Patchwise U-Net Based Semantic Segmentation of COVID-19 Infection from Chest CT Images
International Journal of Computational and Experimental Science and Engineering · 30.12.2025 · 11 (4)
DOI: 10.22399/ijcesen.5129 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Computational and Experimental Science and Engineering, online erschienen am 30.12.2025. Verfasst von Ms. Shital A. Dhumane und 1 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Modern healthcare relies heavily on medical image analysis. The task of analyzing and diagnosing based solely on images is challenging, which has led to the implementation of computer-aided diagnosis techniques. RT‒PCR, a screening tool, has lower sensitivity in the diagnosis of COVID-19, and medical imaging methods such as computed tomography (CT) offer significant benefits over other methods. Segmentation is the most challenging issue when working on medical images, as the deep learning approach has recently become commonly used in diagnosis. A convolutional neural network (CNN) framework called U-Net was created for image processing's semantic pixel segmentation. This paper focuses on assisting radiologists in providing a more detailed depiction of COVID-19 infection on CT images, including various infection categories and lung conditions. In this study, we conducted an experiment on preprocessing for better segmentation results via the U-Net model. Patchwise segmentation yields better results than linear and cubic interpolation does.
Zitieren
APA
Dhumane, M. S. A., & Gaikwad, M. C. (2025). Patchwise U-Net Based Semantic Segmentation of COVID-19 Infection from Chest CT Images. International Journal of Computational and Experimental Science and Engineering, 11(4). https://doi.org/10.22399/ijcesen.5129
Vancouver
Dhumane MSA, Gaikwad MC. Patchwise U-Net Based Semantic Segmentation of COVID-19 Infection from Chest CT Images. International Journal of Computational and Experimental Science and Engineering. 2025;11(4). doi:10.22399/ijcesen.5129
BibTeX
@article{Dhumane2025,
author = {Dhumane, Ms. Shital A. and Gaikwad, Mr. Chandrakant},
title = {Patchwise U-Net Based Semantic Segmentation of COVID-19 Infection from Chest CT Images},
journal = {International Journal of Computational and Experimental Science and Engineering},
year = {2025},
volume = {11},
number = {4},
doi = {10.22399/ijcesen.5129}
}
EUVIMED