Multi-task driven explainable diagnosis of COVID-19 using chest X-ray images. (February 2022)

• Record Type: Journal Article
• Authors: Malhotra, Aakarsh; Mittal, Surbhi; Majumdar, Puspita; Chhabra, Saheb; Thakral, Kartik; Vatsa, Mayank; Singh, Richa; Chaudhury, Santanu; Pudrod, Ashwin; Agrawal, Anjali
• Is Part Of: Pattern recognition. Volume 122(2022)
• Publication Date: 2022-02
• Subjects: X-Ray -- COVID-19 -- Detection -- Diagnostics -- Deep learning -- Explainable artificial intelligence -- Multi-task learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2021.108243
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Develop COMiT-Net with 4 joint tasks to segment lung and disease regions using CXR. COMiT-Net predicts presence of COVID-19 by differentiating them from healthy lungs. Extensive comparison with existing deep learning algorithms for each of the 4 tasks. Assemble frontal CXR from various sources against labels for 4 different tasks. Creating and publicly releasing manual annotations for lung and disease segmentation. Abstract: With increasing number of COVID-19 cases globally, all the countries are ramping up the testing numbers. While the RT-PCR kits are available in sufficient quantity in several countries, others are facing challenges with limited availability of testing kits and processing centers in remote areas. This has motivated researchers to find alternate methods of testing which are reliable, easily accessible and faster. Chest X-Ray is one of the modalities that is gaining acceptance as a screening modality. Towards this direction, the paper has two primary contributions. Firstly, we present the COVID-19 Multi-Task Network (COMiT-Net) which is an automated end-to-end network for COVID-19 screening. The proposed network not only predicts whether the CXR has COVID-19 features present or not, it also performs semantic segmentation of the regions of interest to make the model explainable. Secondly, with the help of medical professionals, we manually annotate the lung regions and semantic segmentation of COVID19 symptoms in CXRs taken from the ChestXray-14, CheXpert, and a consolidated COVID-19 dataset. These annotations will be released to the research community. Experiments performed with more than 2500 frontal CXR images show that at 90% specificity, the proposed COMiT-Net yields 96.80% sensitivity.