicine and national medicine | |
| CN115798661A (en) | Knowledge mining method and device in clinical medicine field | |
| CN114417016A (en) | Knowledge graph-based text information matching method and device and related equipment | |
| CN115114437A (en) | Gastroscope text classification system based on BERT and double-branch network | |
| CN114842301A (en) | Semi-supervised training method of image annotation model | |
| US11270155B2 (en) | Duplicate image detection based on image content | |
| CN114491076A (en) | Data enhancement method, device, equipment and medium based on domain knowledge graph | |
| Mishra et al. | Multimodal machine learning for extraction of theorems and proofs in the scientific literature | |
| CN113313126A (en) | Method, computing device, and computer storage medium for image recognition | |
| CN117235605B (en) | Sensitive information classification method and device based on multi-mode attention fusion | |
| CN116883886B (en) | Weak supervision time sequence language positioning method and device based on two-stage comparison learning and noise robustness |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |