整合四个血细胞数据集，用迁移学习提升检测精度与速度。
Generalizable Blood Cell Detection via Unified Dataset and Faster R-CNN
- 统一四个公开数据集，构建标准化血细胞图像资源。
- 迁移学习使模型收敛更快，验证损失低至0.08666。
- 适合医学图像分析与自动化诊断系统开发者参考。
本文提出一种全自动外周血细胞（PBCs）检测与分类的综合方法，并进行了性能对比分析。针对数据稀缺与异构性难题，首先构建了标准化的数据流水线，将四个公开数据集（PBC、BCCD、Chula、Sickle Cell）合并为统一资源。随后采用基于ResNet-50-FPN主干的先进Faster R-CNN检测框架。通过严格对比两种训练方案：随机初始化基线模型（方案1）与在Microsoft COCO数据集上预训练权重初始化的迁移学习方案（方案2），结果表明迁移学习显著加快收敛速度并提升稳定性，最终验证损失达0.08666，优于基线。该方法为构建高精度、可部署的自动化血液学诊断系统奠定了坚实基础。
原文摘要 · Abstract (English)
This paper presents a comprehensive methodology and comparative performance analysis for the automated classification and object detection of peripheral blood cells (PBCs) in microscopic images. Addressing the critical challenge of data scarcity and heterogeneity, robust data pipeline was first developed to standardize and merge four public datasets (PBC, BCCD, Chula, Sickle Cell) into a unified resource. Then employed a state-of-the-art Faster R-CNN object detection framework, leveraging a ResNet-50-FPN backbone. Comparative training rigorously evaluated a randomly initialized baseline model (Regimen 1) against a Transfer Learning Regimen (Regimen 2), initialized with weights pre-trained on the Microsoft COCO dataset. The results demonstrate that the Transfer Learning approach achieved significantly faster convergence and superior stability, culminating in a final validation loss of 0.08666, a substantial improvement over the baseline. This validated methodology establishes a robust foundation for building high-accuracy, deployable systems for automated hematological diagnosis.
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。