arXiv Machine Learning July 30, 2026 By Haroui Ma, Francesco Quinzan, Theresa Willem, Stefan Bauer

AI Alignment in Medical Imaging: Unveiling Hidden Biases Through Counterfactual Analysis

Read the original on arXiv Machine Learning →

arXiv:2504. 19621v2 Announce Type: replace Abstract: Machine learning (ML) systems for medical imaging have demonstrated remarkable diagnostic capabilities, but their susceptibility to biases poses significant risks, since biases may negatively impact generalization performance.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Jul 7

CIPHER: Causal Intervention Pathways for Healthcare Equity and Robustness

arXiv:2607. 02596v1 Announce Type: cross Abstract: Deep learning models for medical diagnosis frequently exhibit substantial performance disparities across sensitive subgroups (e.

By Xinyu Jia, Weidong Guo, Wangyuan Zhao, Yi Guo, Zeju Li, Yuanyuan Wang

diffusion benchmarks

arXiv AI

Jun 18

Learning Patient-Specific Disease Dynamics with Latent Flow Matching for Longitudinal Imaging Generation

arXiv:2512. 09185v4 Announce Type: replace-cross Abstract: Understanding disease progression is a central clinical challenge with direct implications for early diagnosis and personalized treatment.

By Hao Chen, Rui Yin, Yifan Chen, Qi Chen, Chao Li

diffusion benchmarks safety

arXiv AI

Jun 4

Counterfactual Explanations for Deep Two-Sample Testing

arXiv:2606. 04009v1 Announce Type: cross Abstract: Two-sample testing is a fundamental tool for detecting distributional differences across scientific domains, but classical tests (including kernel-based tests) can be ineffective on high-dimensional structured data such as images.

By Wei-Cheng Lai, Marco Simnacher, Christoph Lippert

diffusion

arXiv AI

Jul 9

CompDiff: Hierarchical Compositional Diffusion for Fair and Zero-Shot Intersectional Medical Image Generation

arXiv:2603. 16551v2 Announce Type: replace-cross Abstract: Generative models are increasingly used to augment medical imaging datasets for fairer AI, yet a key assumption often goes unexamined: that generators produce equally high-quality images across demographic groups.

By Mahmoud Ibrahim, Bart Elen, Chang Sun, Gokhan Ertaylan, Michel Dumontier

rag diffusion fine-tuning safety

arXiv Machine Learning

Jul 15

Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification

arXiv:2607. 12464v1 Announce Type: cross Abstract: When labeled data are scarce, off-the-shelf diffusion models can augment training sets for few-shot medical image classification, but not all generated samples are equally useful for the downstream task.

By Jeeyung Kim, Erfan Esmaeili, Qiang Qiu

diffusion computer-vision reinforcement-learning fine-tuning benchmarks

arXiv AI

Jun 2

MGRegBench: A Novel Benchmark Dataset with Anatomical Landmarks for Mammography Image Registration

arXiv:2512. 17605v2 Announce Type: replace-cross Abstract: Robust mammography registration is essential for clinically relevant applications like tracking disease progression in breast tissue.

By Svetlana Krasnova, Emiliya Starikova, Ilia Naletov, Andrey Krylov, Dmitry Sorokin

computer-vision benchmarks

Related stories

CIPHER: Causal Intervention Pathways for Healthcare Equity and Robustness

Learning Patient-Specific Disease Dynamics with Latent Flow Matching for Longitudinal Imaging Generation

Counterfactual Explanations for Deep Two-Sample Testing

CompDiff: Hierarchical Compositional Diffusion for Fair and Zero-Shot Intersectional Medical Image Generation

Steering Diffusion Models via Class-Contrastive Influence for Few-Shot Medical Classification

MGRegBench: A Novel Benchmark Dataset with Anatomical Landmarks for Mammography Image Registration