Deep Convolutional Neural Network–Based Computer-Aided Detection System for COVID-19 Using Multiple Lung Scans: Design and Implementation Study

• Published in: Journal of medical Internet research Vol. 23; no. 4; p. e27468
• Main Authors: Ghaderzadeh, Mustafa, Asadi, Farkhondeh, Jafari, Ramezan, Bashash, Davood, Abolghasemi, Hassan, Aria, Mehrad
• Format: Journal Article
• Language: English
• Published: Canada JMIR Publications 26.04.2021
• Subjects: COVID-19 - diagnostic imaging; COVID-19 - virology; Datasets as Topic; Deep Learning; Diagnosis, Computer-Assisted; Early Diagnosis; Humans; Lung - diagnostic imaging; Lung - virology; Original Paper; Pandemics; SARS-CoV-2 - isolation & purification; Tomography, X-Ray Computed; COVID-19; computed tomography scan; deep learning; convolutional neural network; coronavirus; model; computer-aided detection; classification; machine learning; pandemic; artificial intelligence; machine vision
• ISSN: 1438-8871; 1439-4456; 1438-8871
• DOI: 10.2196/27468

Owing to the COVID-19 pandemic and the imminent collapse of health care systems following the exhaustion of financial, hospital, and medicinal resources, the World Health Organization changed the alert level of the COVID-19 pandemic from high to very high. Meanwhile, more cost-effective and precise COVID-19 detection methods are being preferred worldwide. Machine vision-based COVID-19 detection methods, especially deep learning as a diagnostic method in the early stages of the pandemic, have been assigned great importance during the pandemic. This study aimed to design a highly efficient computer-aided detection (CAD) system for COVID-19 by using a neural search architecture network (NASNet)-based algorithm. NASNet, a state-of-the-art pretrained convolutional neural network for image feature extraction, was adopted to identify patients with COVID-19 in their early stages of the disease. A local data set, comprising 10,153 computed tomography scans of 190 patients with and 59 without COVID-19 was used. After fitting on the training data set, hyperparameter tuning, and topological alterations of the classifier block, the proposed NASNet-based model was evaluated on the test data set and yielded remarkable results. The proposed model's performance achieved a detection sensitivity, specificity, and accuracy of 0.999, 0.986, and 0.996, respectively. The proposed model achieved acceptable results in the categorization of 2 data classes. Therefore, a CAD system was designed on the basis of this model for COVID-19 detection using multiple lung computed tomography scans. The system differentiated all COVID-19 cases from non-COVID-19 ones without any error in the application phase. Overall, the proposed deep learning-based CAD system can greatly help radiologists detect COVID-19 in its early stages. During the COVID-19 pandemic, the use of a CAD system as a screening tool would accelerate disease detection and prevent the loss of health care resources.