Deep learning-based analysis of COVID-19 X-ray images: Incorporating clinical significance and assessing misinterpretation

Md Rahad Islam Bhuiyan; Sami Azam; Sidratul Montaha; Risul Islam Jim; Asif Karim; Inam Ullah Khan; Mark Brady; Md Zahid Hasan; Friso De Boer; Md Saddam Hossain Mukta

doi:10.1177/20552076231215915

Deep learning-based analysis of COVID-19 X-ray images: Incorporating clinical significance and assessing misinterpretation

Digit Health. 2023 Nov 24:9:20552076231215915. doi: 10.1177/20552076231215915. eCollection 2023 Jan-Dec.

Affiliations

¹ Health Informatics Research Laboratory (HIRL), Department of Computer Science and Engineering, Daffodil International University, Dhaka, Bangladesh.
² Faculty of Science and Technology, Charles Darwin University, Casuarina, NT, Australia.
³ Department of Computer Science, University of Calgary, Calgary, Canada.
⁴ School of Law, Faculty of Arts and Society, Charles Darwin University, Casuarina, NT, Australia.
⁵ Department of Computer Science and Engineering, United International University (UIU), Dhaka, Bangladesh.

Abstract

COVID-19, pneumonia, and tuberculosis have had a significant effect on recent global health. Since 2019, COVID-19 has been a major factor underlying the increase in respiratory-related terminal illness. Early-stage interpretation and identification of these diseases from X-ray images is essential to aid medical specialists in diagnosis. In this study, (COV-X-net19) a convolutional neural network model is developed and customized with a soft attention mechanism to classify lung diseases into four classes: normal, COVID-19, pneumonia, and tuberculosis using chest X-ray images. Image preprocessing is carried out by adjusting optimal parameters to preprocess the images before undertaking training of the classification models. Moreover, the proposed model is optimized by experimenting with different architectural structures and hyperparameters to further boost performance. The performance of the proposed model is compared with eight state-of-the-art transfer learning models for a comparative evaluation. Results suggest that the COV-X-net19 outperforms other models with a testing accuracy of 95.19%, precision of 96.49% and F1-score of 95.13%. Another novel approach of this study is to find out the probable reason behind image misclassification by analyzing the handcrafted imaging features with statistical evaluation. A statistical analysis known as analysis of variance test is performed, to identify at which point the model can identify a class accurately, and at which point the model cannot identify the class. The potential features responsible for the misclassification are also found. Moreover, Random Forest Feature importance technique and Minimum Redundancy Maximum Relevance technique are also explored. The methods and findings of this study can benefit in the clinical perspective in early detection and enable a better understanding of the cause of misclassification.

Keywords: ANOVA test; COVID-19; Fourier transform; image processing; misclassified image; pneumonia; soft attention layer; tuberculosis.

Publication types

Review