Weakly Supervised Patch Annotation for Improved Screening of Diabetic Retinopathy

• URL: http://arxiv.org/abs/2603.03991v1
• Date: Wed, 04 Mar 2026 12:35:55 GMT
• Title: Weakly Supervised Patch Annotation for Improved Screening of Diabetic Retinopathy
• Authors: Shramana Dey, Abhirup Banerjee, B. Uma Shankar, Ramachandran Rajalakshmi, Sushmita Mitra,
• Abstract summary: Diabetic Retinopathy (DR) requires timely screening to prevent irreversible vision loss.<n>Existing literature primarily focuses on image-level supervision, weakly-supervised localization, and clustering-based representation learning.<n>We introduce Similarity-based.<n>enclosure via Feature-space Ensemble (SAFE), a two-stage framework that unifies weak supervision,.<n>contrastive learning, and patch-wise embedding inference.
• Score: 9.215451885169538
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diabetic Retinopathy (DR) requires timely screening to prevent irreversible vision loss. However, its early detection remains a significant challenge since often the subtle pathological manifestations (lesions) get overlooked due to insufficient annotation. Existing literature primarily focuses on image-level supervision, weakly-supervised localization, and clustering-based representation learning, which fail to systematically annotate unlabeled lesion region(s) for refining the dataset. Expert-driven lesion annotation is labor-intensive and often incomplete, limiting the performance of deep learning models. We introduce Similarity-based Annotation via Feature-space Ensemble (SAFE), a two-stage framework that unifies weak supervision, contrastive learning, and patch-wise embedding inference, to systematically expand sparse annotations in the pathology. SAFE preserves fine-grained details of the lesion(s) under partial clinical supervision. In the first stage, a dual-arm Patch Embedding Network learns semantically structured, class-discriminative embeddings from expert annotated patches. Next, an ensemble of independent embedding spaces extrapolates labels to the unannotated regions based on spatial and semantic proximity. An abstention mechanism ensures trade-off between highly reliable annotation and noisy coverage. Experimental results demonstrate reliable separation of healthy and diseased patches, achieving upto 0.9886 accuracy. The annotation generated from SAFE substantially improves downstream tasks such as DR classification, demonstrating a substantial increase in F1-score of the diseased class and a performance gain as high as 0.545 in Area Under the Precision-Recall Curve (AUPRC). Qualitative analysis, with explainability, confirms that SAFE focuses on clinically relevant lesion patterns; and is further validated by ophthalmologists.

Related papers

• Uncertainty-Aware Ordinal Deep Learning for cross-Dataset Diabetic Retinopathy Grading [0.0]
  Early and reliable detection of diabetic retinopathy is critical for preventing blindness.<n>We propose an uncertainty-aware deep learning framework for automated DR severity grading.<n>Our approach combines a convolutional backbone with lesion-query attention pooling and an evidential Dirichlet-based ordinal regression head.
  arXiv  Detail & Related papers  (2026-02-10T21:44:04Z)
• TWLR: Text-Guided Weakly-Supervised Lesion Localization and Severity Regression for Explainable Diabetic Retinopathy Grading [9.839282449612513]
  We propose TWLR, a two-stage framework for interpretable diabetic retinopathy (DR) assessment.<n>In the first stage, a vision-supervised model integrates domain-specific ophthalmological knowledge into text embeddings to jointly perform DR grading and lesion classification.<n>The second stage introduces an iterative severity regression framework based on weakly-language semantic segmentation.
  arXiv  Detail & Related papers  (2025-12-15T06:08:16Z)
• SP-Det: Self-Prompted Dual-Text Fusion for Generalized Multi-Label Lesion Detection [14.796915375957402]
  SP-Det is a novel self-prompted detection framework that automatically generates rich textual context to guide multi-label lesion detection.<n>We introduce an expert-free dual-text prompt generator (DTPG) that leverages two complementary textual modalities.<n>Our experiments on two chest X-ray datasets with diverse thoracic disease categories demonstrate that our SP-Det framework outperforms state-of-the-art detection methods.
  arXiv  Detail & Related papers  (2025-12-04T15:05:04Z)
• Self-Supervised Anatomical Consistency Learning for Vision-Grounded Medical Report Generation [61.350584471060756]
  Vision-grounded medical report generation aims to produce clinically accurate descriptions of medical images.<n>We propose Self-Supervised Anatomical Consistency Learning (SS-ACL) to align generated reports with corresponding anatomical regions.<n>SS-ACL constructs a hierarchical anatomical graph inspired by the invariant top-down inclusion structure of human anatomy.
  arXiv  Detail & Related papers  (2025-09-30T08:59:06Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• A Global and Patch-wise Contrastive Loss for Accurate Automated Exudate Detection [12.669734891001667]
  Diabetic retinopathy (DR) is a leading global cause of blindness. Early detection of hard exudates plays a crucial role in identifying DR, which aids in treating diabetes and preventing vision loss. We present a novel supervised contrastive learning framework to optimize hard exudate segmentation.
  arXiv  Detail & Related papers  (2023-02-22T17:39:00Z)
• Boundary Guided Semantic Learning for Real-time COVID-19 Lung Infection Segmentation System [69.40329819373954]
  The coronavirus disease 2019 (COVID-19) continues to have a negative impact on healthcare systems around the world. At the current stage, automatically segmenting the lung infection area from CT images is essential for the diagnosis and treatment of COVID-19. We propose a boundary guided semantic learning network (BSNet) in this paper.
  arXiv  Detail & Related papers  (2022-09-07T05:01:38Z)
• Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation [74.05906222376608]
  We propose adversarial self-supervision UDA (or ASSUDA) that maximizes the agreement between clean images and their adversarial examples by a contrastive loss in the output space. This paper is rooted in two observations: (i) the robustness of UDA methods in semantic segmentation remains unexplored, which pose a security concern in this field; and (ii) although commonly used self-supervision (e.g., rotation and jigsaw) benefits image tasks such as classification and recognition, they fail to provide the critical supervision signals that could learn discriminative representation for segmentation tasks.
  arXiv  Detail & Related papers  (2021-05-23T01:50:44Z)
• Dual-Consistency Semi-Supervised Learning with Uncertainty Quantification for COVID-19 Lesion Segmentation from CT Images [49.1861463923357]
  We propose an uncertainty-guided dual-consistency learning network (UDC-Net) for semi-supervised COVID-19 lesion segmentation from CT images. Our proposed UDC-Net improves the fully supervised method by 6.3% in Dice and outperforms other competitive semi-supervised approaches by significant margins.
  arXiv  Detail & Related papers  (2021-04-07T16:23:35Z)
• Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation [79.58311369297635]
  We propose a new weakly-supervised lesions transfer framework, which can explore transferable domain-invariant knowledge across different datasets. A Wasserstein quantified transferability framework is developed to highlight widerange transferable contextual dependencies. A novel self-supervised pseudo label generator is designed to equally provide confident pseudo pixel labels for both hard-to-transfer and easy-to-transfer target samples.
  arXiv  Detail & Related papers  (2020-12-08T02:26:03Z)
• Self-Guided Multiple Instance Learning for Weakly Supervised Disease Classification and Localization in Chest Radiographs [22.473965401043717]
  We introduce a novel loss function for training convolutional neural networks increasing the emphlocalization confidence We show that the supervision provided within the proposed learning scheme leads to better performance and more precise predictions on prevalent datasets for multiple-instance learning.
  arXiv  Detail & Related papers  (2020-09-30T22:19:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.