cs.CV · 2607.23883 Copy arXiv ID · Jul 26, 2026 Save Long-Tailed Medical Image Classification Authors: Nathanael Ren , Saagar Arya
Organizations: Pratt School of Engineering Duke University Durham, NC 27708, USA
Abstract In this paper, we examine the difficulties of using standard techniques for medical image classification due to long-tailed distributions (wherein rarer conditions have very few samples) resulting in bias towards diagnosing common diseases and away from rarer diseases. We then discuss and implement deep learning models with techniques such as augmentation to minimize error, especially from rarer diseases. We evaluate various different models with AP, F1 score, AUROC, and loss (all on the validation set). We conclude with the promising results from our best model, and potential applications in the healthcare space.
Explore similar work May 4, 2026 · Jiaxiang Jiang, Mahesh Subedar, Omesh Tickoo Medical Image Classification Skin Lesion Classification
May 15, 2026 · Felix Nützel, Mischa Dombrowski, Bernhard Kainz Medical Image Generation Synthetic Data Augmentation
Jul 1, 2026 · Tong Shao, Hongshun Ling, Li Zhang +4 Chest X-Ray Chest Radiography
May 4, 2026 · cs.CV J/K move · Enter open · S save
Jiaxiang Jiang, Mahesh Subedar, Omesh Tickoo
Intel · Google
Long-tailed class distributions are pervasive in multi-class medical datasets and pose significant challenges for deep learning models which typically underperform on tail classes with limited samples. This limitation is particularly problematic in medical applications, where rare classes often correspond to severe or high-risk diseases and therefore require high diagnostic accuracy. Existing solutions-including specialized architectures, rebalanced loss functions, and handcrafted data augmentation-offer only marginal improvements and struggle to scale due to their limited and largely deterministic variability. To address these challenges, we introduce a diffusion-model-driven synthetic data augmentation pipeline tailored for medical long-tailed classification. Our approach features a novel inpainting diffusion model combined with an Out-of-Distribution (OOD) post-selection mechanism to ensure diverse, realistic, and clinically meaningful synthetic samples. Evaluated on the ISIC2019 skin lesion classification dataset, one of the largest and most imbalanced medical imaging benchmarks, our method yields substantial improvements in overall performance, with particularly pronounced gains on tail classes with more than
28 % 28\% 28% improvement on the class with the fewest samples. These results demonstrate the effectiveness of diffusion-based augmentation in mitigating long-tail imbalance and enhancing medical classification robustness.