基于高效通道注意力的胸部X光片疾病分类算法  

Disease Classification Algorithm of Chest X-Ray Based on Efficient Channel Attention

作　　者：邵凌云 李锵 关欣 丁学文[2] Shao Lingyun;Li Qiang;Guan Xin;Ding Xuewen(School of Microelectronics,Tianjin University,Tianjin 300072,China;Tianjin Fieldbus Control Technology Engineering Center,Tianjin Vocational and Technical Normal University,Tianjin 300222,China)

机构地区：[1]天津大学微电子学院,天津300072 [2]天津职业技术师范大学天津市现场总线控制技术工程中心,天津300222

出　　处：《激光与光电子学进展》2023年第12期350-359,共10页Laser & Optoelectronics Progress

基　　金：国家自然科学基金(62071323,61471263,61872267);天津市自然科学基金(16JCZDJC31100);天津市科技计划项目(20YDTPJC01110);天津大学自主创新基金(2021XZC-0024)。

摘　　要：深入研究不同肺部疾病的X射线光片,有助于更清晰、准确地区分和预测各种疾病。基于此,提出一种基于高效通道注意力机制的胸部X光片疾病分类算法。将高效通道注意力模块以密集连接的方式加入基础特征提取网络,以增强特征通道中有效信息的传递,同时抑制无效信息的传递;使用非对称卷积块提高网络特征提取能力;采用多标签损失函数解决多标签和数据不平衡的问题。将新型冠状病毒肺炎X光片添加到公开数据集Chest X-ray 14中构成数据集Chest X-ray 15,在该数据集上的实验结果表明,所提基于高效通道注意力机制的胸部X光片疾病分类算法的平均area under curve(AUC)值达到0.8245,对气胸的AUC值达到0.8829,性能优于对比算法。Extensive investigations of X-ray films of different lung diseases will help to precisely distinguish and predict various diseases.Herein,an algorithm for chest X-ray disease classification based on an efficient channel attention mechanism is proposed.The high-efficiency channel attention module is added to the basic feature extraction network in a densely connected manner to improve the transmission of effective information in the feature channel while inhibiting the transmission of invalid information.By using asymmetric convolution blocks to improve the ability of network feature extraction,the multilabel loss function is used to address multilabeling and data imbalance.The novel coronavirus pneumonia X-ray film is added to the public dataset,Chest X-ray 14,to form the dataset,Chest X-ray 15.The experimental results on this dataset show that the average area under curve(AUC)value of the proposed chest X-ray-film disease classification algorithm based on the efficient channel attention mechanism reaches 0.8245,and the AUC value for pneumothorax reaches 0.8829.Thus,the proposed algorithm is superior to comparison algorithms.

关 键 词：医用光学 医学图像处理 胸部X光片 卷积神经网络 高效通道注意力 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]