Analysis of lung scan imaging using deep multi‐task learning structure for Covid‐19 disease

Abstract

Covid‐19 caused by the SARS‐CoV2 virus has become a pandemic all over the world. By growing in a number of cases, there is a need for clinical decision‐making system based on machine learning models. Most of the previous studies have examined only one task, while the detection and identification of infectious area are conducted simultaneously in the real world. Thus, the present study aims to propose a multi‐task model which can perform automatic classification‐segmentation for screening Covid‐19 pneumonia by using chest CT imaging. This model includes a common encoder for feature representation, one decoder for segmentation, and a multi‐layer perceptron for classification, respectively. The proposed model can evaluate three datasets, along with the effect of images size on the output of the model. The outputs were examined in both multi‐task and single‐task learning. The result indicates that the effect of multi‐task is significant in improving the results, which can increase the outputs of each task performance to 95.40% accuracy in classification and 95.40% in segmentation. Further, the model represented the highest results among the state‐of‐the‐art methods. The proposed model can be applied as a primary screening tool to help primary service staff in better referral of the suspected patients to specialists.

Deep learning‐based COVID‐19 diagnosis using CT scans with laboratory and physiological parameters

“…However, further study is required to examine how various medical pictures affect classification accuracy. Kordnoori et al [46] suggested a deep multitask learning model that can automatically classify and segment lung tissue to screen for Covid-19 pneumonia using chest CT imaging. U-NET architecture was adopted in the proposed method, including ten fully connected layers in the decoder, ten convolutional layers in the common encoder, and ten layers in the perceptron.…”

An efficient deep multi‐task learning structure for covid‐19 disease

“…Kordnoori et al. [15] proposed a multi‐task model with two main tasks of classification and segmentation. Their model contained one common encoder between tasks for representing features.…”

Automatic detection of infected areas of CT images in COVID-19 patients using Inf-Seg-Net

“…Lung segmentation, a vital stage in the automated processing of lung scan pictures, is the subject of Kordnoori et al [20]. The suggested method makes use of a DL framework that combines numerous related tasks, allowing for collaborative learning and information exchange between various parts of lung study.…”