Qiblawey Yazan, Tahir Anas, Chowdhury Muhammad E H, Khandakar Amith, Kiranyaz Serkan, Rahman Tawsifur, Ibtehaz Nabil, Mahmud Sakib, Maadeed Somaya Al, Musharavati Farayi, Ayari Mohamed Arselene
Department of Electrical Engineering, Qatar University, Doha 2713, Qatar.
Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology, Dhaka 1205, Bangladesh.
Diagnostics (Basel). 2021 May 17;11(5):893. doi: 10.3390/diagnostics11050893.
Detecting COVID-19 at an early stage is essential to reduce the mortality risk of the patients. In this study, a cascaded system is proposed to segment the lung, detect, localize, and quantify COVID-19 infections from computed tomography images. An extensive set of experiments were performed using Encoder-Decoder Convolutional Neural Networks (ED-CNNs), UNet, and Feature Pyramid Network (FPN), with different backbone (encoder) structures using the variants of DenseNet and ResNet. The conducted experiments for lung region segmentation showed a Dice Similarity Coefficient (DSC) of 97.19% and Intersection over Union (IoU) of 95.10% using U-Net model with the DenseNet 161 encoder. Furthermore, the proposed system achieved an elegant performance for COVID-19 infection segmentation with a DSC of 94.13% and IoU of 91.85% using the FPN with DenseNet201 encoder. The proposed system can reliably localize infections of various shapes and sizes, especially small infection regions, which are rarely considered in recent studies. Moreover, the proposed system achieved high COVID-19 detection performance with 99.64% sensitivity and 98.72% specificity. Finally, the system was able to discriminate between different severity levels of COVID-19 infection over a dataset of 1110 subjects with sensitivity values of 98.3%, 71.2%, 77.8%, and 100% for mild, moderate, severe, and critical, respectively.
早期检测新冠病毒对于降低患者的死亡风险至关重要。在本研究中，提出了一种级联系统，用于从计算机断层扫描图像中分割肺部、检测、定位和量化新冠病毒感染情况。使用编码器-解码器卷积神经网络（ED-CNN）、U-Net和特征金字塔网络（FPN）进行了一系列广泛的实验，采用了不同的骨干（编码器）结构，包括DenseNet和ResNet的变体。针对肺部区域分割进行的实验表明，使用带有DenseNet 161编码器的U-Net模型时，骰子相似系数（DSC）为97.19%，交并比（IoU）为95.10%。此外，所提出的系统在使用带有DenseNet201编码器的FPN进行新冠病毒感染分割时，取得了出色的性能，DSC为94.13%，IoU为91.85%。所提出的系统能够可靠地定位各种形状和大小的感染区域，特别是小感染区域，而这些在最近的研究中很少被考虑。此外，所提出的系统在新冠病毒检测方面取得了较高的性能，灵敏度为99.64%，特异性为98.72%。最后，该系统能够在一个包含1110名受试者的数据集上区分新冠病毒感染的不同严重程度，对于轻度、中度、重度和危重症的灵敏度值分别为98.3%、71.2%、77.8%和100%。
