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

Electronics

In-Su Jang¹  Ravi Managuli²  Seungwan Jeon³  Sampa Misra⁴  Seiyon Lee⁴  Chulhong Kim⁴ 

[1] Artificial Intelligence Application Research Section, Electronics and Telecommunications Research Institute (ETRI), Daegu 42994, Korea;Department of Bioengineering, University of Washington, Seattle, WA 98195, USA;Department of Electrical Engineering, Creative IT Engineering, Mechanical Engineering, Graduate School of Artificial Intelligence, and Medical Device Innovation Center, Pohang University of Science and Technology (POSTECH), Pohang 37673, Korea;Opticho, Pohang 37673, Korea;

关键词: COVID-19;    classification;    deep learning;    transfer learning;    X-ray;    ensemble learning;   

DOI  :  10.3390/electronics9091388

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown