EUVIMEDEUVIMED entdecken
Open Access

UViT-Seg: An Efficient ViT and U-Net-Based Framework for Accurate Colorectal Polyp Segmentation in Colonoscopy and WCE Images

Yassine Oukdach, Anass Garbaz, Zakaria Kerkaou, Mohamed El Ansari, Lahcen Koutti, Ahmed Fouad El Ouafdi, Mouna Salihoun

Journal of Imaging Informatics in Medicine · 2024

DOI: 10.1007/s10278-024-01124-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, 2024. Verfasst von Yassine Oukdach und 6 weiteren Autor:innen. Beteiligte Einrichtung: LabSIV, Department of Computer Science, Faculty of Sciences, Ibnou Zohr University, Agadir, 80000, Morocco. yassine.oukdach@edu.uiz.ac.ma. Hauptthemen laut MEDLINE: Colonoscopy, Colonic Polyps, Neural Networks, Computer, Colorectal Neoplasms. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Ministère de l'Education Nationale, de la Formation professionnelle, de l'Enseignement Supérieur et de la Recherche Scientifique, Ministère de l’Education Nationale, de la Formation professionnelle, de l’Enseignement Supérieur et de la Recherche Scientifique.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Colorectal cancer (CRC) stands out as one of the most prevalent global cancers. The accurate localization of colorectal polyps in endoscopy images is pivotal for timely detection and removal, contributing significantly to CRC prevention. The manual analysis of images generated by gastrointestinal screening technologies poses a tedious task for doctors. Therefore, computer vision-assisted cancer detection could serve as an efficient tool for polyp segmentation. Numerous efforts have been dedicated to automating polyp localization, with the majority of studies relying on convolutional neural networks (CNNs) to learn features from polyp images. Despite their success in polyp segmentation tasks, CNNs exhibit significant limitations in precisely determining polyp location and shape due to their sole reliance on learning local features from images. While gastrointestinal images manifest significant variation in their features, encompassing both high- and low-level ones, a framework that combines the ability to learn both features of polyps is desired. This paper introduces UViT-Seg, a framework designed for polyp segmentation in gastrointestinal images. Operating on an encoder-decoder architecture, UViT-Seg employs two distinct feature extraction methods. A vision transformer in the encoder section captures long-range semantic information, while a CNN module, integrating squeeze-excitation and dual attention mechanisms, captures low-level features, focusing on critical image regions. Experimental evaluations conducted on five public datasets, including CVC clinic, ColonDB, Kvasir-SEG, ETIS LaribDB, and Kvasir Capsule-SEG, demonstrate UViT-Seg's effectiveness in polyp localization. To confirm its generalization performance, the model is tested on datasets not used in training. Benchmarking against common segmentation methods and state-of-the-art polyp segmentation approaches, the proposed model yields promising results. For instance, it achieves a mean Dice coefficient of 0.915 and a mean intersection over union of 0.902 on the CVC Colon dataset. Furthermore, UViT-Seg has the advantage of being efficient, requiring fewer computational resources for both training and testing. This feature positions it as an optimal choice for real-world deployment scenarios.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ColonoscopyColonic PolypsNeural Networks, ComputerColorectal NeoplasmsHumansImage Interpretation, Computer-AssistedAlgorithmsImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Attention mechanismCNNColorectal cancerPolyp localizationVision transformer

Autor:innen und Institutionen

  • LabSIV, Department of Computer Science, Faculty of Sciences, Ibnou Zohr University, Agadir, 80000, Morocco. yassine.oukdach@edu.uiz.ac.ma.
  • LabSIV, Department of Computer Science, Faculty of Sciences, Ibnou Zohr University, Agadir, 80000, Morocco.
  • Informatics and Applications Laboratory, Department of Computer Sciences, Faculty of Science, Moulay Ismail University, B.P 11201, Meknès, 52000, Morocco.
  • Faculty of Medicine and Pharmacy of Rabat, Mohammed V University of Rabat, Rabat, 10000, Morocco.

Förderung

  • Ministère de l'Education Nationale, de la Formation professionnelle, de l'Enseignement Supérieur et de la Recherche Scientifique
  • Ministère de l’Education Nationale, de la Formation professionnelle, de l’Enseignement Supérieur et de la Recherche Scientifique

Zitieren

APA

Oukdach, Y., Garbaz, A., Kerkaou, Z., El Ansari, M., Koutti, L., El Ouafdi, A. F., & Salihoun, M. (2024). UViT-Seg: An Efficient ViT and U-Net-Based Framework for Accurate Colorectal Polyp Segmentation in Colonoscopy and WCE Images. Journal of Imaging Informatics in Medicine. https://doi.org/10.1007/s10278-024-01124-8

Vancouver

Oukdach Y, Garbaz A, Kerkaou Z, El Ansari M, Koutti L, El Ouafdi AF, et al. UViT-Seg: An Efficient ViT and U-Net-Based Framework for Accurate Colorectal Polyp Segmentation in Colonoscopy and WCE Images. Journal of Imaging Informatics in Medicine. 2024. doi:10.1007/s10278-024-01124-8

BibTeX
@article{Oukdach2024,
  author = {Oukdach, Yassine and Garbaz, Anass and Kerkaou, Zakaria and El Ansari, Mohamed and Koutti, Lahcen and El Ouafdi, Ahmed Fouad and Salihoun, Mouna},
  title = {UViT-Seg: An Efficient ViT and U-Net-Based Framework for Accurate Colorectal Polyp Segmentation in Colonoscopy and WCE Images},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2024},
  doi = {10.1007/s10278-024-01124-8}
}
Kostenlos starten →