Color fundus photograph-based diabetic retinopathy grading via label relaxed collaborative learning on deep features and radiomics features
IntroductionDiabetic retinopathy (DR) has long been recognized as a common complication of diabetes, making accurate automated grading of its severity essential. Color fundus photographs play a crucial role in the grading of DR. With the advancement of artificial intelligence technologies, numerous...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Cell and Developmental Biology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcell.2024.1513971/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553866607296512 |
|---|---|
| author | Chao Zhang Guanglei Sheng Jie Su Lian Duan |
| author_facet | Chao Zhang Guanglei Sheng Jie Su Lian Duan |
| author_sort | Chao Zhang |
| collection | DOAJ |
| description | IntroductionDiabetic retinopathy (DR) has long been recognized as a common complication of diabetes, making accurate automated grading of its severity essential. Color fundus photographs play a crucial role in the grading of DR. With the advancement of artificial intelligence technologies, numerous researchers have conducted studies on DR grading based on deep features and radiomic features extracted from color fundus photographs.MethodWe combine deep features and radiomic features to design a feature fusion algorithm. First, we utilize convolutional neural networks to extract deep features from color fundus photographs and employ radiomic methodologies to extract radiomic features. Subsequently, we design a label relaxation-based collaborative learning algorithm for feature fusion.ResultsWe validate the effectiveness of the proposed method on two fundus image datasets: the DR1 Dataset and the MESSIDOR Dataset. The proposed method achieved 96.86 of AUC on DR1 and 96.34 of AUC on MESSIDOR, which are better than state-of-the-art methods. Also, the divergence between the training AUC and testing AUC increases substantially after the removal of manifold regularization.ConclusionLabel relaxation can enhance the distinguishability of training samples in the label space, thereby improving the model's classification accuracy. Additionally, graph constraints based on manifold learning methods can mitigate overfitting caused by label relaxation. |
| format | Article |
| id | doaj-art-0bff9083864b468f86a4eaa5e0c3a94f |
| institution | Kabale University |
| issn | 2296-634X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cell and Developmental Biology |
| spelling | doaj-art-0bff9083864b468f86a4eaa5e0c3a94f2025-01-09T06:10:29ZengFrontiers Media S.A.Frontiers in Cell and Developmental Biology2296-634X2025-01-011210.3389/fcell.2024.15139711513971Color fundus photograph-based diabetic retinopathy grading via label relaxed collaborative learning on deep features and radiomics featuresChao Zhang0Guanglei Sheng1Jie Su2Lian Duan3School of Information Engineering, Suqian University, Suqian, Jiangsu, ChinaSchool of Computer Science and Engineering, Xi’an University of Technology, Xi’an, ChinaSchool of Information Engineering, Suqian University, Suqian, Jiangsu, ChinaDepartment of Medical Informatics, Nantong University, Nantong, Jiangsu, ChinaIntroductionDiabetic retinopathy (DR) has long been recognized as a common complication of diabetes, making accurate automated grading of its severity essential. Color fundus photographs play a crucial role in the grading of DR. With the advancement of artificial intelligence technologies, numerous researchers have conducted studies on DR grading based on deep features and radiomic features extracted from color fundus photographs.MethodWe combine deep features and radiomic features to design a feature fusion algorithm. First, we utilize convolutional neural networks to extract deep features from color fundus photographs and employ radiomic methodologies to extract radiomic features. Subsequently, we design a label relaxation-based collaborative learning algorithm for feature fusion.ResultsWe validate the effectiveness of the proposed method on two fundus image datasets: the DR1 Dataset and the MESSIDOR Dataset. The proposed method achieved 96.86 of AUC on DR1 and 96.34 of AUC on MESSIDOR, which are better than state-of-the-art methods. Also, the divergence between the training AUC and testing AUC increases substantially after the removal of manifold regularization.ConclusionLabel relaxation can enhance the distinguishability of training samples in the label space, thereby improving the model's classification accuracy. Additionally, graph constraints based on manifold learning methods can mitigate overfitting caused by label relaxation.https://www.frontiersin.org/articles/10.3389/fcell.2024.1513971/fulldiabetic retinopathy gradingcollaborative learningradiomic featureshighlevel deep featureslabel relaxation |
| spellingShingle | Chao Zhang Guanglei Sheng Jie Su Lian Duan Color fundus photograph-based diabetic retinopathy grading via label relaxed collaborative learning on deep features and radiomics features Frontiers in Cell and Developmental Biology diabetic retinopathy grading collaborative learning radiomic features highlevel deep features label relaxation |
| title | Color fundus photograph-based diabetic retinopathy grading via label relaxed collaborative learning on deep features and radiomics features |
| title_full | Color fundus photograph-based diabetic retinopathy grading via label relaxed collaborative learning on deep features and radiomics features |
| title_fullStr | Color fundus photograph-based diabetic retinopathy grading via label relaxed collaborative learning on deep features and radiomics features |
| title_full_unstemmed | Color fundus photograph-based diabetic retinopathy grading via label relaxed collaborative learning on deep features and radiomics features |
| title_short | Color fundus photograph-based diabetic retinopathy grading via label relaxed collaborative learning on deep features and radiomics features |
| title_sort | color fundus photograph based diabetic retinopathy grading via label relaxed collaborative learning on deep features and radiomics features |
| topic | diabetic retinopathy grading collaborative learning radiomic features highlevel deep features label relaxation |
| url | https://www.frontiersin.org/articles/10.3389/fcell.2024.1513971/full |
| work_keys_str_mv | AT chaozhang colorfundusphotographbaseddiabeticretinopathygradingvialabelrelaxedcollaborativelearningondeepfeaturesandradiomicsfeatures AT guangleisheng colorfundusphotographbaseddiabeticretinopathygradingvialabelrelaxedcollaborativelearningondeepfeaturesandradiomicsfeatures AT jiesu colorfundusphotographbaseddiabeticretinopathygradingvialabelrelaxedcollaborativelearningondeepfeaturesandradiomicsfeatures AT lianduan colorfundusphotographbaseddiabeticretinopathygradingvialabelrelaxedcollaborativelearningondeepfeaturesandradiomicsfeatures |