Multi-Channel Transfer Learning of Chest X-ray Images for Screening of COVID-19

• Published in: Electronics (Basel) Vol. 9; no. 9; p. 1388
• Main Authors: Misra, Sampa, Jeon, Seungwan, Lee, Seiyon, Managuli, Ravi, Jang, In-Su, Kim, Chulhong
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.09.2020
• Subjects: Automatic classification; Chest; Classification; Computer aided medical diagnosis; Coronaviruses; COVID-19; Datasets; Diagnosis; Diagnostic imaging; Feature extraction; Machine learning; Medical imaging; Medical X-ray equipment; Methods; Pneumonia; Polymerase chain reaction; X-rays; South Korea; China
• ISSN: 2079-9292; 2079-9292
• DOI: 10.3390/electronics9091388

The 2019 novel coronavirus (COVID-19) has spread rapidly all over the world. The standard test for screening COVID-19 patients is the polymerase chain reaction test. As this method is time consuming, as an alternative, chest X-rays may be considered for quick screening. However, specialization is required to read COVID-19 chest X-ray images as they vary in features. To address this, we present a multi-channel pre-trained ResNet architecture to facilitate the diagnosis of COVID-19 chest X-ray. Three ResNet-based models were retrained to classify X-rays in a one-against-all basis from (a) normal or diseased, (b) pneumonia or non-pneumonia, and (c) COVID-19 or non-COVID19 individuals. Finally, these three models were ensembled and fine-tuned using X-rays from 1579 normal, 4245 pneumonia, and 184 COVID-19 individuals to classify normal, pneumonia, and COVID-19 cases in a one-against-one framework. Our results show that the ensemble model is more accurate than the single model as it extracts more relevant semantic features for each class. The method provides a precision of 94% and a recall of 100%. It could potentially help clinicians in screening patients for COVID-19, thus facilitating immediate triaging and treatment for better outcomes.