A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability
This work addresses the need for consistent and fine-grained data in computer-aided DR diagnosis, which is crucial for improving performance and interpretability for ophthalmologists, though it is incremental as it focuses on dataset creation and benchmarking.
The authors tackled the problem of limited training data for diabetic retinopathy (DR) diagnosis by constructing a large fine-grained annotated dataset (FGADR) with 2,842 images, enabling benchmark tasks like lesion segmentation and grading, and achieved baseline results through extensive experiments with state-of-the-art methods.
People with diabetes are at risk of developing an eye disease called diabetic retinopathy (DR). This disease occurs when high blood glucose levels cause damage to blood vessels in the retina. Computer-aided DR diagnosis is a promising tool for early detection of DR and severity grading, due to the great success of deep learning. However, most current DR diagnosis systems do not achieve satisfactory performance or interpretability for ophthalmologists, due to the lack of training data with consistent and fine-grained annotations. To address this problem, we construct a large fine-grained annotated DR dataset containing 2,842 images (FGADR). This dataset has 1,842 images with pixel-level DR-related lesion annotations, and 1,000 images with image-level labels graded by six board-certified ophthalmologists with intra-rater consistency. The proposed dataset will enable extensive studies on DR diagnosis. We set up three benchmark tasks for evaluation: 1. DR lesion segmentation; 2. DR grading by joint classification and segmentation; 3. Transfer learning for ocular multi-disease identification. Moreover, a novel inductive transfer learning method is introduced for the third task. Extensive experiments using different state-of-the-art methods are conducted on our FGADR dataset, which can serve as baselines for future research.