Multi-task driven explainable diagnosis of COVID-19 using chest X-ray images

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.

Bilateral adaptive graph convolutional network on CT based Covid-19 diagnosis with uncertainty-aware consensus-assisted multiple instance learning

“…It is known that tackling the NCP diagnosis problem with 2D X-ray or 2D ultrasound images can achieve promising results in many tasks, such as severity assessment ( Signoroni et al, 2021 , Xue et al, 2021 ), infection localisation ( Vieira et al, 2021 , Wang et al, 2021b , Roy et al, 2020 , Malhotra et al, 2021 ) and diagnosis ( Zhong et al, 2021 , Minaee et al, 2020 , Soda et al, 2021 , Oh et al, 2020 , Aviles-Rivero et al, 2022 , Guarrasi et al, 2022 , Kumar et al, 2022 , Shorfuzzaman and Hossain, 2021 , Fan et al, 2021 , Bridge et al, 2020 ). However, compared with CT images, X-ray cannot indicate the significant appearance characteristics of NCP , such as GGO) , multi-focal patchy consolidation and bilateral patchy shadows ( Zhang et al, 2020 ).…”

A teacher–student framework with Fourier Transform augmentation for COVID-19 infection segmentation in CT images

“…[33] proposed to use spatial and channel attention to improve the representation ability of the segmentation network. To address the issue of scarcity of well-labeled data, solutions based on weak supervised, semi-supervised learning and multi-task learning were proposed in the literature [36] , [37] , [38] . Fan et al.…”

Covid-19 Diagnosis Using a Deep Learning Ensemble Model with Chest X-Ray Images

“…Malhotraa et al [11] proposed a multitasking method for the diagnosis of Covid-19 on radiographs. This study has two main contributions.…”