EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSGU-Net: a lightweight multi-scale ghost U-Net for image segmentation

Hua Cheng, Yang Zhang, Huangxin Xu, Dingliang Li, Zejian Zhong, Yinchuan Zhao, Zhuo Yan

Frontiers in Neurorobotics · 06.01.2025 · 18

DOI: 10.3389/fnbot.2024.1480055 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Neurorobotics, online erschienen am 06.01.2025. Verfasst von Hua Cheng und 6 weiteren Autor:innen. Beteiligte Einrichtung: Chengdu Civil Aviation Information Technology Co., Ltd, Chengdu, China. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

U-Net and its variants have been widely used in the field of image segmentation. In this paper, a lightweight multi-scale Ghost U-Net (MSGU-Net) network architecture is proposed. This can efficiently and quickly process image segmentation tasks while generating high-quality object masks for each object. The pyramid structure (SPP-Inception) module and ghost module are seamlessly integrated in a lightweight manner. Equipped with an efficient local attention (ELA) mechanism and an attention gate mechanism, they are designed to accurately identify the region of interest (ROI). The SPP-Inception module and ghost module work in tandem to effectively merge multi-scale information derived from low-level features, high-level features, and decoder masks at each stage. Comparative experiments were conducted between the proposed MSGU-Net and state-of-the-art networks on the ISIC2017 and ISIC2018 datasets. In short, compared to the baseline U-Net, our model achieves superior segmentation performance while reducing parameter and computation costs by 96.08 and 92.59%, respectively. Moreover, MSGU-Net can serve as a lightweight deep neural network suitable for deployment across a range of intelligent devices and mobile platforms, offering considerable potential for widespread adoption.

Schlagwörter

Stichwörter der Autor:innen

SPP-InceptionU-Netimage segmentationlightweight neural networkmulti-scale

Autor:innen und Institutionen

  • Chengdu Civil Aviation Information Technology Co., Ltd, Chengdu, China.
  • The College of Artificial Intelligence, Shenyang Aerospace University, Shenyang, China.
  • Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.

Zitieren

APA

Cheng, H., Zhang, Y., Xu, H., Li, D., Zhong, Z., Zhao, Y., & Yan, Z. (2025). MSGU-Net: a lightweight multi-scale ghost U-Net for image segmentation. Frontiers in Neurorobotics, 18. https://doi.org/10.3389/fnbot.2024.1480055

Vancouver

Cheng H, Zhang Y, Xu H, Li D, Zhong Z, Zhao Y, et al. MSGU-Net: a lightweight multi-scale ghost U-Net for image segmentation. Frontiers in Neurorobotics. 2025;18. doi:10.3389/fnbot.2024.1480055

BibTeX
@article{Cheng2025,
  author = {Cheng, Hua and Zhang, Yang and Xu, Huangxin and Li, Dingliang and Zhong, Zejian and Zhao, Yinchuan and Yan, Zhuo},
  title = {MSGU-Net: a lightweight multi-scale ghost U-Net for image segmentation},
  journal = {Frontiers in Neurorobotics},
  year = {2025},
  volume = {18},
  doi = {10.3389/fnbot.2024.1480055}
}
Kostenlos starten →