Your browser doesn't support javascript.
An Expert System for COVID-19 Infection Tracking in Lungs Using Image Processing and Deep Learning Techniques.
Subramaniam, Umashankar; Subashini, M Monica; Almakhles, Dhafer; Karthick, Alagar; Manoharan, S.
  • Subramaniam U; Department of Communications and Networks, Prince Sultan University, 11586 Riyadh, Saudi Arabia.
  • Subashini MM; Department of Control and Automation, School of Electrical Engineering, Vellore Institute of Technology, 632014 Vellore, India.
  • Almakhles D; Department of Communications and Networks, Prince Sultan University, 11586 Riyadh, Saudi Arabia.
  • Karthick A; Renewable Energy Lab, Department of Electrical and Electronics Engineering, KPR Institute of Engineering and Technology, Arasur, Coimbatore 641407, Tamilnadu, India.
  • Manoharan S; Department of Computer Science, School of Informatics and Electrical Engineering, Institute of Technology, Ambo University, Ambo Post Box No.: 19, Ethiopia.
Biomed Res Int ; 2021: 1896762, 2021.
Article in English | MEDLINE | ID: covidwho-1511530
ABSTRACT
The proposed method introduces algorithms for the preprocessing of normal, COVID-19, and pneumonia X-ray lung images which promote the accuracy of classification when compared with raw (unprocessed) X-ray lung images. Preprocessing of an image improves the quality of an image increasing the intersection over union scores in segmentation of lungs from the X-ray images. The authors have implemented an efficient preprocessing and classification technique for respiratory disease detection. In this proposed method, the histogram of oriented gradients (HOG) algorithm, Haar transform (Haar), and local binary pattern (LBP) algorithm were applied on lung X-ray images to extract the best features and segment the left lung and right lung. The segmentation of lungs from the X-ray can improve the accuracy of results in COVID-19 detection algorithms or any machine/deep learning techniques. The segmented lungs are validated over intersection over union scores to compare the algorithms. The preprocessed X-ray image results in better accuracy in classification for all three classes (normal/COVID-19/pneumonia) than unprocessed raw images. VGGNet, AlexNet, Resnet, and the proposed deep neural network were implemented for the classification of respiratory diseases. Among these architectures, the proposed deep neural network outperformed the other models with better classification accuracy.
Subject(s)

Full text: Available Collection: International databases Database: MEDLINE Main subject: Image Processing, Computer-Assisted / COVID-19 / Lung Type of study: Prognostic study Limits: Humans Language: English Journal: Biomed Res Int Year: 2021 Document Type: Article Affiliation country: 2021

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Image Processing, Computer-Assisted / COVID-19 / Lung Type of study: Prognostic study Limits: Humans Language: English Journal: Biomed Res Int Year: 2021 Document Type: Article Affiliation country: 2021