COVID-19 Pneumonia Diagnosis Using a Simple 2D Deep Learning Framework With a Single Chest CT Image: Model Development and Validation

Abstract

Background Coronavirus disease (COVID-19) has spread explosively worldwide since the beginning of 2020. According to a multinational consensus statement from the Fleischner Society, computed tomography (CT) is a relevant screening tool due to its higher sensitivity for detecting early pneumonic changes. However, physicians are extremely occupied fighting COVID-19 in this era of worldwide crisis. Thus, it is crucial to accelerate the development of an artificial intelligence (AI) diagnostic tool to support physicians. Objective We aimed to rapidly develop an AI technique to diagnose COVID-19 pneumonia in CT images and differentiate it from non–COVID-19 pneumonia and nonpneumonia diseases. Methods A simple 2D deep learning framework, named the fast-track COVID-19 classification network (FCONet), was developed to diagnose COVID-19 pneumonia based on a single chest CT image. FCONet was developed by transfer learning using one of four state-of-the-art pretrained deep learning models (VGG16, ResNet-50, Inception-v3, or Xception) as a backbone. For training and testing of FCONet, we collected 3993 chest CT images of patients with COVID-19 pneumonia, other pneumonia, and nonpneumonia diseases from Wonkwang University Hospital, Chonnam National University Hospital, and the Italian Society of Medical and Interventional Radiology public database. These CT images were split into a training set and a testing set at a ratio of 8:2. For the testing data set, the diagnostic performance of the four pretrained FCONet models to diagnose COVID-19 pneumonia was compared. In addition, we tested the FCONet models on an external testing data set extracted from embedded low-quality chest CT images of COVID-19 pneumonia in recently published papers. Results Among the four pretrained models of FCONet, ResNet-50 showed excellent diagnostic performance (sensitivity 99.58%, specificity 100.00%, and accuracy 99.87%) and outperformed the other three pretrained models in the testing data set. In the additional external testing data set using low-quality CT images, the detection accuracy of the ResNet-50 model was the highest (96.97%), followed by Xception, Inception-v3, and VGG16 (90.71%, 89.38%, and 87.12%, respectively). Conclusions FCONet, a simple 2D deep learning framework based on a single chest CT image, provides excellent diagnostic performance in detecting COVID-19 pneumonia. Based on our testing data set, the FCONet model based on ResNet-50 appears to be the best model, as it outperformed other FCONet models based on VGG16, Xception, and Inception-v3.

Review on Diagnosis of COVID-19 from Chest CT Images Using Artificial Intelligence

“…Ko et al [ 59 ] proposed a model, a fast-track COVID-19 classification network (FCONet) that used VGG16, ResNet-50, InceptionV3, and Xception as a backbone to classify images as COVID-19, other pneumonia, or nonpneumonia. They considered 1194 COVID-19, 264 low-quality COVID-19 (only for testing), and 2239 pneumonia, normal, and other disease CT scans in their study.…”

Covid-19 classification by FGCNet with deep feature fusion from graph convolutional network and convolutional neural network

“…We compared our DBDRMBN method, i.e., N (8) model, with 15 state-of-the-art approaches: RBFNN [4] , KELM [5] , ELM-BA [6] , RCBBO [7] , 6L-CLF [8] , GoogLeNet [9] , ResNet-18 [10] , RN-50-AD [11] , SMO [12] , CSSNet [13] , GGNet [14] , COVNet [15] , NiNet [16] , FCONet [17] , and DeCovNet [18] . All the methods were compared on the test set of our 640-image dataset.…”

“…Their method is called NiNet in this study. Ko, et al [17] proposed a simple 2D deep learning framework for single CCT image. The authors compared four pretrained models: VGG16, ResNet-50, Inception-V3, and Xception.…”

Applications of artificial intelligence in battling against covid-19: A literature review

“…The authors use some wellknown pre-trained architecture including ResNet18, ResNet50, ResNet101, and SqueezeNet. A classification algorithm based on transfer learning is proposed in [144] which uses four state-of-the-art pretrained deep learning mode. The research uses VGG16, ResNet-50, Inception-v3, and Xception as backbone.…”