用于视网膜图像白内障检测的可解释深度学习：一种双眼与知识蒸馏方法
Explainable Deep Learning for Cataract Detection in Retinal Images: A Dual-Eye and Knowledge Distillation Approach
AI总结：
本文提出基于双眼信息与知识蒸馏的白内障视网膜图像分类流程，验证轻量模型可在保持高准确率与可解释性的同时降低计算成本。
摘要：
白内障仍然是全球视力损害的主要原因之一，通过视网膜成像进行早期检测对于及时干预至关重要。我们提出了一种用于白内障分类的深度学习流程，使用 Ocular Disease Recognition（眼科疾病识别）数据集，其中包含来自 5000 名患者的左眼和右眼眼底照片。我们评估了 CNN、transformer、轻量级架构以及知识蒸馏模型。表现最佳的模型 Swin-Base Transformer 达到了 98.58% 的准确率和 0.9836 的 F1 分数。利用 Swin-Base 知识训练的蒸馏 MobileNetV3 在计算成本大幅降低的情况下，达到了 98.42% 的准确率和 0.9787 的 F1 分数。所提出的蒸馏 MobileNet 的双眼 Siamese 变体整合了来自双眼的信息，取得了 98.21% 的准确率。使用 Grad-CAM 进行的可解释性分析表明，CNN 关注具有医学意义的特征，例如晶状体混浊和中央模糊。这些结果表明，即使使用轻量级模型，也可以实现准确、可解释的白内障检测，从而支持在资源有限环境中的潜在临床整合。
英文摘要：
Cataract remains a leading cause of visual impairment worldwide, and early detection from retinal imaging is critical for timely intervention. We present a deep learning pipeline for cataract classification using the Ocular Disease Recognition dataset, containing left and right fundus photographs from 5000 patients. We evaluated CNNs, transformers, lightweight architectures, and knowledge-distilled models. The top-performing model, Swin-Base Transformer, achieved 98.58% accuracy and an F1-score of 0.9836. A distilled MobileNetV3, trained with Swin-Base knowledge, reached 98.42% accuracy and a 0.9787 F1-score with greatly reduced computational cost. The proposed dual-eye Siamese variant of the distilled MobileNet, integrating information from both eyes, achieved an accuracy of 98.21%. Explainability analysis using Grad-CAM demonstrated that the CNNs concentrated on medically significant features, such as lens opacity and central blur. These results show that accurate, interpretable cataract detection is achievable even with lightweight models, supporting potential clinical integration in resource-limited settings
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
