AI 中文总结
针对医学图像分类的类别不平衡问题，提出循环对比学习方法，通过复用历史特征扩充尾类支持区域，经多数据集验证性能优于强基线。
AI 中文摘要
医学图像分类常因疾病发病率的固有差异而遭遇类别不平衡问题。现有方法如类别重采样和损失重加权，主要在观测到的特征分布内改进学习，但未显式扩充尾类的潜在支持区域。结果，尾类表示仍过于紧凑，易被头类侵占，导致决策边界有偏。本研究提出用于不平衡医学图像分类的循环对比学习（Recurrent Contrastive Learning，RCL），RCL通过在训练阶段循环复用历史特征状态，逐步扩充尾类的支持区域。具体而言，采用带LoRA适配器的DINOv3作为骨干网络以提供鲁棒的特征嵌入；设计时间记忆队列（Temporal Memory Queue，TMQ）来保存跨训练阶段的语料级特征，为对比学习提供多样化的全局参考；基于TMQ构建时间锚点（Temporal Anchors，TARs），在尾类周围形成锚定场，该场可扩充尾类的支持区域、抑制头类侵占并提升类间分离度。在三个不平衡医学数据集上的大量实验表明，RCL相较于强基线取得了一致的性能提升，代码可通过指定URL获取。
英文摘要
Medical image classification often suffers from class imbalance due to the inherent disparities in disease incidence. Existing approaches, such as class resampling and loss reweighting, mainly improve learning within the observed feature distribution, but do not explicitly enlarge the latent support region of tail classes. As a result, tail-class representations remain overly compact and are easily encroached upon by head classes, leading to biased decision boundaries. In this work, we propose Recurrent Contrastive Learning (RCL) for imbalanced medical image classification. RCL progressively expands the support region of tail classes by recurrently reusing historical feature states across training phases. Specifically, we adopt DINOv3 with LoRA adapters as the backbone to provide robust feature embeddings. We then devise a Temporal Memory Queue (TMQ) to preserve corpus-level features across training phases and provide diversified global references for contrastive learning. Based on TMQ, we construct Temporal Anchors (TARs) to form an anchor field around tail classes. This field enlarges the support region of tail classes, suppresses head-class encroachment, and improves inter-class separation. Extensive experiments on three imbalanced medical datasets demonstrate that RCL achieves consistent improvements over strong baselines. The code is available at https://github.com/dndins/RCL.
Comments10 pages, 3 figures
Journal refThe 7th MICCAI Workshop on Advances in Simplifying Medical UltraSound.2026
