Color fundus photograph-based diabetic retinopathy grading via label relaxed collaborative learning on deep features and radiomics features
Label 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.
Authors
- Jie Su (ORCID: https://orcid.org/0000-0003-0534-3793)
- Lian Duan (ORCID: https://orcid.org/0000-0002-4213-474X)
- Guanglei Sheng
- Chao Zhang (ORCID: https://orcid.org/0000-0002-0152-2586)
Institutions
- Nantong University (CN)
- Xi'an University of Technology (CN)
- Suqian University
Publication Details
- Journal
- Frontiers in Cell and Developmental Biology
- Published
- 2025-01-09
- DOI
- https://doi.org/10.3389/fcell.2024.1513971
- Citations
- 3
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 4.08
Funders
- Government of Jiangsu Province