Scholarlink

<p>The global prevalence of diabetic retinopathy (DR) is increasing in parallel with the rising burden of diabetes, posing a substantial public health challenge. Current automated DR screening systems often lack lesion-level interpretable, robustness against class imbalance, and reliable uncertainty estimation, limiting their applicability in real-world clinical settings. The study suggests a clinical-guided deep learning framework of diabetic retinopathy (CG-DRNet) that considers lesion-conscious attention, adversarial data augmentation, and Bayesian uncertainty measurement to achieve reliable and explainable DR severity detection with objective to allow early-stage detection, particularly mild nonproliferative diabetic retinopathy (NPDR), and reciprocate clinical diagnostic procedures. The proposed framework uses a multi-task deep learning framework and lesion-aware attention network to explicitly predict microaneurysms, hemorrhages, exudates, and neovascularization. The system consists of a conditional generative adversarial network (CWGAN-GP) that is employed to overcome extreme imbalance in classes by generating clinically realistic images of minority classes of the fundus. Monte Carlo dropout is used to model Bayesian uncertainty to estimate predictive confidence, and an uncertainty-informed semi-supervised strategy of learning is used to enhance data efficiency. Evaluation of the framework is carried out on publicly available fundus image datasets APTOS 2019, Messidor-2 and Clinical metadata with the use of PyTorch 2.0.1. The proposed CG-DRNet reached 93.8% accuracy on APTOS 2019 and 91.2% on Messidor-2 with only 2.6% difference between generalization and the original model, macro F1-score of 0.891, quadratic weighted kappa of 0.912, referable DR detection AUC of 0.963 and expected calibration error of 0.034. The framework was shown to have 84.7% sensitivity when detecting Grade 2 + with 67&#xa0;ms inference time and therefore has been shown to be viable in clinical use.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Clinical-guided deep learning framework for diabetic retinopathy: integrating lesion-aware attention, adversarial augmentation, and uncertainty quantification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年8月5日

查看全文
  • Sehrish Saleem,
  • Ramzan Talib,
  • Muhammad Kashif Hanif,
  • Muhammad Umer Sarwar

摘要

The global prevalence of diabetic retinopathy (DR) is increasing in parallel with the rising burden of diabetes, posing a substantial public health challenge. Current automated DR screening systems often lack lesion-level interpretable, robustness against class imbalance, and reliable uncertainty estimation, limiting their applicability in real-world clinical settings. The study suggests a clinical-guided deep learning framework of diabetic retinopathy (CG-DRNet) that considers lesion-conscious attention, adversarial data augmentation, and Bayesian uncertainty measurement to achieve reliable and explainable DR severity detection with objective to allow early-stage detection, particularly mild nonproliferative diabetic retinopathy (NPDR), and reciprocate clinical diagnostic procedures. The proposed framework uses a multi-task deep learning framework and lesion-aware attention network to explicitly predict microaneurysms, hemorrhages, exudates, and neovascularization. The system consists of a conditional generative adversarial network (CWGAN-GP) that is employed to overcome extreme imbalance in classes by generating clinically realistic images of minority classes of the fundus. Monte Carlo dropout is used to model Bayesian uncertainty to estimate predictive confidence, and an uncertainty-informed semi-supervised strategy of learning is used to enhance data efficiency. Evaluation of the framework is carried out on publicly available fundus image datasets APTOS 2019, Messidor-2 and Clinical metadata with the use of PyTorch 2.0.1. The proposed CG-DRNet reached 93.8% accuracy on APTOS 2019 and 91.2% on Messidor-2 with only 2.6% difference between generalization and the original model, macro F1-score of 0.891, quadratic weighted kappa of 0.912, referable DR detection AUC of 0.963 and expected calibration error of 0.034. The framework was shown to have 84.7% sensitivity when detecting Grade 2 + with 67 ms inference time and therefore has been shown to be viable in clinical use.