Detection and segmentation of lesion areas in chest CT scans for the prediction of COVID-19

Science in Information Technology Letters

View Publication Info
 
 
Field Value
 
Title Detection and segmentation of lesion areas in chest CT scans for the prediction of COVID-19
 
Creator Ter-Sarkisov, Aram
 
Subject COVID-19; Lesion Segmentation; Pneumonia Classification; Mask R-CNN
 
Description This paper compares the models for the detection and segmentation of Ground Glass Opacity and Consolidation in chest CT scans. These lesion areas are often associated both with common pneumonia and COVID-19. We train a Mask R-CNN model to segment these areas with high accuracy using three approaches: merging masks for these lesions into one, deleting the mask for Consolidation, and using both masks separately. The best model achieves the mean average precision of 44.68% using MS COCO criterion on the segmentation across all accuracy thresholds. The classification model, COVID-CT-Mask-Net, learns to predict the presence of COVID-19 vs. common pneumonia vs. control. The model achieves the 93.88% COVID-19 sensitivity, 95.64% overall accuracy, 95.06% common pneumonia sensitivity, and 96.91% true-negative rate on the COVIDx-CT test split (21192 CT scans) using a small fraction of the training data. We also analyze the effect of the Non-Maximum Suppression of overlapping object predictions, both on the segmentation and classification accuracy. The full source code, models, and pre-trained weights are available on https://github.com/AlexTS1980/COVID-CT-Mask-Net.
 
Publisher Association for Scientific Computing Electronics and Engineering (ASCEE)
 
Contributor
 
Date 2020-11-30
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion

 
Format application/pdf
 
Identifier https://pubs2.ascee.org/index.php/sitech/article/view/202
10.31763/sitech.v1i2.202
 
Source Science in Information Technology Letters; Vol 1, No 2: November 2020; 92-99
2722-4139
 
Language eng
 
Relation https://pubs2.ascee.org/index.php/sitech/article/view/202/pdf
https://pubs2.ascee.org/index.php/sitech/article/downloadSuppFile/202/30
 
Rights Copyright (c) 2020 Aram Ter-Sarkisov
https://creativecommons.org/licenses/by-sa/4.0
 

Contact Us

The PKP Index is an initiative of the Public Knowledge Project.

For PKP Publishing Services please use the PKP|PS contact form.

For support with PKP software we encourage users to consult our wiki for documentation and search our support forums.

For any other correspondence feel free to contact us using the PKP contact form.

Find Us

Twitter

Copyright © 2015-2018 Simon Fraser University Library