CN117936079A - Manifold learning-based diabetic retinopathy identification method, medium and system - Google Patents
Manifold learning-based diabetic retinopathy identification method, medium and system Download PDFInfo
- Publication number
- CN117936079A CN117936079A CN202410327013.3A CN202410327013A CN117936079A CN 117936079 A CN117936079 A CN 117936079A CN 202410327013 A CN202410327013 A CN 202410327013A CN 117936079 A CN117936079 A CN 117936079A
- Authority
- CN
- China
- Prior art keywords
- matrix
- diabetic retinopathy
- manifold learning
- patient
- item
- 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 49
- 206010012689 Diabetic retinopathy Diseases 0.000 title claims abstract description 41
- 239000011159 matrix material Substances 0.000 claims abstract description 95
- 230000006870 function Effects 0.000 claims abstract description 14
- 238000003384 imaging method Methods 0.000 claims abstract description 14
- 239000013598 vector Substances 0.000 claims abstract description 10
- 238000013507 mapping Methods 0.000 claims abstract description 7
- 239000008280 blood Substances 0.000 claims description 22
- 210000004369 blood Anatomy 0.000 claims description 22
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims description 16
- 239000008103 glucose Substances 0.000 claims description 16
- 238000012549 training Methods 0.000 claims description 16
- 206010012601 diabetes mellitus Diseases 0.000 claims description 13
- 238000007689 inspection Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 8
- 235000012054 meals Nutrition 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000004438 eyesight Effects 0.000 claims description 6
- NOESYZHRGYRDHS-UHFFFAOYSA-N insulin Chemical compound N1C(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(NC(=O)CN)C(C)CC)CSSCC(C(NC(CO)C(=O)NC(CC(C)C)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CCC(N)=O)C(=O)NC(CC(C)C)C(=O)NC(CCC(O)=O)C(=O)NC(CC(N)=O)C(=O)NC(CC=2C=CC(O)=CC=2)C(=O)NC(CSSCC(NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2C=CC(O)=CC=2)NC(=O)C(CC(C)C)NC(=O)C(C)NC(=O)C(CCC(O)=O)NC(=O)C(C(C)C)NC(=O)C(CC(C)C)NC(=O)C(CC=2NC=NC=2)NC(=O)C(CO)NC(=O)CNC2=O)C(=O)NCC(=O)NC(CCC(O)=O)C(=O)NC(CCCNC(N)=N)C(=O)NCC(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC=CC=3)C(=O)NC(CC=3C=CC(O)=CC=3)C(=O)NC(C(C)O)C(=O)N3C(CCC3)C(=O)NC(CCCCN)C(=O)NC(C)C(O)=O)C(=O)NC(CC(N)=O)C(O)=O)=O)NC(=O)C(C(C)CC)NC(=O)C(CO)NC(=O)C(C(C)O)NC(=O)C1CSSCC2NC(=O)C(CC(C)C)NC(=O)C(NC(=O)C(CCC(N)=O)NC(=O)C(CC(N)=O)NC(=O)C(NC(=O)C(N)CC=1C=CC=CC=1)C(C)C)CC1=CN=CN1 NOESYZHRGYRDHS-UHFFFAOYSA-N 0.000 claims description 6
- 230000000740 bleeding effect Effects 0.000 claims description 5
- 102000017011 Glycated Hemoglobin A Human genes 0.000 claims description 4
- 108010014663 Glycated Hemoglobin A Proteins 0.000 claims description 4
- 206010038848 Retinal detachment Diseases 0.000 claims description 4
- 230000004264 retinal detachment Effects 0.000 claims description 4
- 208000007342 Diabetic Nephropathies Diseases 0.000 claims description 3
- 208000031226 Hyperlipidaemia Diseases 0.000 claims description 3
- 206010020772 Hypertension Diseases 0.000 claims description 3
- 102000004877 Insulin Human genes 0.000 claims description 3
- 108090001061 Insulin Proteins 0.000 claims description 3
- 208000033679 diabetic kidney disease Diseases 0.000 claims description 3
- 229940125396 insulin Drugs 0.000 claims description 3
- 208000033808 peripheral neuropathy Diseases 0.000 claims description 2
- 238000010801 machine learning Methods 0.000 abstract description 8
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 208000032843 Hemorrhage Diseases 0.000 description 6
- 238000003745 diagnosis Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 3
- 238000013399 early diagnosis Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 210000004204 blood vessel Anatomy 0.000 description 2
- 238000002790 cross-validation Methods 0.000 description 2
- 239000011521 glass Substances 0.000 description 2
- 238000012014 optical coherence tomography Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 208000032131 Diabetic Neuropathies Diseases 0.000 description 1
- 206010061818 Disease progression Diseases 0.000 description 1
- 208000001344 Macular Edema Diseases 0.000 description 1
- 206010025415 Macular oedema Diseases 0.000 description 1
- 206010029113 Neovascularisation Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 230000005750 disease progression Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 230000003902 lesion Effects 0.000 description 1
- 201000010230 macular retinal edema Diseases 0.000 description 1
- 230000001575 pathological effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000011425 standardization method Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of diabetic retinopathy identification, in particular to a method, medium and system for identifying diabetic retinopathy based on manifold learning. The recognition method of diabetic retinopathy based on manifold learning comprises inputting patient imaging examination result, extracting feature vector, splicing to form imaging feature matrix, and marking corresponding image to form examination result matrix; inputting physiological characteristics of a patient, and checking a checking result to construct a Laplacian matrix; constructing a prediction function by using a feature matrix and a Laplacian matrix based on manifold learning theory; solving to obtain an optimized mapping matrix; a predictive score matrix is calculated. The invention combines a plurality of machine learning techniques and improves the accuracy and the robustness of the model. The model can provide accurate and reliable auxiliary diagnostic tools for ophthalmologists, is beneficial to early discovery of diabetic retinopathy, improves treatment effect and reduces social and family burden.
Description
Technical Field
The invention relates to the crossing technical field of artificial intelligence and diabetic retinopathy identification, in particular to a method, medium and system for identifying diabetic retinopathy based on manifold learning.
Background
Diabetic retinopathy (Diabetic Retinopathy, DR) is one of the most common complications of diabetics, severely affecting the eyesight and quality of life of the patient. Early DR patients often have no obvious symptoms, but progressive DR can cause macular edema, neovascularization with secondary glass-volumetric blood and even retinal detachment, etc., with significant vision hazards. Together with the irreversibility of DR disease progression, early diagnosis and treatment are therefore critical for preventing and alleviating progression of DR lesions. In clinic, diagnosis of DR mainly depends on experienced fundus disease specialists to directly perform fundus examination on a patient or observe and evaluate fundus images of the patient.
The traditional fundus image analysis method has a plurality of problems such as difficult feature extraction, low classification accuracy and the like. The disclosed deep learning model (such as CN116152229B, a method for constructing a diabetic retinopathy diagnosis model and a diagnosis model) can extract pathological features from marked data, but has the defects of poor interpretability and the like. In addition, a single machine learning algorithm often cannot fully utilize information in fundus images, resulting in low recognition accuracy. Secondly, the existing method has the problems of difficult feature selection, complex model fusion and the like when processing fundus images, and limits the application of the method in diabetic retinopathy identification.
In recent years, machine learning techniques have made remarkable progress in the field of medical image analysis. Manifold learning is a technique that takes into account data distribution characteristics, and can effectively extract important characteristics of unlabeled samples in fundus images. Subspace regression is a regression method based on subspace decomposition, and the fitting capacity and generalization capacity of a model are improved by communicating local and whole. Sparse learning is a method for extracting features through sparse representation, and can reduce redundant features and noise interference.
Therefore, the invention provides a method, medium and system for identifying diabetic retinopathy based on manifold learning, aiming at improving the accuracy and efficiency of early diagnosis of diabetic retinopathy. The method integrates various machine learning technologies such as manifold learning, subspace regression, sparse learning and the like, combines the method into a unified model by constructing a loss function, can fully utilize information in fundus images, and improves recognition accuracy and robustness.
Disclosure of Invention
The invention aims to provide a manifold learning-based diabetic retinopathy identification method, medium and system with simple feature extraction and high accuracy.
In order to solve the problems, the technical scheme provided by the invention is as follows: a method for identifying diabetic retinopathy based on manifold learning comprises
Step one, inputting a patient imaging examination result, extracting feature vectors, splicing to form an imaging feature matrix, and marking a corresponding image to form an examination result matrix, wherein the method specifically comprises the following steps:
Inputting the image inspection results of the color fundus photography and optical coherence tomography of a patient, extracting three types of characteristics of a color correlation chart, a wavelet texture and an edge direction histogram to form characteristic vectors, splicing the characteristic vectors of each image to form an imaging characteristic matrix, marking as X, wherein the number of lines is the image sample quantity n, and the number of columns is the characteristic number; marking each inspection result image in sequence according to a given column, wherein the corresponding columns are respectively: microangioma, hard exudation, punctiform hemorrhage, flaky hemorrhage, soft exudation, glass volume blood, new blood vessel, microangioma, multiple bleeding points, fibroplasia, retinal detachment, if the conditions are met, the corresponding position is marked as 1, otherwise, the corresponding position is marked as 0, an inspection result matrix is marked as Y, the number of lines of the matrix Y is the image sample quantity n, and the number of columns is the result characteristic number;
Inputting physiological characteristics of a patient and checking results, and constructing a Laplacian matrix L, wherein the method comprises the following steps of:
physiological characteristics, inspection test results, specifically include: vision, age, sex, family history of diabetes, course of diabetes, type 1/2 diabetes, whether diabetic nephropathy is associated, whether peripheral neuropathy is associated, and fasting blood glucose levels; glycosylated hemoglobin, 7 random blood glucose values (blood glucose before meal and blood glucose after meal for two hours before sleep in the morning, in the evening), whether insulin is injected, whether hyperlipidemia, and a history of hypertension.
The method for constructing the Laplace matrix L comprises the following steps: firstly, standardizing quantitative data to a range of 0-1, then calculating Gaussian distances by using a Gaussian radial basis function to represent similarity between two cases of patients, wherein a matrix L is a patient similarity matrix which is obtained by summing according to columns and subtracting the patient similarity matrix from a diagonalized result;
Thirdly, constructing a prediction function by using a feature matrix and a Laplacian matrix based on manifold learning theory:
；
Wherein F is a prediction result scoring matrix (to be solved), and G is a mapping matrix (to be solved); item 1 is a laplace regularization item, where Tr () represents the trace of the matrix and T represents the transpose of the matrix; the 2 nd item is a reconstruction loss item, and the difference between the prediction score matrix and the original matrix is measured, wherein U represents a decision rule matrix; item 3 is a subspace regression term, and communicates a prediction result score matrix F and an imaging feature matrix X, wherein mu is a regularization coefficient, and I F represent a matrix F norm; item 4 is a matrix norm item, |·| 2,1 represents the L 2,1 matrix norm;
step four, solving the prediction function and outputting an optimized mapping matrix G;
Step five, calculating a prediction score matrix f=x T G.
A medium of a method for identifying diabetic retinopathy based on manifold learning, comprising a storage medium and a processing medium; the storage medium is used for storing fundus image data and parameters of the training model, and the processing medium is used for executing each step in the diabetic retinopathy identification method.
The system of the diabetic retinopathy recognition method based on manifold learning comprises an image acquisition module, a feature extraction module, a model training module and a recognition module; the image acquisition module is used for acquiring fundus image data of a diabetic patient, the characteristic extraction module is used for extracting manifold characteristic representation of the fundus image, the model training module is used for training an optimized prediction model, and the identification module is used for identifying diabetic retinopathy on a new fundus image.
The beneficial effects of the invention are as follows: the invention combines various machine learning technologies such as manifold learning, subspace regression, sparse learning and the like, fully utilizes the advantages of each machine, and improves the accuracy and the robustness of the model; the model can provide an accurate and reliable auxiliary diagnosis tool for doctors, is favorable for early discovery and identification of diabetic retinopathy, and improves the treatment effect and the life quality of patients.
Drawings
FIG. 1 is a flow chart of a method for recognition of diabetic retinopathy based on manifold learning;
FIG. 2 is a frame diagram of a diabetic retinopathy identification medium based on manifold learning;
Fig. 3 is a block diagram of a manifold learning based diabetic retinopathy identification system.
Detailed Description
Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in FIG. 1, a method for identifying diabetic retinopathy based on manifold learning comprises
Inputting imaging examination results of a patient color fundus camera and optical coherence tomography, extracting three types of features, including a color correlation diagram, wavelet textures and edge direction histograms to form feature vectors, splicing the feature vectors of each image to form an imaging feature matrix, marking the feature matrix as X, wherein the number of rows of the matrix X is the number of images n, and the number of columns is the feature number, if 345, marking each examination result image in sequence according to a given column, and the corresponding columns are respectively: microangioma, hard exudation, punctiform hemorrhage, flaky hemorrhage, soft exudation, glass volume blood, new blood vessel, microangioma, multiple bleeding points, fibroplasia, retinal detachment, if the conditions are met, the corresponding position is marked as1, otherwise, the corresponding position is marked as 0, an inspection result matrix is marked as Y, the number of lines of the matrix Y is the number of images n, and the number of columns is the number of result characteristics 8;
Inputting physiological characteristics of a patient and checking results, and constructing a Laplacian matrix L, wherein the method comprises the following steps of:
Physiological characteristics, inspection test results, specifically include: vision, age, sex, family history of diabetes, course of diabetes (time to diabetes), type 1/2 of diabetes, whether to incorporate diabetic nephropathy, whether to incorporate diabetic peripheral neuropathy, fasting blood glucose (fasting blood glucose is the venous blood glucose value in the morning); glycosylated hemoglobin, 7 random blood glucose values (blood glucose before meal and blood glucose after meal for two hours before sleep, fingertip blood glucose values) whether insulin is injected, whether hyperlipidemia, and a history of hypertension;
The method for constructing the Laplace matrix L comprises the following steps: firstly, standardizing the physiological characteristics of a patient and quantitative data in an examination and test result to a range of 0-1, and in this case, scaling eyesight, age, glycosylated hemoglobin, random blood sugar and blood fat to a range of 0,1 by using a 0-1 standardization method; then, gaussian radial basis function G (p i,pj) = exp(-||pi-pj||2/gamma) is used to calculate Gaussian distance, G (p i,pj) represents similarity between corresponding input vectors p i and p j of two cases of patients, wherein ||·| represents the euclidean distance is used to determine, gamma is the width parameter of the gaussian function, here taken as 1; the matrix L is the patient similarity matrix subtracted from the diagonalized result after summing the patient similarity matrix according to columns;
Thirdly, constructing a prediction function by using a feature matrix and a Laplacian matrix based on manifold learning theory:
；
Wherein F is a prediction result scoring matrix (to be solved), and G is a mapping matrix (to be solved); item 1 is a laplace regularization item, where Tr () represents the trace of the matrix and T represents the transpose of the matrix; the 2 nd item is a reconstruction loss item, and the difference between the prediction score matrix and the original matrix is measured, wherein U represents a decision rule matrix; item 3 is a subspace regression term, and communicates a prediction result score matrix F and an imaging feature matrix X, wherein mu is a regularization coefficient, and I F represent a matrix F norm; item 4 is a matrix norm item, |·| 2,1 represents the L 2,1 matrix norm;
step four, solving the prediction function, inputting an imaging feature matrix X, checking a result matrix Y, a manifold regularization matrix L and taking a unit matrix from the decision rule matrix U; calculating an intermediate process matrix Wherein A is the full one matrix of equal size minus one-half the number of samples, and then the intermediate process matrix/>, is calculatedCalculating the intermediate process matrix/>Let the number of loops t=0, randomly initialize G 0, repeatedly calculate the diagonal matrix D t, update/>Where t=t+l until convergence; and (3) outputting: optimizing the mapping matrix G;
step five, calculating a prediction score matrix F=X T G;
in the actual use process of the model, five-fold cross validation is used for further optimizing parameters. The five-fold cross validation method evaluates the diabetic retinopathy identification model as follows: first, the entire data set is randomly divided into five mutually exclusive subsets, four of which serve as training sets for the model and the other as verification set. Then, a different subset is selected as the verification set at a time, and the rest are used as training sets. During each training process, the model is trained using a training set and performance assessment is performed on a validation set. Finally, we average the five validation results to arrive at a final performance assessment index for the model, including but not limited to accuracy, sensitivity, specificity, etc. The performance of the model is evaluated through five-fold cross verification, and the performance of the model in different parameters is verified, so that the parameters are further optimized, and the robustness and the reliability of the model are ensured.
As shown in fig. 2, the medium of the manifold learning-based diabetic retinopathy identification method comprises a storage medium and a processing medium; the storage medium is used for storing fundus image data and parameters of the training model, and the processing medium is used for executing each step in the diabetic retinopathy identification method.
As shown in fig. 3, the system of the recognition method of diabetic retinopathy based on manifold learning comprises an image acquisition module, a feature extraction module, a model training module and a recognition module; the image acquisition module is used for acquiring fundus image data of a diabetic patient, the characteristic extraction module is used for extracting manifold characteristic representation of the fundus image, the model training module is used for training an optimized prediction model, and the identification module is used for identifying diabetic retinopathy on a new fundus image.
Working principle: the invention provides a manifold learning-based diabetic retinopathy identification method, medium and system, aiming at improving the early diagnosis accuracy and efficiency of diabetic retinopathy. The method integrates various machine learning technologies such as manifold learning, subspace regression, sparse learning and the like, and can fully utilize information in fundus images by constructing a loss function combination into a unified model, thereby improving recognition accuracy and robustness. The invention combines various machine learning technologies such as manifold learning, subspace regression, sparse learning and the like, fully utilizes the advantages of each machine learning technology, improves the accuracy and the robustness of the model, can provide an accurate and reliable auxiliary diagnosis tool for doctors, is beneficial to early discovery and treatment of diabetic retinopathy identification, and improves the treatment effect and the life quality of patients.
The invention and its embodiments have been described above with no limitation, and the actual construction is not limited to the embodiments of the invention as shown in the drawings. In summary, if one of ordinary skill in the art is informed by this disclosure, a structural manner and an embodiment similar to the technical solution should not be creatively devised without departing from the gist of the present invention.
Claims (6)
1. The method for identifying the diabetic retinopathy based on manifold learning is characterized by comprising the following steps of:
step one, inputting a patient imaging examination result, extracting feature vectors, splicing to form an imaging feature matrix, and marking a corresponding image to form an examination result matrix, wherein the method specifically comprises the following steps:
Inputting the patient image inspection result, extracting features to form feature vectors, and splicing the feature vectors to form an imaging feature matrix; marking each inspection result image in sequence according to a given column, marking the corresponding position as 1 if the inspection result images accord with the given column, and marking the corresponding position as 0 if the inspection result images accord with the given column, so as to form an inspection result matrix;
Inputting physiological characteristics of a patient and checking results, and constructing a Laplacian matrix L, wherein the method comprises the following steps of:
The method for constructing the Laplace matrix L comprises the following steps: firstly, standardizing quantitative data to a range of 0-1, then calculating Gaussian distances by using a Gaussian radial basis function to represent similarity between two cases of patients, wherein a matrix L is a patient similarity matrix which is obtained by summing according to columns and subtracting the patient similarity matrix from a diagonalized result;
Thirdly, constructing a prediction function by using a feature matrix and a Laplacian matrix based on manifold learning theory;
Step four, solving the prediction function and outputting an optimized mapping matrix;
and fifthly, calculating a prediction score matrix.
2. The manifold learning-based diabetic retinopathy identification method according to claim 1, wherein: in the first step, each inspection result image is marked in sequence according to a given column, and the corresponding columns are respectively: microangiomas, hard exudation, punctate bleeding, platelet bleeding, soft exudation, glass-volume blood, neovasculature, microangiomas, multiple bleeding sites, fibroplasia, retinal detachment.
3. The manifold learning-based diabetic retinopathy identification method according to claim 1, wherein: in the second step, the physiological characteristics and the checking and checking results specifically comprise: vision, age, sex, family history of diabetes, course of diabetes, type 1/2 diabetes, whether diabetic nephropathy is associated, whether peripheral neuropathy is associated, and fasting blood glucose levels; glycosylated hemoglobin, 7 random blood glucose values, whether insulin is injected, whether hyperlipidemia, and a history of hypertension, wherein the 7 random blood glucose values refer to a pre-meal blood glucose value of three meals a morning, a evening, a two hour meal and a pre-sleep blood glucose value.
4. The manifold learning-based diabetic retinopathy identification method according to claim 1, wherein: in the third step, the prediction function is:
；
Wherein F is a prediction result scoring matrix, Y is an inspection result matrix, G is a mapping matrix, F, G are all matrices to be solved; item 1 is a laplace regularization item, where Tr () represents the trace of the matrix and T represents the transpose of the matrix; the 2 nd item is a reconstruction loss item, and the difference between the prediction score matrix and the original matrix is measured, wherein U represents a decision rule matrix; item 3 is a subspace regression term, and communicates a prediction result score matrix F and an imaging feature matrix X, wherein mu is a regularization coefficient, and I F represent a matrix F norm; item 4 is a matrix norm item, |·| 2,1 represents the L 2,1 matrix norm.
5. The medium of the manifold learning-based diabetic retinopathy identification method according to claim 1, wherein: including a storage medium and a processing medium; the storage medium is used for storing fundus image data and parameters of the training model, and the processing medium is used for executing each step in the diabetic retinopathy identification method.
6. The system of manifold learning based diabetic retinopathy identification method according to claim 1, wherein: the system comprises an image acquisition module, a feature extraction module, a model training module and an identification module; the image acquisition module is used for acquiring fundus image data of a diabetic patient, the characteristic extraction module is used for extracting manifold characteristic representation of the fundus image, the model training module is used for training an optimized prediction model, and the identification module is used for identifying diabetic retinopathy on a new fundus image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410327013.3A CN117936079A (en) | 2024-03-21 | 2024-03-21 | Manifold learning-based diabetic retinopathy identification method, medium and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410327013.3A CN117936079A (en) | 2024-03-21 | 2024-03-21 | Manifold learning-based diabetic retinopathy identification method, medium and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117936079A true CN117936079A (en) | 2024-04-26 |
Family
ID=90761165
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410327013.3A Pending CN117936079A (en) | 2024-03-21 | 2024-03-21 | Manifold learning-based diabetic retinopathy identification method, medium and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117936079A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102722578A (en) * | 2012-05-31 | 2012-10-10 | 浙江大学 | Unsupervised cluster characteristic selection method based on Laplace regularization |
| CN105426923A (en) * | 2015-12-14 | 2016-03-23 | 北京科技大学 | Semi-supervised classification method and system |
| CN110767263A (en) * | 2019-10-18 | 2020-02-07 | 中国人民解放军陆军军医大学 | Non-coding RNA and disease associated prediction method based on sparse subspace learning |
| CN113160119A (en) * | 2021-02-04 | 2021-07-23 | 广州中医药大学第一附属医院 | Diabetic retinopathy image classification method based on deep learning |
| CN116386860A (en) * | 2022-12-22 | 2023-07-04 | 东北林业大学 | Diabetes and complications intelligent auxiliary prediction and diagnosis platform based on multiple modes |
| EP4231230A1 (en) * | 2022-02-18 | 2023-08-23 | Median Technologies | Method and system for computer aided diagnosis based on morphological characteristics extracted from 3-dimensional medical images |
| CN117455829A (en) * | 2023-03-30 | 2024-01-26 | 东北林业大学 | Anti-learning-based diabetic retinopathy detection algorithm |
| CN117612703A (en) * | 2023-11-24 | 2024-02-27 | 杭州电子科技大学 | Diabetes retinopathy classification method based on medical test indexes |
-
2024
- 2024-03-21 CN CN202410327013.3A patent/CN117936079A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102722578A (en) * | 2012-05-31 | 2012-10-10 | 浙江大学 | Unsupervised cluster characteristic selection method based on Laplace regularization |
| CN105426923A (en) * | 2015-12-14 | 2016-03-23 | 北京科技大学 | Semi-supervised classification method and system |
| CN110767263A (en) * | 2019-10-18 | 2020-02-07 | 中国人民解放军陆军军医大学 | Non-coding RNA and disease associated prediction method based on sparse subspace learning |
| CN113160119A (en) * | 2021-02-04 | 2021-07-23 | 广州中医药大学第一附属医院 | Diabetic retinopathy image classification method based on deep learning |
| EP4231230A1 (en) * | 2022-02-18 | 2023-08-23 | Median Technologies | Method and system for computer aided diagnosis based on morphological characteristics extracted from 3-dimensional medical images |
| WO2023156290A1 (en) * | 2022-02-18 | 2023-08-24 | Median Technologies | Method and system for computer aided diagnosis based on morphological characteristics extracted from 3-dimensional medical images |
| CN116386860A (en) * | 2022-12-22 | 2023-07-04 | 东北林业大学 | Diabetes and complications intelligent auxiliary prediction and diagnosis platform based on multiple modes |
| CN117455829A (en) * | 2023-03-30 | 2024-01-26 | 东北林业大学 | Anti-learning-based diabetic retinopathy detection algorithm |
| CN117612703A (en) * | 2023-11-24 | 2024-02-27 | 杭州电子科技大学 | Diabetes retinopathy classification method based on medical test indexes |
Non-Patent Citations (1)
| Title |
|---|
| EMON, MU (EMON, MINHAZ UDDIN): "Performance Analysis of Diabetic Retinopathy Prediction using Machine Learning Models", 《 PROCEEDINGS OF THE 6TH INTERNATIONAL CONFERENCE ON INVENTIVE COMPUTATION TECHNOLOGIES (ICICT 2021)》, 24 December 2021 (2021-12-24) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Carass et al. | Longitudinal multiple sclerosis lesion segmentation: resource and challenge | |
| Hassan et al. | Joint segmentation and quantification of chorioretinal biomarkers in optical coherence tomography scans: A deep learning approach | |
| Nasir et al. | Deep dr: Detection of diabetic retinopathy using a convolutional neural network | |
| CN109215035B (en) | Brain MRI hippocampus three-dimensional segmentation method based on deep learning | |
| Hassan et al. | CDC-Net: Cascaded decoupled convolutional network for lesion-assisted detection and grading of retinopathy using optical coherence tomography (OCT) scans | |
| CN110956610A (en) | Method and system for predicting thrombolytic curative effect of lower limb deep venous thrombosis based on sparse representation | |
| CN115035127A (en) | Retinal vessel segmentation method based on generative confrontation network | |
| Reddy et al. | Discovering optimal algorithm to predict diabetic retinopathy using novel assessment methods | |
| CN112926537A (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
| Shi et al. | Artifact-tolerant clustering-guided contrastive embedding learning for ophthalmic images in glaucoma | |
| Liu et al. | Weakly-supervised localization and classification of biomarkers in OCT images with integrated reconstruction and attention | |
| Li et al. | RPS‐Net: An effective retinal image projection segmentation network for retinal vessels and foveal avascular zone based on OCTA data | |
| Liu et al. | Retinal vessel segmentation using densely connected convolution neural network with colorful fundus images | |
| CN116564511A (en) | Chronic disease health state prediction method, device and equipment | |
| CN117936079A (en) | Manifold learning-based diabetic retinopathy identification method, medium and system | |
| Alshayeji et al. | Two-stage framework for diabetic retinopathy diagnosis and disease stage screening with ensemble learning | |
| US20240108276A1 (en) | Systems and Methods for Identifying Progression of Hypoxic-Ischemic Brain Injury | |
| CN116051545A (en) | Brain age prediction method for bimodal images | |
| Velia et al. | Retracted: Designing Diabetes Mellitus Detection System Based on Iridology with Convolutional Neural Network Modeling | |
| Burlina et al. | Artificial intelligence and deep learning in retinal image analysis | |
| CN114550910A (en) | Artificial intelligence-based ejection fraction retention type heart failure diagnosis and typing system | |
| CN112132782B (en) | Method and terminal for processing DME (DME) typing based on deep neural network | |
| CN117854139B (en) | Open angle glaucoma recognition method, medium and system based on sparse selection | |
| Vaidya | Diabetes Detection using Convolutional Neural Network through Feature Sequencing | |
| Ding et al. | Low-rank Domain Adaptive Method with Inter-class difference Constraint for Multi-site Autism Spectrum Disorder Identification |
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 |