arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.23271cs.CV
收藏

一种用于对抗域偏移的白血球分类分层集成推理管道

A Hierarchical Ensemble Inference Pipeline for Robust White Blood Cell Classification Under Domain Shifts

Department of Computer Science and Engineering(计算机科学与工程系);The Hong Kong University of Science and Technology(香港理工大学);Department of Chemical and Biological Engineering(化学与生物工程系);Division of Life Science(生命科学系);HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute(香港科技大学深圳-香港协同创新研究院);State Key Laboratory of Nervous System Disorders(神经系统疾病国家重点实验室)

Ruyi Dai, Tingkwong Ng, Hao Chen

AI总结:

本文提出一种分层集成管道,通过特征库和LoRA微调的DinoBloom骨干网络,提升白血球分类在域偏移下的鲁棒性,特别是在识别白血病关键稀有亚型上表现优异。

摘要:

自动化白血球(WBC)分类对大规模白血病筛查至关重要。然而,现实部署受到染色协议、扫描仪特性和实验室间差异引起的域偏移挑战,通常会降低模型性能。ISBI 2026的白血球分类挑战(WBCBench)旨在推动鲁棒的WBC识别,重点是准确识别 blasts 细胞和其他临床关键稀有亚型。我们提出了一种内存增强的分层集成管道,利用特征库和通过LoRA微调的DinoBloom骨干网络。我们的三阶段推理层次在每个层级结合k最近邻(kNN)检索,减少对单一决策的依赖。在WBCBench数据集上评估,我们的方法在最终测试阶段的宏F1分数排名前十。

英文摘要:

Automated white blood cell (WBC) classification is essential for scalable leukaemia screening. However, real-world deployment is challenged by domain shifts caused by staining protocols, scanner characteristics, and inter-laboratory variability, which often degrade model performance. The White Blood Cell Classification Challenge (WBCBench) at ISBI 2026 aims to advance robust WBC recognition, with a focus on accurately identifying blast cells and other clinically critical rare subtypes. We propose a memory-augmented, hierarchical ensemble pipeline for WBC classification under domain shifts, leveraging a feature bank and a DinoBloom backbone fine-tuned with LoRA. Our three-stage inference hierarchy combines k-nearest neighbors (kNN) retrieval at each level, reducing over-reliance on any single decision. Evaluated on the WBCBench dataset, our method ranks within the top ten by macro F1-score in the final testing phase.

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。

↑