Skip to main content

ORIGINAL RESEARCH article

Front. Cell Dev. Biol.
Sec. Molecular and Cellular Pathology
Volume 12 - 2024 | doi: 10.3389/fcell.2024.1513971
This article is part of the Research Topic Artificial Intelligence Applications in Chronic Ocular Diseases, Volume II View all 15 articles

Color Fundus Photograph-based Diabetic Retinopathy Grading via Label Relaxed Collaborative Learning on Deep features and Radiomics features

Provisionally accepted
Chao Zhang Chao Zhang 1*Guanglei Sheng Guanglei Sheng 2Jie Su Jie Su 1*Lian Duan Lian Duan 3*
  • 1 Suqian University, Suqian, China
  • 2 Xi'an University of Technology, Xi'an, Shaanxi, China
  • 3 Nantong University, Nantong, Jiangsu Province, China

The final, formatted version of the article will be published soon.

    Diabetic 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. In this study, we 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. The primary goal of label relaxation is to enhance the distinguishability of training samples in the label space, thereby improving the model's classification accuracy. Additionally, we introduce graph constraints based on manifold learning methods to mitigate overfitting caused by label relaxation. Finally, we validate the effectiveness of the proposed method on two fundus image datasets: the DR1 Dataset and the MESSIDOR Dataset. Experimental results indicate the promising performance of the proposed method.

    Keywords: Diabetic retinopathy grading, Collaborative Learning, radiomic features, Highlevel deep Features, Label relaxation

    Received: 19 Oct 2024; Accepted: 26 Dec 2024.

    Copyright: © 2024 Zhang, Sheng, Su and Duan. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Chao Zhang, Suqian University, Suqian, China
    Jie Su, Suqian University, Suqian, China
    Lian Duan, Nantong University, Nantong, 226019, Jiangsu Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.