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.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/AMAI_073.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/profile?id=%7ESamrajya_Thapa1
BibTex
@InProceedings{ThaSam_Beyond_MICCAISAT2026,
author = { Thapa, Samrajya AND Quest, Daniel J. AND Kline, Timothy L. AND Langstraat, Carrie L. AND Trabuco, Emanuel C. AND Le, Wei},
title = { { Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17273},
month = {pending},
page = {pending}
}