基于HA-Net模型的职业性尘肺病筛查  

Occupational Pneumoconiosis Screening Based on HA-Net Model

作　　者：王家乐 宋文爱[1] 富丽贞[1] WANG Jiale;SONG Wenai;FU Lizhen(School of Software,North University of China,Taiyuan 030024,China)

机构地区：[1]中北大学软件学院,山西太原030024

出　　处：《计算机与现代化》2025年第4期103-110,共8页Computer and Modernization

基　　金：国家青年基金资助项目(61602467);中北大学研究生科技立项(20231960)。

摘　　要：通过深度学习方法与注意力机制的结合,提高基于数字化X射线摄影的职业性尘肺病筛查的准确率和效率。提出一种改进的深度学习模型HA-Net(Hybrid Attention Network),融合SEB(Squeeze-and-Excitation Block)和CAB(Coordinate Attention Block),以增强特征表示能力。SEB通过全局平均池化提取通道间的关系信息,利用全连接层调整通道权重,并将调整后的权重与原输入特征图相乘,强化重要特征。CAB通过水平方向和垂直方向的全局池化捕捉空间信息,再经由1×1卷积和通道数恢复生成注意力权重,进而与SEB处理后的特征图相乘,最后集成于ResNet50V2模型中,区分有尘肺病和无尘肺病的影像,并对疑似病例进行准确筛查。实验结果显示,该模型在职业性尘肺病的筛查任务中表现出色,准确率高,能够可靠地检测出尘肺病例,同时对疑似病例的识别也具有高精度和敏感性。By combining deep learning methods and attention mechanisms,this study aims to improve the accuracy and efficiency of screening for occupational pneumoconiosis based on digital radiography.An improved deep learning model,hybrid attention network(HA-Net),is proposed,which integrates squeeze-and-excitation block(SEB)and coordinate attention block(CAB)to enhance feature representation capabilities.SEB extracts inter-channel relationship information through global average pooling,uses fully connected layers to adjust channel weights,and multiplies the adjusted weights with the original input feature maps to strengthen important features.CAB captures spatial information through global pooling in both horizontal and vertical directions,then generates attention weights via 1×1 convolution and channel restoration,which are subsequently multiplied with the feature maps processed by SEB.Finally,these components are integrated into the ResNet50V2 model to distinguish between pneumoconiosis and non-pneumoconiosis images and accurately screen suspected cases.Experimental results show that the proposed model performs excellently in the task of screening occupational pneumoconiosis with high accuracy.It can reliably detect pneumoconiosis cases and also demonstrates high precision and sensitivity in identifying suspected cases.

关 键 词：尘肺病 注意力机制 深度学习 职业病筛查 数字化X射线摄影 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]