← Back to all news
arXiv Machine Learning By Samrajya Thapa, Daniel J. Quest, Timothy L. Kline, Carrie L. Langstraat, Emanuel C. Trabuco, Wei Le

Beyond Explanation: Debugging Medical Imaging Models via Concept Intervention

Read the original on arXiv Machine Learning →

The paper presents a plug‑and‑play framework that uses concept-based interpretation to debug medical imaging models. By aligning a single‑modality encoder with BioMedCLIP, the authors build a Concept Bottleneck Model that allows concept‑level interventions to distinguish causal from spurious features. Experiments on Mayo Clinic ultrasound and CheXpert chest X‑ray data show that these interventions can reliably diagnose model issues and even improve performance through guided fine‑tuning.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Aug 24

TRACE: Training-time Report-guided and Clinically Ordered Concept Editing

TRACE is a training-time framework that uses structured radiology reports to guide concept editing, allowing image-only diagnosis during inference. It refines image-derived concepts with a teacher-guided editing mechanism in a malignancy-aware ordered concept space and introduces Strategic Concept Missing Training to handle incomplete annotations. The authors also present BUSC, a benchmark linking images, labels, and structured attributes, and show that TRACE outperforms existing methods on multiple datasets with better cross-domain robustness.

By Wentao Yue, Tianyou Lai, Jiayu Luo, Qingyu Mao, Ziying Wang, Zhenyuan Ning, Qilei Li
agentsefficiencymultimodalbenchmarkssafety
More like this →
arXiv Computer Vision
Sep 3

Generating Medical Image Counterfactuals using Causal Explanations

The paper introduces a new framework for generating medical image counterfactuals that does not rely on auxiliary generative models. By extracting causal evidence directly from a classifier, the method deterministically produces edits within user-specified regions, requiring no additional training. Experiments on real-world medical imaging datasets show that these counterfactuals alter classifier predictions while staying closer to the original image than generative baselines, offering a clearer view of the model’s decision boundary.

By David A. Kelly, Tom Yaacov, Nathan Blake, Sander Beckers, Hana Chockler
diffusionsafety
More like this →
Hugging Face Trending Papers
Sep 2

Generating Medical Image Counterfactuals using Causal Explanations

The paper introduces a new method for generating medical image counterfactuals that does not rely on auxiliary generative models. By extracting causal evidence directly from the classifier, the approach deterministically edits user-specified regions to alter predictions while staying closer to the original image than generative baselines. Experiments on real-world medical imaging datasets show that this technique provides a more direct and transparent view of the classifier’s decision boundary.

diffusionsafety
More like this →