arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.16249cs.CV
收藏

融合深度学习与生物学启发方法用于极端长尾白细胞分类

Synergizing Deep Learning and Biological Heuristics for Extreme Long-Tail White Blood Cell Classification

VinUni-Illinois Smart Health Center, VinUniversity(VinUniversity-VinUni-Illinois智能健康中心);The Computer Vision and Medical AI Lab, VinUniversity(VinUniversity计算机视觉与医学人工智能实验室)

Duc T. Nguyen, Hoang-Long Nguyen, Huy-Hieu Pham

AI总结:

本文提出融合生成对抗网络与生物启发方法的框架,解决白细胞分类中的类别不平衡与长尾分布问题,提升稀有亚型的识别性能。

摘要:

自动化白细胞(WBC)分类对白血病筛查至关重要,但受到极端类别不平衡、长尾分布和域偏移的挑战,导致深度模型过度拟合主导类别而无法识别稀有亚型。本文提出一种混合框架,整合生成Pix2Pix基于的修复模块以去除伪影,Swin Transformer集成与MedSigLIP对比嵌入用于鲁棒表征学习,以及生物启发的细化步骤利用几何尖锐度和基于Mahalanobis的形态约束以恢复非分布预测。在WBCBench 2026挑战中评估,本文方法在私有排行榜上实现宏F1值0.77139,证明在严重不平衡情况下性能优异,展示了将生物先验纳入深度学习进行血液图像分析的价值。代码可在https://github.com/trongduc-nguyen/WBCBench2026获取。

英文摘要:

Automated white blood cell (WBC) classification is essential for leukemia screening but remains challenged by extreme class imbalance, long-tail distributions, and domain shift, leading deep models to overfit dominant classes and fail on rare subtypes. We propose a hybrid framework for rare-class generalization that integrates a generative Pix2Pix-based restoration module for artifact removal, a Swin Transformer ensemble with MedSigLIP contrastive embeddings for robust representation learning, and a biologically-inspired refinement step using geometric spikiness and Mahalanobis-based morphological constraints to recover out-of-distribution predictions. Evaluated on the WBCBench 2026 challenge, our method achieves a Macro-F1 of 0.77139 on the private leaderboard, demonstrating strong performance under severe imbalance and highlighting the value of incorporating biological priors into deep learning for hematological image analysis. The code is available at https://github.com/trongduc-nguyen/WBCBench2026

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑