Affordable Access

deepdyve-link
Publisher Website

COVID-19 lesion detection and segmentation-A deep learning method.

Authors
  • Jingxin, Liu1
  • Mengchao, Zhang1
  • Yuchen, Liu2
  • Jinglei, Cui3
  • Yutong, Zhong4
  • Zhong, Zhang5
  • Lihui, Zu6
  • 1 Department of Radiology, China-Japan Union Hospital, Jilin University, Changchun, China. , (China)
  • 2 School of Medical Information, Changchun University of Chinese Medicine, Changchun, China. , (China)
  • 3 Medical Imaging Engineering Technology R&D Center of Jilin Province, Changchun, China. , (China)
  • 4 Electronic Information Engineering College, Changchun University of Science and Technology, Changchun, China. , (China)
  • 5 R&D Department, WX Medical Technology Co., Shenyang, China. Electronic address: [email protected] , (China)
  • 6 Department of Radiology, China-Japan Union Hospital, Jilin University, Changchun, China. Electronic address: [email protected] , (China)
Type
Published Article
Journal
Methods
Publisher
Elsevier
Publication Date
Jun 01, 2022
Volume
202
Pages
62–69
Identifiers
DOI: 10.1016/j.ymeth.2021.07.001
PMID: 34237453
Source
Medline
Keywords
Language
English
License
Unknown

Abstract

In this paper, we utilized deep learning methods to screen the positive COVID-19 cases in chest CT. Our primary goal is to supply rapid and precise assistance for disease surveillance on the medical imaging aspect. Basing on deep learning, we combined semantic segmentation and object detection methods to study the lesion performance of COVID-19. We put forward a novel end-to-end model which takes advantage of the Spatio-temporal features. Furthermore, a segmentation model attached with a fully connected CRF was designed for a more effective ROI input. Our method showed a better performance across different metrics against the comparison models. Moreover, our strategy highlighted strong robustness for the processed augmented testing samples. The comprehensive fusion of Spatio-temporal correlations can exploit more valuable features for locating target regions, and this mechanism is friendly to detect tiny lesions. Although it remains in discrete form, the feature extracting in temporal dimension improves the precision of final prediction. Copyright © 2021 Elsevier Inc. All rights reserved.

Report this publication

Statistics

Seen <100 times