融合生物先验与深度学习，提升罕见白细胞分类准确率
Synergizing Deep Learning and Biological Heuristics for Extreme Long-Tail White Blood Cell Classification
- 用生成模型去噪，结合Transformer和对比学习提取鲁棒特征
- 在极端长尾数据下实现0.771的宏平均F1，显著优于传统方法
- 适合血液图像分析、医学影像诊断等需要泛化能力的研究者
自动化白细胞分类对白血病筛查至关重要，但受极端类别不平衡、长尾分布和域偏移影响，深度模型易过拟合常见类型而忽略罕见亚型。本文提出一种混合框架，包含基于Pix2Pix的生成修复模块以去除伪影，采用Swin Transformer集成与MedSigLIP对比嵌入进行鲁棒表征学习，并引入基于几何尖锐度和马氏距离的生物学启发修正步骤，恢复分布外预测。在WBCBench 2026挑战赛上，该方法在私有排行榜取得0.77139的宏平均F1，验证了在严重不平衡条件下性能优越，凸显将生物先验融入深度学习对血液图像分析的价值。代码已开源。
原文摘要 · Abstract (English)
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
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。