Sharma Ajay, Mishra Pramod Kumar
Department of Computer Science, Institute of Science, Banaras Hindu University, Varanasi 221005, India.
Pattern Recognit. 2022 Nov;131:108826. doi: 10.1016/j.patcog.2022.108826. Epub 2022 Jun 6.
The devastating outbreak of Coronavirus Disease (COVID-19) cases in early 2020 led the world to face health crises. Subsequently, the exponential reproduction rate of COVID-19 disease can only be reduced by early diagnosis of COVID-19 infection cases correctly. The initial research findings reported that radiological examinations using CT and CXR modality have successfully reduced false negatives by RT-PCR test. This research study aims to develop an explainable diagnosis system for the detection and infection region quantification of COVID-19 disease. The existing research studies successfully explored deep learning approaches with higher performance measures but lacked generalization and interpretability for COVID-19 diagnosis. In this study, we address these issues by the Covid-MANet network, an automated end-to-end multi-task attention network that works for 5 classes in three stages for COVID-19 infection screening. The first stage of the Covid-MANet network localizes attention of the model to the relevant lungs region for disease recognition. The second stage of the Covid-MANet network differentiates COVID-19 cases from bacterial pneumonia, viral pneumonia, normal and tuberculosis cases, respectively. To improve the interpretation and explainability, three experiments have been conducted in exploration of the most coherent and appropriate classification approach. Moreover, the multi-scale attention model MA-DenseNet201 proposed for the classification of COVID-19 cases. The final stage of the Covid-MANet network quantifies the proportion of infection and severity of COVID-19 in the lungs. The COVID-19 cases are graded into more specific severity levels such as mild, moderate, severe, and critical as per the score assigned by the RALE scoring system. The MA-DenseNet201 classification model outperforms eight state-of-the-art CNN models, in terms of sensitivity and interpretation with lung localization network. The COVID-19 infection segmentation by UNet with DenseNet121 encoder achieves dice score of 86.15% outperforming UNet, UNet++, AttentionUNet, R2UNet, with VGG16, ResNet50 and DenseNet201 encoder. The proposed network not only classifies images based on the predicted label but also highlights the infection by segmentation/localization of model-focused regions to support explainable decisions. MA-DenseNet201 model with a segmentation-based cropping approach achieves maximum interpretation of 96% with COVID-19 sensitivity of 97.75%. Finally, based on class-varied sensitivity analysis Covid-MANet ensemble network of MA-DenseNet201, ResNet50 and MobileNet achieve 95.05% accuracy and 98.75% COVID-19 sensitivity. The proposed model is externally validated on an unseen dataset, yields 98.17% COVID-19 sensitivity.
2020年初，新型冠状病毒肺炎（COVID-19）病例的毁灭性爆发使世界面临健康危机。随后，只有通过正确早期诊断COVID-19感染病例，才能降低COVID-19疾病的指数繁殖率。初步研究结果报告称，使用CT和CXR模式的放射学检查已成功减少了RT-PCR检测中的假阴性。本研究旨在开发一种可解释的诊断系统，用于检测和量化COVID-19疾病的感染区域。现有研究成功探索了具有更高性能指标的深度学习方法，但在COVID-19诊断方面缺乏泛化性和可解释性。在本研究中，我们通过Covid-MANet网络解决这些问题，这是一种自动化的端到端多任务注意力网络，在三个阶段对COVID-19感染进行筛查，适用于5个类别。Covid-MANet网络的第一阶段将模型的注意力定位到相关肺部区域以进行疾病识别。Covid-MANet网络的第二阶段分别将COVID-19病例与细菌性肺炎、病毒性肺炎、正常病例和肺结核病例区分开来。为了提高解释性和可解释性，进行了三个实验以探索最连贯和合适的分类方法。此外，还提出了用于COVID-19病例分类的多尺度注意力模型MA-DenseNet201。Covid-MANet网络的最后阶段量化肺部COVID-19的感染比例和严重程度。根据RALE评分系统分配的分数，将COVID-19病例分为更具体的严重程度级别，如轻度、中度、重度和危重度。MA-DenseNet201分类模型在敏感性和肺部定位网络的可解释性方面优于八个最先进的CNN模型。使用DenseNet121编码器的UNet对COVID-19感染进行分割，骰子分数达到86.15%，优于使用VGG16、ResNet50和DenseNet201编码器的UNet、UNet++、AttentionUNet、R2UNet。所提出的网络不仅根据预测标签对图像进行分类，还通过对模型关注区域的分割/定位突出显示感染情况，以支持可解释的决策。采用基于分割的裁剪方法的MA-DenseNet201模型在COVID-19敏感性为97.75%时，最大解释率达到96%。最后，基于类别可变敏感性分析，MA-DenseNet201、ResNet50和MobileNet的Covid-MANet集成网络实现了95.05%的准确率和98.75%的COVID-19敏感性。所提出的模型在一个未见数据集上进行了外部验证，COVID-19敏感性为98.17%。
