让医学影像模型说出判断依据并标出位置，提升可解释性。
ViConEx-Med: Visual Concept Explainability via Multi-Concept Token Transformer for Medical Image Analysis
- 用可学习的多概念令牌，同时预测和定位视觉概念。
- 在真实医疗数据上，定位精度优于已有概念模型。
- 适合需要透明决策的医学影像分析场景。
基于概念的模型旨在通过人类可理解的概念解释模型决策。然而，现有方法大多将概念视为数值属性，未能提供能定位预测概念的互补视觉解释，限制了其在实际应用中的价值，尤其在医疗等高风险场景中。本文提出 ViConEx-Med，一种基于 Transformer 的视觉概念可解释性框架，引入多概念可学习令牌，联合预测并定位视觉概念。通过专用注意力层处理视觉与文本概念令牌，该方法生成概念级定位图，同时保持高预测准确率。在合成与真实医疗数据集上的实验表明，ViConEx-Med 在概念检测与定位精度上均优于现有概念模型，并达到与黑箱模型相当的性能。结果表明，基于视觉概念构建内在可解释模型具有广阔前景。代码已公开于 https://github.com/CristianoPatricio/viconex-med。
原文摘要 · Abstract (English)
Concept-based models aim to explain model decisions with human-understandable concepts. However, most existing approaches treat concepts as numerical attributes, without providing complementary visual explanations that could localize the predicted concepts. This limits their utility in real-world applications and particularly in high-stakes scenarios, such as medical use-cases. This paper proposes ViConEx-Med, a novel transformer-based framework for visual concept explainability, which introduces multi-concept learnable tokens to jointly predict and localize visual concepts. By leveraging specialized attention layers for processing visual and text-based concept tokens, our method produces concept-level localization maps while maintaining high predictive accuracy. Experiments on both synthetic and real-world medical datasets demonstrate that ViConEx-Med outperforms prior concept-based models and achieves competitive performance with black-box models in terms of both concept detection and localization precision. Our results suggest a promising direction for building inherently interpretable models grounded in visual concepts. Code is publicly available at https://github.com/CristianoPatricio/viconex-med.
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。