Zheng Xin, Xu Qiqi, Zheng Shiyi, Zhao Luxian, Liu Deyang, Zhang Liangliang
School of Computer and Information, Anqing Normal University, Anqing, 246133, China.
The University Key Laboratory of Intelligent Perception and Computing of Anhui Province, School of Computer and Information, Anqing Normal University, Anqing, 246133, China.
Sci Rep. 2025 Apr 26;15(1):14591. doi: 10.1038/s41598-025-99165-8.
White blood cell (WBC) detection is pivotal in medical diagnostics, crucial for diagnosing infections, inflammations, and certain cancers. Traditional WBC detection methods are labor-intensive and time-consuming. Convolutional Neural Networks (CNNs) are widely used for cell detection due to their strong feature extraction capability. However, they struggle with global information and long-distance dependencies in WBC images. Transformers, on the other hand, excel at modeling long-range dependencies, which improves their performance in vision tasks. To tackle the large foreground-background differences in WBC images, this paper introduces a novel WBC detection method, named the Multi-Scale Cross-Deformation Attention Fusion Network (MCDAF-Net), which combines CNNs and Transformers. The Attention Multi-scale Sensing Module (AMSM) is designed to localize WBCs more accurately by fusing features at different scales and enhancing feature representation through a self-attention mechanism. The Cross-Deformation Convolution Module (CDCM) reduces feature correlation, aiding the model in capturing diverse aspects and patterns in images, thereby improving generalization. MCDAF-Net outperforms other models on public datasets (LISC, BCCD, and WBCDD), demonstrating its superiority in WBC detection. Our code and pretrained models: https://github.com/xqq777/MCDAF-Net .
白细胞（WBC）检测在医学诊断中至关重要，对于诊断感染、炎症和某些癌症起着关键作用。传统的白细胞检测方法 labor-intensive 且耗时。卷积神经网络（CNN）因其强大的特征提取能力而被广泛用于细胞检测。然而，它们在白细胞图像中的全局信息和长距离依赖方面存在困难。另一方面，Transformer 在对长距离依赖进行建模方面表现出色，这提高了它们在视觉任务中的性能。为了解决白细胞图像中前景与背景的巨大差异，本文介绍了一种新颖的白细胞检测方法，称为多尺度交叉变形注意力融合网络（MCDAF-Net），它结合了 CNN 和 Transformer。注意力多尺度感知模块（AMSM）旨在通过融合不同尺度的特征并通过自注意力机制增强特征表示，更准确地定位白细胞。交叉变形卷积模块（CDCM）减少了特征相关性，有助于模型捕捉图像中的各种方面和模式，从而提高泛化能力。MCDAF-Net 在公共数据集（LISC、BCCD 和 WBCDD）上优于其他模型，证明了其在白细胞检测中的优越性。我们的代码和预训练模型：https://github.com/xqq777/MCDAF-Net 。 （注：“labor-intensive”未翻译完整，可能是原文有误，推测是“劳动密集型”）
