EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

SepU-Net MRI Segmentation Algorithm Using Depthwise Separable Convolution and Pointwise Convolution Integrated U-Net

Phong Mai Hong, Lam Mai Thanh, Lam Nguyen Ngo

Journal of Technical Education Science · 28.02.2026 · 21 (01) · 35-46

DOI: 10.54644/jte.2026.1890 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Technical Education Science, online erschienen am 28.02.2026. Verfasst von Phong Mai Hong und 2 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate segmentation of brain tumors in MRI remains challenging due to the computational demands of conventional deep learning models. We present SepU-Net, a lightweight convolutional neural network that employs Depthwise Separable Convolutions and efficiently channel attention to reduce model complexity by 69.3% compared to standard U-Net (2.39M vs. 7.76M parameters).Evaluated on both BraTS2020 and BraTS2021, SepU-Net achieves high accuracy (0.9938 and 0.994), mean IoU (0.842 and 0.8318), and Dice coefficients (0.846 and 0.8325), with only minor declines on the more heterogeneous BraTS2021 dataset. Notably, SepU-Net delivers a 32.34% improvement in Tumor Core segmentation and a 10.14% gain in Enhancing Tumor segmentation over U-Net, while maintaining strong precision (0.994/0.9942) and sensitivity (0.9921/0.9915) across datasets. SepU-Net requires only 8.3 GFLOPs per inference, 65% fewer than U-Net and operates efficiently on embedded devices with a memory footprint of 1.4GB. These results validate its ability to balance accuracy and efficiency, enabling real-time segmentation in clinical settings. Future work will integrate attention mechanisms and extend the architecture to 3D for enhanced spatial context.

Zitieren

APA

Hong, P. M., Thanh, L. M., & Ngo, L. N. (2026). SepU-Net MRI Segmentation Algorithm Using Depthwise Separable Convolution and Pointwise Convolution Integrated U-Net. Journal of Technical Education Science, 21(01), 35-46. https://doi.org/10.54644/jte.2026.1890

Vancouver

Hong PM, Thanh LM, Ngo LN. SepU-Net MRI Segmentation Algorithm Using Depthwise Separable Convolution and Pointwise Convolution Integrated U-Net. Journal of Technical Education Science. 2026;21(01):35-46. doi:10.54644/jte.2026.1890

BibTeX
@article{Hong2026,
  author = {Hong, Phong Mai and Thanh, Lam Mai and Ngo, Lam Nguyen},
  title = {SepU-Net MRI Segmentation Algorithm Using Depthwise Separable Convolution and Pointwise Convolution Integrated U-Net},
  journal = {Journal of Technical Education Science},
  year = {2026},
  volume = {21},
  number = {01},
  pages = {35--46},
  doi = {10.54644/jte.2026.1890}
}
Kostenlos starten →