无需标注数据，用医学先验知识提升模型可解释性。
Weakly Supervised Concept Learning with Class-Level Priors for Interpretable Medical Diagnosis
- 利用疾病级别的概念先验作为弱监督信号，避免人工标注。
- 在四个医学数据集上，概念识别准确率比零样本方法高33%以上。
- 适合临床部署，特别关注可解释性且缺乏标注的医疗场景。
人类可理解的预测对人工智能在医学影像中的应用至关重要，但大多数可解释性设计（IBD）框架需要概念标注进行训练，这在临床环境中成本高昂且不切实际。近期尝试绕过标注的方法，如零样本视觉-语言模型或概念生成框架，难以捕捉特定医学特征，导致可靠性差。本文提出一种新的先验引导概念预测器（PCP），一种弱监督框架，可在无需显式监督或依赖语言模型的情况下实现概念预测。PCP利用类别级概念先验作为弱监督，并引入基于KL散度和熵正则化的优化机制，使预测结果更符合临床推理逻辑。在PH2（皮肤镜）和WBCatt（血液学）数据集上的实验表明，与零样本基线相比，PCP在概念层面的F1分数提升超过33%，同时在四个医学数据集（PH2、WBCatt、HAM10000、CXR4）上分类性能与全监督概念瓶颈模型（CBMs）和V-IP相当。
原文摘要 · Abstract (English)
Human-interpretable predictions are essential for deploying AI in medical imaging, yet most interpretable-by-design (IBD) frameworks require concept annotations for training data, which are costly and impractical to obtain in clinical contexts. Recent attempts to bypass annotation, such as zero-shot vision-language models or concept-generation frameworks, struggle to capture domain-specific medical features, leading to poor reliability. In this paper, we propose a novel Prior-guided Concept Predictor (PCP), a weakly supervised framework that enables concept answer prediction without explicit supervision or reliance on language models. PCP leverages class-level concept priors as weak supervision and incorporates a refinement mechanism with KL divergence and entropy regularization to align predictions with clinical reasoning. Experiments on PH2 (dermoscopy) and WBCatt (hematology) show that PCP improves concept-level F1-score by over 33% compared to zero-shot baselines, while delivering competitive classification performance on four medical datasets (PH2, WBCatt, HAM10000, and CXR4) relative to fully supervised concept bottleneck models (CBMs) and V-IP.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。