Segmentation and classification of lungs CT-scan for detecting COVID-19 abnormalities by deep learning technique: U-Net model

Abdoulreza S Moosavi; Ashraf Mahboobi; Farzin Arabzadeh; Nazanin Ramezani; Helia S Moosavi; Golbarg Mehrpoor

doi:10.4103/jfmpc.jfmpc_695_23

Segmentation and classification of lungs CT-scan for detecting COVID-19 abnormalities by deep learning technique: U-Net model

J Family Med Prim Care. 2024 Feb;13(2):691-698. doi: 10.4103/jfmpc.jfmpc_695_23. Epub 2024 Mar 6.

Authors

Abdoulreza S Moosavi¹, Ashraf Mahboobi², Farzin Arabzadeh³, Nazanin Ramezani⁴, Helia S Moosavi⁵, Golbarg Mehrpoor⁶

Affiliations

¹ Department of Radiologist, Golestan Radiology and Sonography Clinic, Tehran, Iran.
² Department of Radiologist, Babol University of Medical Sciences, Babol, Iran.
³ Department of Radiologist, Dr. Arabzadeh Radiology and Sonography Clinic, Behbahan, Iran.
⁴ School of Medicine, Tehran University of Medical Sciences, Tehran, Iran.
⁵ Computer Science Bachelor Degree, University of Toronto, On, Canada.
⁶ Department of Rheumatologist, Alborz University of Medical Sciences, Karaj, Iran.

Abstract

Background: Artificial intelligence (AI) techniques have been ascertained useful in the analysis and description of infectious areas in radiological images promptly. Our aim in this study was to design a web-based application for detecting and labeling infected tissues on CT (computed tomography) lung images of patients based on the deep learning (DL) method as a type of AI.

Materials and methods: The U-Net architecture, one of the DL networks, is used as a hybrid model with pre-trained densely connected convolutional network 121 (DenseNet121) architecture for the segmentation process. The proposed model was constructed on 1031 persons' CT-scan images from Ibn Sina Hospital of Iran in 2021 and some publicly available datasets. The network was trained using 6000 slices, validated on 1000 slices images, and tested against the 150 slices. Accuracy, sensitivity, specificity, and area under the receiver operating characteristics (ROC) curve (AUC) were calculated to evaluate model performance.

Results: The results indicate the acceptable ability of the U-Net-DenseNet121 model in detecting COVID-19 abnormality (accuracy = 0.88 and AUC = 0.96 for thresholds of 0.13 and accuracy = 0.88 and AUC = 0.90 for thresholds of 0.2). Based on this model, we developed the "Imaging-Tech" web-based application for use at hospitals and clinics to make our project's output more practical and attractive in the market.

Conclusion: We designed a DL-based model for the segmentation of COVID-19 CT scan images and, based on this model, constructed a web-based application that, according to the results, is a reliable detector for infected tissue in lung CT-scans. The availability of such tools would aid in automating, prioritizing, fastening, and broadening the treatment of COVID-19 patients globally.

Keywords: COVID-19; Classification; U-Net model; deep learning; lungs CT-scan; segmentation.