Department of Digital Medicine, School of Biomedical Engineering and Imaging Medicine, Army Medical University (Third Military Medical University), Chongqing, 400038, China.
Department of Radiology, Southwest Hospital, Army Medical University (Third Military Medical University), Chongqing, 400038, China.
Comput Biol Med. 2022 Aug;147:105732. doi: 10.1016/j.compbiomed.2022.105732. Epub 2022 Jun 15.
Lung infections caused by bacteria and viruses are infectious and require timely screening and isolation, and different types of pneumonia require different treatment plans. Therefore, finding a rapid and accurate screening method for lung infections is critical. To achieve this goal, we proposed a multi-branch fusion auxiliary learning (MBFAL) method for pneumonia detection from chest X-ray (CXR) images. The MBFAL method was used to perform two tasks through a double-branch network. The first task was to recognize the absence of pneumonia (normal), COVID-19, other viral pneumonia and bacterial pneumonia from CXR images, and the second task was to recognize the three types of pneumonia from CXR images. The latter task was used to assist the learning of the former task to achieve a better recognition effect. In the process of auxiliary parameter updating, the feature maps of different branches were fused after sample screening through label information to enhance the model's ability to recognize case of pneumonia without impacting its ability to recognize normal cases. Experiments show that an average classification accuracy of 95.61% is achieved using MBFAL. The single class accuracy for normal, COVID-19, other viral pneumonia and bacterial pneumonia was 98.70%, 99.10%, 96.60% and 96.80%, respectively, and the recall was 97.20%, 98.60%, 96.10% and 89.20%, respectively, using the MBFAL method. Compared with the baseline model and the model constructed using the above methods separately, better results for the rapid screening of pneumonia were achieved using MBFAL.
细菌和病毒引起的肺部感染具有传染性，需要及时进行筛查和隔离，不同类型的肺炎需要不同的治疗方案。因此，找到一种快速准确的肺部感染筛查方法至关重要。为了实现这一目标，我们提出了一种基于多分支融合辅助学习（MBFAL）的用于从胸部 X 射线（CXR）图像中检测肺炎的方法。MBFAL 方法通过双分支网络执行两项任务。第一项任务是从 CXR 图像中识别是否存在肺炎（正常）、COVID-19、其他病毒性肺炎和细菌性肺炎，第二项任务是从 CXR 图像中识别这三种肺炎。第二项任务用于辅助第一项任务的学习，以达到更好的识别效果。在辅助参数更新过程中，通过标签信息对样本进行筛选后融合不同分支的特征图，增强模型识别无肺炎病例的能力，同时不影响其识别正常病例的能力。实验表明，MBFAL 可实现平均分类准确率 95.61%。MBFAL 对正常、COVID-19、其他病毒性肺炎和细菌性肺炎的单类准确率分别为 98.70%、99.10%、96.60%和 96.80%，召回率分别为 97.20%、98.60%、96.10%和 89.20%。与基线模型和单独使用上述方法构建的模型相比，MBFAL 可实现更好的肺炎快速筛查效果。
