PiPViT：用于视网膜图像分析的基于Patch的视觉可解释原型
PiPViT: Patch-based Visual Interpretable Prototypes for Retinal Image Analysis
AI总结：
针对现有基于原型的医学图像分析方法可解释性不足的问题，提出结合ViT、对比学习和多分辨率处理的PiPViT模型，仅用图像级标签学习可解释原型，在四个视网膜OCT数据集上性能达SOTA水平且解释性更强。
摘要：
研究背景与目的：基于原型的方法通过学习细粒度的部件原型来提升可解释性，但其在输入像素空间的可视化结果与人类可理解的生物标志物并非始终一致。此外，主流的基于原型的方法通常学习极细粒度的原型，这类原型在医学成像领域可解释性较低，因为医学场景中生物标志物和病灶的存在与否及其范围都至关重要。\n方法：为应对上述挑战，我们提出PiPViT（基于Patch的视觉可解释原型），这是一种具备固有可解释性的图像识别原型模型。PiPViT借助视觉Transformer（ViT）捕捉图像块（patch）之间的长距离依赖关系，仅使用图像级标签即可学习到鲁棒的、人类可解释的原型，且这些原型能够近似病灶范围。此外，PiPViT结合了对比学习和多分辨率输入处理，可实现跨尺度的生物标志物有效定位。\n结果：我们在四个视网膜OCT图像分类数据集上对PiPViT进行了评估，其量化性能与当前最优方法相当，同时能提供更具实际意义的解释。此外，在留出测试集上的量化评估证实，学习到的原型具备语义相关性和临床相关性。我们认为PiPViT能够透明地解释其决策过程，辅助临床医生理解诊断结果。项目GitHub页面：https://github.com/marziehoghbaie/PiPViT
英文摘要：
Background and Objective: Prototype-based methods improve interpretability by learning fine-grained part-prototypes; however, their visualization in the input pixel space is not always consistent with human-understandable biomarkers. In addition, well-known prototype-based approaches typically learn extremely granular prototypes that are less interpretable in medical imaging, where both the presence and extent of biomarkers and lesions are critical. Methods: To address these challenges, we propose PiPViT (Patch-based Visual Interpretable Prototypes), an inherently interpretable prototypical model for image recognition. Leveraging a vision transformer (ViT), PiPViT captures long-range dependencies among patches to learn robust, human-interpretable prototypes that approximate lesion extent only using image-level labels. Additionally, PiPViT benefits from contrastive learning and multi-resolution input processing, which enables effective localization of biomarkers across scales. Results: We evaluated PiPViT on retinal OCT image classification across four datasets, where it achieved competitive quantitative performance compared to state-of-the-art methods while delivering more meaningful explanations. Moreover, quantitative evaluation on a hold-out test set confirms that the learned prototypes are semantically and clinically relevant. We believe PiPViT can transparently explain its decisions and assist clinicians in understanding diagnostic outcomes. Github page: https://github.com/marziehoghbaie/PiPViT
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。
