用自注意力增强的CNN模型，精准识别骨髓涂片中的急性淋巴细胞白血病。
Deep Learning with Self-Attention and Enhanced Preprocessing for Precise Diagnosis of Acute Lymphoblastic Leukemia from Bone Marrow Smears in Hemato-Oncology
- 在VGG19中加入多头自注意力模块，捕捉细胞间的长程关系。
- 结合焦点损失训练，99.25%准确率超越ResNet101基线。
- 适合临床辅助诊断，提升白血病筛查效率与可靠性。
急性淋巴细胞白血病（ALL）是儿童和成人中常见的血液系统恶性肿瘤。早期准确检测并精确分型对治疗指导至关重要。传统流程复杂、耗时且易出错。本文提出一种深度学习框架，实现骨髓涂片图像的自动化ALL诊断。方法结合稳健的预处理流程与卷积神经网络（CNN），统一图像质量，提升推理效率。关键设计是在VGG19主干网络中嵌入多头自注意力（MHSA）模块，以建模细胞特征间的长程依赖与上下文关系。为缓解类别不平衡问题，采用焦点损失（Focal Loss）进行训练。在多个架构中，经焦点损失优化的增强型VGG19+MHSA达到99.25%准确率，优于强基线ResNet101的98.62%。结果表明，注意力增强的CNN结合针对性损失优化与预处理，能生成更具区分性的白血病细胞形态表征。该方法为自动化ALL识别与分型提供高精度、低延迟工具，有望加速诊断流程，支持临床决策。
原文摘要 · Abstract (English)
Acute lymphoblastic leukemia (ALL) is a prevalent hematological malignancy in both pediatric and adult populations. Early and accurate detection with precise subtyping is essential for guiding therapy. Conventional workflows are complex, time-consuming, and prone to human error. We present a deep learning framework for automated ALL diagnosis from bone marrow smear images. The method combines a robust preprocessing pipeline with convolutional neural networks (CNNs) to standardize image quality and improve inference efficiency. As a key design, we insert a multi-head self-attention (MHSA) block into a VGG19 backbone to model long-range dependencies and contextual relationships among cellular features. To mitigate class imbalance, we train with Focal Loss. Across evaluated architectures, the enhanced VGG19+MHSA trained with Focal Loss achieves 99.25% accuracy, surpassing a strong ResNet101 baseline (98.62%). These results indicate that attention-augmented CNNs, coupled with targeted loss optimization and preprocessing, yield more discriminative representations of leukemic cell morphology. Our approach offers a highly accurate and computationally efficient tool for automated ALL recognition and subtyping, with potential to accelerate diagnostic workflows and support reliable decision-making in clinical settings.
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。