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.
arXiv:2605.07785v3 Announce Type: replace Abstract: Concept Bottleneck Models (CBMs) in medical imaging aim to improve model interpretability by predicting intermediate clinical concepts before final...
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.
arXiv:2512. 21414v2 Announce Type: replace-cross Abstract: Recent tool-use frameworks powered by vision-language models (VLMs) improve image understanding by grounding model predictions with specialized tools.
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.
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.
arXiv:2603. 02221v2 Announce Type: replace-cross Abstract: In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods.
ICON Decomposition is a new method for explaining deep neural networks by quantifying how much variance each concept explains in a network layer after accounting for all other concepts and the outcome. Unlike previous concept‑based methods that evaluate concepts in isolation, ICON can distinguish genuine model reliance from spurious correlations. Experiments on synthetic data, skin‑lesion, and brain‑imaging models show that ICON recovers concept importance more accurately, isolates truly relied‑upon concepts, and provides sparse explanations validated through retraining and out‑of‑distribution testing.
arXiv:2605.10894v2 Announce Type: replace Abstract: Deep learning models in medical imaging often fail when deployed in new clinical environments due to distribution shifts in demographics, scanner h...
ProtoCAM is an explainable few‑shot learning framework for classifying breast lesions in ultrasound images. It combines mask‑guided feature encoding, prototypical metric learning, and gradient‑based visual explanations to leverage limited annotated data. Evaluated on the BUSI dataset, ProtoCAM achieved a macro F1‑score of 0.910 in a 3‑way 5‑shot setting, outperforming standard supervised CNNs, with ResNet18 reaching 91.65% under 15‑shot conditions.
arXiv:2603.02790v2 Announce Type: replace Abstract: Foundation models are changing the way we develop medical artificial intelligence. By learning broadly generalizable features across diverse data m...
arXiv:2606. 04326v1 Announce Type: cross Abstract: Concept bottleneck models predict outcomes from high-level concepts detected in inputs.
arXiv:2607. 02596v1 Announce Type: cross Abstract: Deep learning models for medical diagnosis frequently exhibit substantial performance disparities across sensitive subgroups (e.