Recently, postdoctoral fellow Ben Ye and Ph.D. student Xixi Yuan at the Faculty of Information Technology of Macau University of Science published an academic article entitled “Severity Assessment of COVID-19 Based on Feature Extraction and V-Descriptors” (DOI: 10.1109/TII.2021.3056386) in the top international academic journal IEEE Transactions on Industrial Informatics, wherein the Macau University of Science and Technology is the only affiliation to complete this article, and Prof. Zhanchuan Cai is the corresponding author.
This study was independently completed by the researchers from the Macau University of Science and Technology, and mainly investigated on the segmentation, detection, and diagnosis of COVID-19 infection based on chest CT images. This research proposes a new method that identifies rich features of lung infection from a chest CT image and assesses the severity of COVID-19 based on the extracted features. First, in a chest CT image, the lung contours are corrected for the segmentation of bilateral lungs. Then, the lung contours and areas are obtained from the lung regions. Next, the coarseness, contrast, roughness, and entropy texture features are extracted to confirm the COVID-19 infected regions, and the lesion contours are extracted from the infected regions. Finally, the texture features and V-descriptors are fused as an assessment descriptor for the COVID-19 severity estimation. The new descriptor processes more information than most of the existing methods that only indicate the infection ratio, so the new descriptor is more appropriate to evaluate the severity assessment of COVID-19. The article has been highly praised by the reviewers many times during the peer review process. This work is supported by the Science and Technology Development Fund of Macao under the COVID-19 Anti-epidemic Project “Research on Rapid Detection and Recognition of COVID-19 CT Images” (Grant No. 0038/2020/A). The online publication URL of the article is as follows: https://ieeexplore.ieee.org/document/9346008
IEEE Transactions on Industrial Informatics is an authoritative international journal for automation, control systems, and computer industry applications founded and published by the IEEE Industrial Electronics Society. The impact factor of this journal in 2019 is 9.112 and is ranked 4/109 in COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS.
Figure: Flowchart of the proposed CT image detection technology of COVID-19 (From the article)