用生物启发的损失函数提升骨髓细胞分类准确率，适合临床高风险场景。
CytoDINO: Risk-Aware and Biologically-Informed Adaptation of DINOv3 for Bone Marrow Cytomorphology
- 基于层级焦点损失与关键惩罚，强化危险误判的识别
- 在21类细胞上达88.2%加权F1、76.5%宏F1，性能领先
- 仅用8%参数微调，单张消费级显卡即可部署
骨髓细胞形态分析对血液系统恶性肿瘤诊断至关重要，但依赖人工且存在显著观察者差异。尽管近期基础模型在计算病理学中展现潜力，却常需大量算力，且未考虑临床误诊的非对称风险。本文提出CytoDINO，通过低秩适配（LoRA）微调DINOv3，在慕尼黑白血病实验室（MLL）数据集上实现最优性能。核心创新为一种含关键惩罚的分层焦点损失，编码细胞谱系生物学关系，并显式惩罚高危误判（如将原始细胞误判为正常细胞）。模型在21类细胞的保留测试集上取得88.2%加权F1和76.5%宏F1。仅使用8%可训练参数，在单张NVIDIA RTX 5080上完成训练，证明消费级硬件可媲美专用设施。此外，基于置信度的选择性预测在67%样本上达到99.5%准确率，为临床部署提供可行路径——高不确定性样本可标记由专家复核。
原文摘要 · Abstract (English)
Bone marrow cell cytomorphology analysis is critical for the diagnosis of hematological malignancies but remains a labor-intensive process subject to significant inter-observer variability. While recent foundation models have shown promise in computational pathology, they often require extensive computational resources and fail to account for the asymmetric risks associated with clinical misdiagnosis. We introduce CytoDINO, a framework that achieves state-of-the-art performance on the Munich Leukemia Laboratory (MLL) dataset by fine-tuning DINOv3 using Low-Rank Adaptation (LoRA). Our primary contribution is a novel Hierarchical Focal Loss with Critical Penalties, which encodes biological relationships between cell lineages and explicitly penalizes clinically dangerous misclassifications (e.g., classifying blasts as normal cells). CytoDINO achieves an 88.2% weighted F1 score and 76.5% macro F1 on a held-out test set of 21 cell classes. By utilizing parameter-efficient fine-tuning with only 8% trainable parameters on a single NVIDIA RTX 5080, we demonstrate that consumer-grade hardware can match specialized infrastructure. Furthermore, confidence-based selective prediction yields 99.5% accuracy on 67% of samples, suggesting a viable pathway for clinical deployment where high-uncertainty cases are flagged for expert review
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。