Murugan R, Goel Tripti, Mirjalili Seyedali, Chakrabartty Deba Kumar
Bio-Medical Imaging Laboratory(BIOMIL), Department of Electronics and communication Engineering, National Institute Of Technology Silchar, Assam 788010, India.
Centre for Artificial Intelligence Research and Optimisation, Torrens University Australia, Fortitude Valley, Brisbane, QLD 4006, Australia.
Biocybern Biomed Eng. 2021 Oct-Dec;41(4):1702-1718. doi: 10.1016/j.bbe.2021.10.004. Epub 2021 Oct 23.
Coronavirus Diseases (COVID-19) is a new disease that will be declared a global pandemic in 2020. It is characterized by a constellation of traits like fever, dry cough, dyspnea, fatigue, chest pain, etc. Clinical findings have shown that the human chest Computed Tomography(CT) images can diagnose lung infection in most COVID-19 patients. Visual changes in CT scan due to COVID-19 is subjective and evaluated by radiologists for diagnosis purpose. Deep Learning (DL) can provide an automatic diagnosis tool to relieve radiologists' burden for quantitative analysis of CT scan images in patients. However, DL techniques face different training problems like mode collapse and instability. Deciding on training hyper-parameters to adjust the weight and biases of DL by a given CT image dataset is crucial for achieving the best accuracy. This paper combines the backpropagation algorithm and Whale Optimization Algorithm (WOA) to optimize such DL networks. Experimental results for the diagnosis of COVID-19 patients from a comprehensive COVID-CT scan dataset show the best performance compared to other recent methods. The proposed network architecture results were validated with the existing pre-trained network to prove the efficiency of the network.
冠状病毒病（COVID-19）是一种新型疾病，于2020年被宣布为全球大流行疾病。它具有一系列特征，如发热、干咳、呼吸困难、疲劳、胸痛等。临床研究结果表明，人体胸部计算机断层扫描（CT）图像能够诊断出大多数COVID-19患者的肺部感染情况。由COVID-19导致的CT扫描视觉变化具有主观性，需由放射科医生进行评估以用于诊断目的。深度学习（DL）可以提供一种自动诊断工具，减轻放射科医生对患者CT扫描图像进行定量分析的负担。然而，DL技术面临着诸如模式崩溃和不稳定性等不同的训练问题。通过给定的CT图像数据集确定训练超参数以调整DL的权重和偏差，对于实现最佳准确率至关重要。本文将反向传播算法与鲸鱼优化算法（WOA）相结合，以优化此类DL网络。与其他近期方法相比，从综合COVID-CT扫描数据集中诊断COVID-19患者的实验结果显示出最佳性能。所提出的网络架构结果通过现有的预训练网络进行了验证，以证明该网络的有效性。
