IViT: 一种用于皮肤病检测的新型可解释视觉Transformer
IViT: A Novel Interpretable Visual Transformer for Skin Disease Detection
- Chongqing Health Center for Women and Children（重庆妇女儿童健康中心）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出一种受二次规划约束的可解释视觉Transformer（IViT），通过预训练迁移学习适应小样本特征提取，并构建离散QP特征选择框架筛选符合临床诊断逻辑的判别性特征，在保持分类性能的同时降低特征冗余29.5%，实现准确率93.80%与可解释性的平衡。
AI中文摘要：
皮肤病的临床诊断易受皮损类间相似性干扰，且过度依赖临床医生经验易导致主观偏差。尽管现有深度学习辅助诊断方法取得了有竞争力的准确率，但存在视觉Transformer（ViT）的黑箱不透明性以及对医学小样本场景适应性差的问题。此外，主流可解释算法在提升可解释性时通常面临准确率显著下降的瓶颈。本文提出一种受二次规划（QP）约束的可解释ViT（IViT）。引入的预训练迁移学习适应小样本特征提取。构建离散QP特征选择框架，筛选与临床诊断逻辑一致的通用且判别性特征。设计多目标损失函数，在保持分类性能的同时减少特征冗余并优化激活分布。在六个标准皮肤病数据集上的实验结果表明，IViT达到了93.80%的准确率，仅比基线低0.21%，特征冗余降低了29.5%。其核心激活区域与临床关注的病变区域一致。所提模型平衡了准确率和可解释性，为小样本智能皮肤病诊断的临床部署提供了可靠解决方案。
英文摘要：
The clinical diagnosis of skin diseases is susceptible to interference from inter-class similarity of skin lesions, and over-reliance on clinicians'experience easily leads to subjective bias. Although existing deep learning aided diagnosis methods achieve competitive accuracy, they suffer from the black-box opacity of Vision Transformer (ViT) and poor adaptability to medical few-shot scenarios. Moreover, mainstream explainable algorithms generally face the bottleneck of significant accuracy degradation when improving interpretability. This paper proposes an interpretable ViT (IViT) constrained by Quadratic Programming (QP). The introduced pre-trained transfer learning adapts to few-shot feature extraction. A discrete QP feature selection framework is constructed to screen generic and discriminative features consistent with clinical diagnostic logic. A multi-objective loss function is designed to reduce feature redundancy and optimize activation distribution while preserving classification performance. Experimental results on six standard skin disease datasets show that IViT achieves an accuracy of 93.80%, only 0.21% lower than the baseline, with feature redundancy reduced by 29.5%. Its core activation regions are consistent with clinically concerned lesion areas. The proposed model balances accuracy and interpretability, providing a reliable solution for the clinical deployment of few-shot intelligent skin disease diagnosis.
