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.
Abstract (translated)
糖尿病视网膜病变（DR）需要及时筛查以防止不可逆的视力丧失。然而，其早期检测仍然是一个重大挑战，因为细微的病理表现（病灶）常常由于标注不足而被忽视。现有文献主要集中在图像级监督、弱监督定位和基于聚类表示学习上，这些方法未能系统地为未标记病变区域进行注释以优化数据集。专家驱动的病变标注耗时且通常不完整，限制了深度学习模型的表现。我们引入了一种名为通过特征空间集成实现相似性标注（SAFE）的方法，这是一种两阶段框架，将弱监督、对比学习和基于补丁嵌入推断统一起来，在病理学中系统地扩展稀疏注释。 SAFE在部分临床监护下保留病变的细节信息。在第一阶段，双臂Patch Embedding Network从专家标记的补丁中学习语义结构化且区分度高的嵌入表示。接下来，一组独立的嵌入空间基于空间和语义邻近性将标签外推到未标注区域。一个弃权机制确保了高可靠注释与噪声覆盖率之间的平衡。实验结果表明，SAFE能够可靠地区分健康和病变补丁，并达到了高达0.9886的准确率。来自SAFE生成的标注极大地改善了下游任务如DR分类的表现，患病类别的F1分数显著提高，以及在精度-召回曲线下的面积（AUPRC）提高了最多达0.545。基于可解释性的定性分析证实了SAFE专注于临床相关的病变模式，并且这一方法还得到了眼科医生的验证和认可。
URL
https://arxiv.org/abs/2603.03991
