Arnab Kumar Mondal1,2, Arnab Bhattacharjee3, Parag Singla4, A P Prathosh2. 1. Amar Nath and Shashi Khosla School of Information TechnologyIndian Institute of Technology Delhi New Delhi 110016 India. 2. Department of Electrical Communication EngineeringIndian Institute of Science (IISc) Bangalore 560 India. 3. UQ-IITD Academy of ResearchIndian Institute of Technology Delhi New Delhi 110016 India. 4. Department of Computer Science and EngineeringIndian Institute of Technology Delhi New Delhi 110016 India.
Abstract
Objective: Since its outbreak, the rapid spread of COrona VIrus Disease 2019 (COVID-19) across the globe has pushed the health care system in many countries to the verge of collapse. Therefore, it is imperative to correctly identify COVID-19 positive patients and isolate them as soon as possible to contain the spread of the disease and reduce the ongoing burden on the healthcare system. The primary COVID-19 screening test, RT-PCR although accurate and reliable, has a long turn-around time. In the recent past, several researchers have demonstrated the use of Deep Learning (DL) methods on chest radiography (such as X-ray and CT) for COVID-19 detection. However, existing CNN based DL methods fail to capture the global context due to their inherent image-specific inductive bias. Methods: Motivated by this, in this work, we propose the use of vision transformers (instead of convolutional networks) for COVID-19 screening using the X-ray and CT images. We employ a multi-stage transfer learning technique to address the issue of data scarcity. Furthermore, we show that the features learned by our transformer networks are explainable. Results: We demonstrate that our method not only quantitatively outperforms the recent benchmarks but also focuses on meaningful regions in the images for detection (as confirmed by Radiologists), aiding not only in accurate diagnosis of COVID-19 but also in localization of the infected area. The code for our implementation can be found here - https://github.com/arnabkmondal/xViTCOS. Conclusion: The proposed method will help in timely identification of COVID-19 and efficient utilization of limited resources.
Objective: Since its outbreak, the rapid spread of COrona VIrus Disease 2019 (COVID-19) across the globe has pushed the health care system in many countries to the verge of collapse. Therefore, it is imperative to correctly identify COVID-19 positive patients and isolate them as soon as possible to contain the spread of the disease and reduce the ongoing burden on the healthcare system. The primary COVID-19 screening test, RT-PCR although accurate and reliable, has a long turn-around time. In the recent past, several researchers have demonstrated the use of Deep Learning (DL) methods on chest radiography (such as X-ray and CT) for COVID-19 detection. However, existing CNN based DL methods fail to capture the global context due to their inherent image-specific inductive bias. Methods: Motivated by this, in this work, we propose the use of vision transformers (instead of convolutional networks) for COVID-19 screening using the X-ray and CT images. We employ a multi-stage transfer learning technique to address the issue of data scarcity. Furthermore, we show that the features learned by our transformer networks are explainable. Results: We demonstrate that our method not only quantitatively outperforms the recent benchmarks but also focuses on meaningful regions in the images for detection (as confirmed by Radiologists), aiding not only in accurate diagnosis of COVID-19 but also in localization of the infected area. The code for our implementation can be found here - https://github.com/arnabkmondal/xViTCOS. Conclusion: The proposed method will help in timely identification of COVID-19 and efficient utilization of limited resources.
Entities:
Keywords:
AI for COVID-19 detection; CT scan and CXR; deep learning; vision transformer
Authors: Muhammad Owais; Young Won Lee; Tahir Mahmood; Adnan Haider; Haseeb Sultan; Kang Ryoung Park Journal: IEEE J Biomed Health Inform Date: 2021-06-03 Impact factor: 7.021
Authors: Harrison X Bai; Robin Wang; Zeng Xiong; Ben Hsieh; Ken Chang; Kasey Halsey; Thi My Linh Tran; Ji Whae Choi; Dong-Cui Wang; Lin-Bo Shi; Ji Mei; Xiao-Long Jiang; Ian Pan; Qiu-Hua Zeng; Ping-Feng Hu; Yi-Hui Li; Fei-Xian Fu; Raymond Y Huang; Ronnie Sebro; Qi-Zhi Yu; Michael K Atalay; Wei-Hua Liao Journal: Radiology Date: 2020-04-27 Impact factor: 11.105