COVID-19 Deep Learning Prediction Model Using Publicly Available Radiologist-Adjudicated Chest X-Ray Images as Training Data: Preliminary Findings. (18th August 2020)

• Record Type: Journal Article
• Authors: Che Azemin, Mohd Zulfaezal; Hassan, Radhiana; Mohd Tamrin, Mohd Izzuddin; Md Ali, Mohd Adli
• Other Names: Chen Jyh-Cheng Academic Editor.
• Is Part Of: International journal of biomedical imaging. Volume 2020(2020)
• Publication Date: 2020-08-18
• Subjects: Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Imagerie pour le diagnostic; Imagerie médicale; Diagnostic imaging; Imaging systems in medicine; Diagnostic Imaging -- Periodicals; Electronic journals; Periodicals; 616.0754
• DOI: 10.1155/2020/8828855
• Languages: English
• ISSNs: 1687-4188

Abstract

Abstract : The key component in deep learning research is the availability of training data sets. With a limited number of publicly available COVID-19 chest X-ray images, the generalization and robustness of deep learning models to detect COVID-19 cases developed based on these images are questionable. We aimed to use thousands of readily available chest radiograph images with clinical findings associated with COVID-19 as a training data set, mutually exclusive from the images with confirmed COVID-19 cases, which will be used as the testing data set. We used a deep learning model based on the ResNet-101 convolutional neural network architecture, which was pretrained to recognize objects from a million of images and then retrained to detect abnormality in chest X-ray images. The performance of the model in terms of area under the receiver operating curve, sensitivity, specificity, and accuracy was 0.82, 77.3%, 71.8%, and 71.9%, respectively. The strength of this study lies in the use of labels that have a strong clinical association with COVID-19 cases and the use of mutually exclusive publicly available data for training, validation, and testing.