arXiv：cs.LG· Samrajya Thapa, Daniel J. Quest, Timothy L. Kline, Carrie L. Langstraat, Emanuel C. Trabuco, Wei Le·· 4 小时前AI 评分31
超越解释：通过概念干预调试医学影像模型
Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention
AI 导读
研究者提出一个即插即用框架，通过将单模态编码器对齐 BioMedCLIP 构建概念瓶颈模型（CBM），实现概念级干预，从而区分因果概念与虚假相关概念。在 Mayo Clinic 超声数据集和 CheXpert 5x200 胸部 X 光数据集上，概念干预能可靠诊断模型，并通过引导微调维持甚至偶尔提升预测性能。该框架已入选 MICCAI 2026 第五届医学 AI 应用研讨会（AMAI）。
正文
Abstract:Medical imaging models often operate as black boxes, limiting interpretability and systematic debugging. We introduce an easy-to-use, plug-and-play framework for concept-based interpretation and model refinement. By aligning a single-modality encoder to BioMedCLIP, we construct a Concept Bottleneck Model (CBM) that enables concept-level interventions. These interventions allow us to isolate causal versus spuriously correlated concepts, validate insights with domain experts, and generate counterfactual samples for targeted fine-tuning. We evaluate our framework on a Mayo Clinic ultrasound dataset and the CheXpert 5x200 chest X-ray dataset. Results demonstrate that concept intervention enables reliable model diagnosis while maintaining, and occasionally improving predictive performance via guided fine-tuning. Our findings highlight the practical value of this framework for controlled, interpretable refinement of clinical deep learning models.
| Comments: | Accepted at the 5th Workshop on Applications of Medical AI (AMAI), MICCAI 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.09031 [cs.CV] |
| (or arXiv:2610.09031v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09031 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Samrajya Thapa [view email]
[v1]
Tue, 6 Oct 2026 19:31:42 UTC (10,646 KB)
来源：arXiv：cs.LG · arxiv.org