发表机构
National Institute of Technology Durgapur; IIT Kanpur（杜尔加布尔国立技术学院; 坎普尔印度理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对视网膜疾病分类中深度学习框架可解释性瓶颈问题，提出CounterFundus框架，结合CycleGAN实现疾病到正常眼底图像转换以提供反事实解释，引入CCAS量化一致性，提升了分类性能，成为可解释的视网膜疾病检测XAI框架。
AI 中文摘要
从眼底图像中自动检测基于视网膜的视力损害眼部疾病对于早期筛查、及时转诊和减少对专家评估的依赖非常重要，基于神经网络的深度学习（DL）模型已被广泛应用。然而，DL框架的可解释性仍然是临床应用的主要瓶颈。本研究提出了CounterFundus，一种新颖的由CycleGAN驱动的反事实可解释性框架，将基于EfficientNet-B5的视网膜疾病检测与视觉上可解释的疾病到正常眼底图像转换相结合。对于每个病理图像，CycleGAN生成器产生的反事实代表估计的健康对应物，所得差异图用于定位与疾病相关的视网膜变化。与传统的事后显著性方法不同，CounterFundus通过视觉上合理的疾病到正常视网膜转换提供反事实解释。此后，为了量化反事实差异图与分类器显著性之间的空间一致性，引入了反事实分类器对齐分数（CCAS），将Spearman相关性、二元IoU和指向准确性嵌入到单个评估协议中。EigenCAM对齐评估表明，生成的反事实解释在所有CCAS维度上与分类器相关的视网膜证据在空间上保持一致。消融研究进一步证实，CCAS过滤的反事实增强提高了眼底图像中的下游分类性能，确立了CounterFundus作为一种基于临床的、可解释的人工智能（XAI）框架用于视网膜疾病检测。
英文摘要
Automated detection of vision impairing retina-based ocular conditions from fundus images is important for early screening, timely referral and reducing dependency on specialist-only assessment, for which neural network-based deep learning (DL) models have been widely utilized. However, explainability of the DL frameworks remains a major bottleneck for clinical adoption, particularly when model decisions are not linked to retinal regions that are clinically meaningful. To address this issue, this study presents CounterFundus, a novel CycleGAN-driven counterfactual explainability framework, integrating EfficientNet-B5-based retinal disease detection with visually interpretable disease-to-normal fundus image translation. For each pathological image, the counterfactual yielded by the CycleGAN generator represents an estimated healthy counterpart and the resultant difference map is utilized to localize disease-associated retinal changes. Unlike conventional post-hoc saliency methods, CounterFundus provides counterfactual explanations through visually plausible disease-to-normal retinal translation. Thereafter, to quantify the spatial agreement between counterfactual difference maps and classifier saliency, the Counterfactual-Classifier Alignment Score (CCAS) is introduced, embedding Spearman correlation, binary IoU and pointing accuracy into a single assessment protocol. To this end, EigenCAM-aligned evaluation demonstrates that the generated counterfactual explanations remain spatially consistent with classifier-relevant retinal evidence across all CCAS dimensions. Along with that, ablation studies further confirm that CCAS-filtered counterfactual augmentation improves the downstream classification performance in fundus images, establishing CounterFundus as a clinically-grounded, explainable artificially intelligence (XAI) framework for retinal disease detection.
Comments8 pages, 9 figures, 9 tables
