EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MWG-UNet++: Hybrid Transformer U-Net Model for Brain Tumor Segmentation in MRI Scans

Yu Lyu iD, Xiaolin Tian

Bioengineering · 31.01.2025 · 12 (2) · 140

DOI: 10.3390/bioengineering12020140 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioengineering, online erschienen am 31.01.2025. Verfasst von Yu Lyu und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Faculty of Information Technology, Macau University of Science and Technology, Macao 999078, China. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: study on the segmentation method and key technology of Heart x-ray image and CT image.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The accurate segmentation of brain tumors from medical images is critical for diagnosis and treatment planning. However, traditional segmentation methods struggle with complex tumor shapes and inconsistent image quality which leads to suboptimal results. To address this challenge, we propose multiple tasking Wasserstein Generative Adversarial Network U-shape Network++ (MWG-UNet++) to brain tumor segmentation by integrating a U-Net architecture enhanced with transformer layers which combined with Wasserstein Generative Adversarial Networks (WGAN) for data augmentation. The proposed model called Residual Attention U-shaped Network (RAUNet) for brain tumor segmentation leverages the robust feature extraction capabilities of U-Net and the global context awareness provided by transformers to improve segmentation accuracy. Incorporating WGAN for data augmentation addresses the challenge of limited medical imaging datasets to generate high-quality synthetic images that enhance model training and generalization. Our comprehensive evaluation demonstrates that this hybrid model significantly improves segmentation performance. The RAUNet outperforms compared approaches by capturing long-range dependencies and considering spatial variations. The use of WGANs augments the dataset for resulting in robust training and improved resilience to overfitting. The average evaluation metric for brain tumor segmentation is 0.8965 which outperformed the compared methods.

Schlagwörter

Stichwörter der Autor:innen

MRIU-NetWGANattention mechanismbrain tumor segmentation

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Faculty of Information Technology, Macau University of Science and Technology, Macao 999078, China.

ORCID-Profile: Yu Lyu

Förderung

  • study on the segmentation method and key technology of Heart x-ray image and CT image

Zitieren

APA

Lyu, Y., & Tian, X. (2025). MWG-UNet++: Hybrid Transformer U-Net Model for Brain Tumor Segmentation in MRI Scans. Bioengineering, 12(2), 140. https://doi.org/10.3390/bioengineering12020140

Vancouver

Lyu Y, Tian X. MWG-UNet++: Hybrid Transformer U-Net Model for Brain Tumor Segmentation in MRI Scans. Bioengineering. 2025;12(2):140. doi:10.3390/bioengineering12020140

BibTeX
@article{Lyu2025,
  author = {Lyu, Yu and Tian, Xiaolin},
  title = {MWG-UNet++: Hybrid Transformer U-Net Model for Brain Tumor Segmentation in MRI Scans},
  journal = {Bioengineering},
  year = {2025},
  volume = {12},
  number = {2},
  pages = {140},
  doi = {10.3390/bioengineering12020140}
}
Kostenlos starten →