EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LM-UNet: Lightweight Mamba-UNet Prostate MRI image segmentation network

Kuncai Xu iD, Shuai Zhou, Yan Chen, Junhao Chen, Ning Zhang, Yilong Liao

PLOS One · 23.03.2026 · 21 (3) · e0339719

DOI: 10.1371/journal.pone.0339719 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 23.03.2026. Verfasst von Kuncai Xu und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Intelligent Engineering, Guiyang Institute of Information Science and Technology, Guiyang, Guizhou, PR China. Hauptthemen laut MEDLINE: Magnetic Resonance Imaging, Prostate, Prostatic Neoplasms, Image Processing, Computer-Assisted. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guizhou Provincial Natural Science Research Project, Guizhou Provincial Education Science Planning Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate segmentation of lesions in prostate magnetic resonance images (MRI) is important for assessing patient health and personalized treatment in the clinic. However, the traditional UNet segmentation network has low segmentation accuracy because of the fuzzy boundary and low contrast. Therefore, we propose a Lightweight Mamba-UNet (LM-UNet) prostate MRI image segmentation method. Initially, the encoder-decoder backbone structure consists of parallel vision mamba (PV-Mamba) and efficient multi-scale attention (EMA). The number of model parameters is reduced by constructing PV-Mamba while extracting the correlation between features over long distances. The EMA is then used to learn different spatial features in groups and construct cross-spatial information aggregation methods for richer feature aggregation. Subsequently, we construct the edge feature extraction (EFE) and the edge feature fusion (EFF) to achieve different levels of feature fusion in the encoder. Ultimately, we suggest a multi-stage and multi-level skip connections (MMSC) to achieve multi-level fusion between the encoder and decoder, there reducing semantic discrepancies between contextual features and improving segmentation accuracy. Experimental results demonstrate that on the PROMISE12 dataset, LM-UNet outperforms seven comparative segmentation methods in terms of parameter count, computational memory requirements, and precise segmentation of lesion margins.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Magnetic Resonance ImagingProstateProstatic NeoplasmsImage Processing, Computer-AssistedHumansMaleAlgorithms

Autor:innen und Institutionen

  • College of Intelligent Engineering, Guiyang Institute of Information Science and Technology, Guiyang, Guizhou, PR China.
  • Department of Radiology, Jiangmen Central Hospital, Jiangmen, Guangdong, PR China.

ORCID-Profile: Kuncai Xu

Förderung

  • Guizhou Provincial Natural Science Research Project
  • Guizhou Provincial Education Science Planning Project

Zitieren

APA

Xu, K., Zhou, S., Chen, Y., Chen, J., Zhang, N., & Liao, Y. (2026). LM-UNet: Lightweight Mamba-UNet Prostate MRI image segmentation network. PLOS One, 21(3), e0339719. https://doi.org/10.1371/journal.pone.0339719

Vancouver

Xu K, Zhou S, Chen Y, Chen J, Zhang N, Liao Y. LM-UNet: Lightweight Mamba-UNet Prostate MRI image segmentation network. PLOS One. 2026;21(3):e0339719. doi:10.1371/journal.pone.0339719

BibTeX
@article{Xu2026,
  author = {Xu, Kuncai and Zhou, Shuai and Chen, Yan and Chen, Junhao and Zhang, Ning and Liao, Yilong},
  title = {LM-UNet: Lightweight Mamba-UNet Prostate MRI image segmentation network},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {3},
  pages = {e0339719},
  doi = {10.1371/journal.pone.0339719}
}
Kostenlos starten →