Chest X ray and cough sample based deep learning framework for accurate diagnosis of COVID-19

Santosh Kumar; Rishab Nagar; Saumya Bhatnagar; Ramesh Vaddi; Sachin Kumar Gupta; Mamoon Rashid; Ali Kashif Bashir; Tamim Alkhalifah

doi:10.1016/j.compeleceng.2022.108391

Chest X ray and cough sample based deep learning framework for accurate diagnosis of COVID-19

Comput Electr Eng. 2022 Oct:103:108391. doi: 10.1016/j.compeleceng.2022.108391. Epub 2022 Sep 14.

Authors

Santosh Kumar¹, Rishab Nagar¹, Saumya Bhatnagar¹, Ramesh Vaddi², Sachin Kumar Gupta³, Mamoon Rashid^{4

5}, Ali Kashif Bashir⁶, Tamim Alkhalifah⁷

Affiliations

¹ Department of Computer Science and Engineering, International Institute of Information Technology, Naya Raipur, Raipur, Chhattisgarh, 493661, India.
² Department of Electronics and Communication Engineering, School of Engineering and Applied Sciences, SRM University, Amaravati, Guntur, Andhra Pradesh, 522240, India.
³ School of Electronics and Communication Engineering, Shri Mata Vaishno Devi University, Katra, India.
⁴ Department of Computer Engineering, Faculty of Science and Technology, Vishwakarma University, Pune, India.
⁵ Vishwakarma University Research Center of Excellence for Health Informatics, Pune, India.
⁶ Department of Computing and Mathematics, Manchester Metropolitan University, Manchester, UK.
⁷ Department of computer science, College of Science and Arts in Ar Rass, Qassim University, Saudi Arabia.

Abstract

All witnessed the terrible effects of the COVID-19 pandemic on the health and work lives of the population across the world. It is hard to diagnose all infected people in real time since the conventional medical diagnosis of COVID-19 patients takes a couple of days for accurate diagnosis results. In this paper, a novel learning framework is proposed for the early diagnosis of COVID-19 patients using hybrid deep fusion learning models. The proposed framework performs early classification of patients based on collected samples of chest X-ray images and Coswara cough (sound) samples of possibly infected people. The captured cough samples are pre-processed using speech signal processing techniques and Mel frequency cepstral coefficient features are extracted using deep convolutional neural networks. Finally, the proposed system fuses extracted features to provide 98.70% and 82.7% based on Chest-X ray images and cough (audio) samples for early diagnosis using the weighted sum-rule fusion method.

Keywords: COVID-19; Chest X-ray; Cough-breathing sounds; Deep learning; Multimodal; Segmentation.