CN111613299A - Multi-label analysis technology of traditional Chinese medicine data - Google Patents
Multi-label analysis technology of traditional Chinese medicine data Download PDFInfo
- Publication number
- CN111613299A CN111613299A CN202010541835.3A CN202010541835A CN111613299A CN 111613299 A CN111613299 A CN 111613299A CN 202010541835 A CN202010541835 A CN 202010541835A CN 111613299 A CN111613299 A CN 111613299A
- Authority
- CN
- China
- Prior art keywords
- sample
- label
- neural network
- image
- convolutional neural
- 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
- 239000003814 drug Substances 0.000 title claims abstract description 42
- 238000004458 analytical method Methods 0.000 title claims abstract description 23
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000000007 visual effect Effects 0.000 claims abstract description 8
- 238000000034 method Methods 0.000 claims description 17
- 239000013598 vector Substances 0.000 claims description 6
- 238000013145 classification model Methods 0.000 claims description 3
- 238000003745 diagnosis Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
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
- G16H30/00—ICT specially adapted for the handling or processing of medical images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Computing Systems (AREA)
- Epidemiology (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Primary Health Care (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Image Analysis (AREA)
Abstract
The multi-label analysis technology of the traditional Chinese medicine data comprises the following specific steps: s1, collecting traditional Chinese medicine image data information to obtain a sample data set; s2, processing each sample image in the sample data set to obtain a plurality of groups of image samples; s3, performing multi-label processing on case labels labeled on each sample image in the sample data set to obtain a multi-label training sample set; s4, training the convolutional neural network through a plurality of groups of image samples and a multi-label training sample set to obtain a convolutional neural network case model; s5, constructing visual similar neighbor indexes of the sample images and the label groups according to the corresponding relation between each sample image in the sample data set A and the multi-label training sample set C in the convolutional neural network case model; and S6, inputting the acquired traditional Chinese medicine image data information to be analyzed into the convolutional neural network case model to acquire case data corresponding to the traditional Chinese medicine image data information to be analyzed. The invention can improve the efficiency of diagnosing the medical image data.
Description
Technical Field
The invention relates to the technical field of medical data analysis, in particular to a multi-label analysis technology of traditional Chinese medicine data.
Background
The combination of traditional Chinese medicine and western medicine combines the knowledge and method of traditional Chinese medicine with the knowledge and method of western medicine, so as to clarify the mechanism and further obtain a new approach for medical understanding on the basis of improving the clinical curative effect. The combination of traditional Chinese and western medicine is a long-term policy implemented by the government after the establishment of the people's republic of China. The combination of traditional Chinese medicine and western medicine is the cross field of traditional Chinese medicine and western medicine, and is a work policy of Chinese medical health career. The combination of traditional Chinese medicine and western medicine is developed in clinical practice, and gradually evolves to an academic system with a definite development target and a unique methodology; when a doctor visits a patient in a department combining traditional Chinese medicine and western medicine, the doctor usually needs to analyze and judge the image information of the patient so as to judge the state of the patient, and finally, a treatment scheme is formulated according to the state of the patient, but the image information of the patient is analyzed and judged, long experience accumulation is usually needed to accurately judge, a large amount of time is still needed in the process of analyzing the state of the patient, and the treatment efficiency of the patient is greatly reduced; the present application proposes a multi-label analysis technique for traditional Chinese medicine data.
Disclosure of Invention
Objects of the invention
In order to solve the technical problems in the background technology, the invention provides a multi-label analysis technology of traditional Chinese medicine data, and the invention can improve the efficiency of diagnosing the image data of the mid-inhalation medicine.
(II) technical scheme
In order to solve the problems, the invention provides a multi-label analysis technology of traditional Chinese medicine data, which comprises the following specific steps:
s1, collecting traditional Chinese medicine image data information to obtain a sample data set A;
s2, processing each sample image in the sample data set A to obtain a plurality of groups of image samples B;
s3, performing multi-label processing on case labels labeled on each sample image in the sample data set A, and mapping the same number of labels on each sample image to obtain a multi-label training sample set C;
s4, taking a plurality of groups of image samples B as the input of a multi-output convolutional neural network, taking a multi-label training sample set C as the output, and training the convolutional neural network to obtain a convolutional neural network case model;
s5, constructing visual similar neighbor indexes of the sample images and the label groups according to the corresponding relation between each sample image in the sample data set A and the multi-label training sample set C in the convolutional neural network case model;
and S6, inputting the acquired traditional Chinese medicine image data information to be analyzed into the convolutional neural network case model to acquire case data corresponding to the traditional Chinese medicine image data information to be analyzed.
Preferably, the convolutional neural network is an arbitrary network structure.
Preferably, the chinese medical science image data information in S1 is image data after a confirmed diagnosis of a case analysis has been performed.
Preferably, the method for constructing the visually similar neighbor indexes of the sample image and the tag group in S5 includes the following specific steps:
s51, constructing a high-dimensional feature vector based on the corresponding relation between each sample image in the sample data set A and the multi-label training sample set C;
and S52, establishing visual semantic similarity nearest neighbor indexes of distance measurement for the high-dimensional feature vectors in a mode of combining sample image based and quantization based.
Preferably, the concrete steps of obtaining the convolutional neural network case model in S4 include:
s41, constructing a two-classification model for each label by utilizing a multi-label training sample set C;
s42, taking a plurality of groups of image samples B as the input of a multi-output convolutional neural network, and taking a multi-label training sample set C as the output;
and S43, training the convolutional neural network by using a cross loss function of the real output and the expected output of the convolutional neural network model as an objective function of network training to obtain a convolutional neural network case model.
Preferably, in S2, the region in each sample image that can represent the case features is cut to obtain a plurality of sets of image samples B.
The technical scheme of the invention has the following beneficial technical effects:
when the system is used, the past traditional Chinese medicine image data information is collected, the obtained traditional Chinese medicine image data information is processed, the traditional Chinese medicine image data information is obtained from the interior of a hospital, the data acquisition is convenient, the reality and the effectiveness of the acquired data can be ensured, and the accuracy of the analysis result of the traditional Chinese medicine image data information is ensured; in addition, the invention carries out disease analysis based on the trained convolutional neural network model, has shorter running time and greatly improves the efficiency of inquiry.
Drawings
Fig. 1 is a flow chart of a method of the multi-label analysis technique of chinese medical data according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings in conjunction with the following detailed description. It should be understood that the description is intended to be exemplary only, and is not intended to limit the scope of the present invention. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present invention.
As shown in fig. 1, the multi-label analysis technique for chinese medical data provided by the present invention comprises the following specific steps:
s1, collecting traditional Chinese medicine image data information to obtain a sample data set A;
s2, processing each sample image in the sample data set A to obtain a plurality of groups of image samples B;
s3, performing multi-label processing on case labels labeled on each sample image in the sample data set A, and mapping the same number of labels on each sample image to obtain a multi-label training sample set C;
s4, taking a plurality of groups of image samples B as the input of a multi-output convolutional neural network, taking a multi-label training sample set C as the output, and training the convolutional neural network to obtain a convolutional neural network case model;
s5, constructing visual similar neighbor indexes of the sample images and the label groups according to the corresponding relation between each sample image in the sample data set A and the multi-label training sample set C in the convolutional neural network case model;
and S6, inputting the acquired traditional Chinese medicine image data information to be analyzed into the convolutional neural network case model to acquire case data corresponding to the traditional Chinese medicine image data information to be analyzed.
When the system is used, the past traditional Chinese medicine image data information is collected, the obtained traditional Chinese medicine image data information is processed, the traditional Chinese medicine image data information is obtained from the interior of a hospital, the data acquisition is convenient, the reality and the effectiveness of the acquired data can be ensured, and the accuracy of the analysis result of the traditional Chinese medicine image data information is ensured; in addition, the invention carries out disease analysis based on the trained convolutional neural network model, has shorter running time and greatly improves the efficiency of inquiry.
In an alternative embodiment, the convolutional neural network is an arbitrary network structure.
In an alternative embodiment, the chinese medical image data information in S1 is image data after the confirmed diagnosis of case analysis has been performed, and a convolutional neural network model is constructed according to the confirmed chinese medical image data information, so as to ensure accuracy of disease analysis performed on the chinese medical image data information to be analyzed.
In an alternative embodiment, the method for constructing the visual similarity neighbor index of the sample image and the tag group in S5 includes the following specific steps:
s51, constructing a high-dimensional feature vector based on the corresponding relation between each sample image in the sample data set A and the multi-label training sample set C;
and S52, establishing visual semantic similarity nearest neighbor indexes of distance measurement for the high-dimensional feature vectors in a mode of combining sample image based and quantization based.
In an alternative embodiment, the concrete steps of obtaining the convolutional neural network case model in S4 include:
s41, constructing a two-classification model for each label by utilizing a multi-label training sample set C;
s42, taking a plurality of groups of image samples B as the input of a multi-output convolutional neural network, and taking a multi-label training sample set C as the output;
and S43, training the convolutional neural network by using a cross loss function of the real output and the expected output of the convolutional neural network model as an objective function of network training to obtain a convolutional neural network case model.
In an alternative embodiment, the region in each sample image that can represent the case features is cut in S2 to obtain a plurality of sets of image samples B.
It is to be understood that the above-described embodiments of the present invention are merely illustrative of or explaining the principles of the invention and are not to be construed as limiting the invention. Therefore, any modification, equivalent replacement, improvement and the like made without departing from the spirit and scope of the present invention should be included in the protection scope of the present invention. Further, it is intended that the appended claims cover all such variations and modifications as fall within the scope and boundaries of the appended claims or the equivalents of such scope and boundaries.
Claims (6)
1. The multi-label analysis technology of the traditional Chinese medicine data is characterized by comprising the following specific steps of:
s1, collecting traditional Chinese medicine image data information to obtain a sample data set A;
s2, processing each sample image in the sample data set A to obtain a plurality of groups of image samples B;
s3, performing multi-label processing on case labels labeled on each sample image in the sample data set A, and mapping the same number of labels on each sample image to obtain a multi-label training sample set C;
s4, taking a plurality of groups of image samples B as the input of a multi-output convolutional neural network, taking a multi-label training sample set C as the output, and training the convolutional neural network to obtain a convolutional neural network case model;
s5, constructing visual similar neighbor indexes of the sample images and the label groups according to the corresponding relation between each sample image in the sample data set A and the multi-label training sample set C in the convolutional neural network case model;
and S6, inputting the acquired traditional Chinese medicine image data information to be analyzed into the convolutional neural network case model to acquire case data corresponding to the traditional Chinese medicine image data information to be analyzed.
2. The technique for multi-label analysis of chinese medical data according to claim 1, wherein the convolutional neural network is of an arbitrary network structure.
3. The technique for multi-label analysis of chinese medical data according to claim 1, wherein the chinese medical image data information in S1 is image data after a confirmed diagnosis of a case analysis has been performed.
4. The technique for multi-tag analysis of chinese medical data according to claim 1, wherein the method for constructing the visually similar neighborhood index of the sample image and the tag group in S5 comprises the following steps:
s51, constructing a high-dimensional feature vector based on the corresponding relation between each sample image in the sample data set A and the multi-label training sample set C;
and S52, establishing visual semantic similarity nearest neighbor indexes of distance measurement for the high-dimensional feature vectors in a mode of combining sample image based and quantization based.
5. The multi-label analysis technique for chinese medical data according to claim 1, wherein the concrete steps of obtaining the convolutional neural network case model in S4 include:
s41, constructing a two-classification model for each label by utilizing a multi-label training sample set C;
s42, taking a plurality of groups of image samples B as the input of a multi-output convolutional neural network, and taking a multi-label training sample set C as the output;
and S43, training the convolutional neural network by using a cross loss function of the real output and the expected output of the convolutional neural network model as an objective function of network training to obtain a convolutional neural network case model.
6. The technique for multi-label analysis of chinese medical data according to claim 1, wherein the region where the characteristics of the case are represented in each sample image is cut in S2 to obtain a plurality of sets of image samples B.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010541835.3A CN111613299A (en) | 2020-06-15 | 2020-06-15 | Multi-label analysis technology of traditional Chinese medicine data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010541835.3A CN111613299A (en) | 2020-06-15 | 2020-06-15 | Multi-label analysis technology of traditional Chinese medicine data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN111613299A true CN111613299A (en) | 2020-09-01 |
Family
ID=72202628
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010541835.3A Pending CN111613299A (en) | 2020-06-15 | 2020-06-15 | Multi-label analysis technology of traditional Chinese medicine data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111613299A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106250915A (en) * | 2016-07-22 | 2016-12-21 | 福州大学 | A kind of automatic image marking method merging depth characteristic and semantic neighborhood |
CN108520780A (en) * | 2018-03-07 | 2018-09-11 | 中国科学院计算技术研究所 | A kind of medical data processing and system based on transfer learning |
CN109101938A (en) * | 2018-08-23 | 2018-12-28 | 武汉嫦娥医学抗衰机器人股份有限公司 | A kind of multi-tag age estimation method based on convolutional neural networks |
CN109783682A (en) * | 2019-01-19 | 2019-05-21 | 北京工业大学 | It is a kind of based on putting non-to the depth of similarity loose hashing image search method |
EP3545468A1 (en) * | 2016-11-25 | 2019-10-02 | Contextflow GmbH | Method and a system for creating a medical image database by means of a convolutional neural network |
CN110472090A (en) * | 2019-08-20 | 2019-11-19 | 腾讯科技(深圳)有限公司 | Image search method and relevant apparatus, storage medium based on semantic label |
CN110795590A (en) * | 2019-09-30 | 2020-02-14 | 武汉大学 | Multi-label image retrieval method and device based on direct-push zero-sample hash |
-
2020
- 2020-06-15 CN CN202010541835.3A patent/CN111613299A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106250915A (en) * | 2016-07-22 | 2016-12-21 | 福州大学 | A kind of automatic image marking method merging depth characteristic and semantic neighborhood |
EP3545468A1 (en) * | 2016-11-25 | 2019-10-02 | Contextflow GmbH | Method and a system for creating a medical image database by means of a convolutional neural network |
CN108520780A (en) * | 2018-03-07 | 2018-09-11 | 中国科学院计算技术研究所 | A kind of medical data processing and system based on transfer learning |
CN109101938A (en) * | 2018-08-23 | 2018-12-28 | 武汉嫦娥医学抗衰机器人股份有限公司 | A kind of multi-tag age estimation method based on convolutional neural networks |
CN109783682A (en) * | 2019-01-19 | 2019-05-21 | 北京工业大学 | It is a kind of based on putting non-to the depth of similarity loose hashing image search method |
CN110472090A (en) * | 2019-08-20 | 2019-11-19 | 腾讯科技(深圳)有限公司 | Image search method and relevant apparatus, storage medium based on semantic label |
CN110795590A (en) * | 2019-09-30 | 2020-02-14 | 武汉大学 | Multi-label image retrieval method and device based on direct-push zero-sample hash |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Mijwil et al. | From Pixels to Diagnoses: Deep Learning's Impact on Medical Image Processing-A Survey | |
CN109544518B (en) | Method and system applied to bone maturity assessment | |
CN111161822A (en) | Medical image artificial intelligence diagnosis data management system and management method thereof | |
CN113241135A (en) | Disease risk prediction method and system based on multi-mode fusion | |
CN111564223B (en) | Infectious disease survival probability prediction method, and prediction model training method and device | |
Salpea et al. | Medical image segmentation: A review of modern architectures | |
CN106934235A (en) | Patient's similarity measurement migratory system between a kind of disease areas based on transfer learning | |
CN105342569A (en) | Mental state detection system based on electroencephalogram analysis | |
CN112466462B (en) | EMR information association and evolution method based on deep learning of image | |
CN114582496A (en) | Common gynecological disease prediction model construction method and prediction system | |
CN112365976A (en) | Compound disease clinical path construction method and system based on transfer learning | |
CN113722507A (en) | Hospital cost prediction method and device based on knowledge graph and computer equipment | |
CN114283406A (en) | Cell image recognition method, device, equipment, medium and computer program product | |
CN116543917A (en) | Information mining method for heterogeneous time sequence data | |
CN111613299A (en) | Multi-label analysis technology of traditional Chinese medicine data | |
Bao et al. | Application research of artificial intelligence in medical information system | |
Amruthalingam et al. | Objective hand eczema severity assessment with automated lesion anatomical stratification | |
Ferber et al. | In-context learning enables multimodal large language models to classify cancer pathology images | |
CN114678126A (en) | Disease tracking and predicting system | |
CN113553840A (en) | Text information processing method, device, equipment and storage medium | |
WO2021021430A1 (en) | System and method for region detection in tissue sections using image registration | |
CN110889836A (en) | Image data analysis method and device, terminal equipment and storage medium | |
Chanchaichujit et al. | Application of artificial intelligence in healthcare | |
CN111920430A (en) | Automatic bone age assessment method for weak supervised deep learning | |
CN110660479A (en) | AI training and diagnosis system for dynamic medical image |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200901 |