EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DIG-MambaNet: A Dual-Path Interactive Guided Mamba Network for Medical Image Segmentation

Yongkang Zhu, Tianyue Yu, Hongmei Li, Xin Shu iD

Journal of Imaging · 28.07.2026 · 12 (8) · 343

DOI: 10.3390/jimaging12080343 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 28.07.2026. Verfasst von Yongkang Zhu und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212100, China. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable medical image segmentation remains challenging because models must preserve fine boundary details while maintaining global semantic consistency. CNNs capture local structures effectively but have limited long-range modeling ability, whereas Transformer-based methods improve global context at high computational cost. Mamba-based state space models offer efficient long-range modeling, but may weaken high-frequency textures and boundary cues. To address these limitations, we propose DIG-MambaNet, a Dual-path Interactive Guided Mamba Network for medical image segmentation. The network introduces a dual-path complementary modeling block (DCM Block), where a cross-feature spatial interaction module (CSIM) adaptively integrates CNN-based local features and Mamba-based global features. A source image-guided module (SIGM) injects high-frequency information from the original image to compensate for downsampling-induced detail loss, while an inter-layer detail refinement fusion module (IDRFM) improves encoder–decoder feature alignment during reconstruction. Experiments on 2018DSB, ISIC2018, JSUAH-Cerebellum, and CVC-ClinicDB, covering nuclei segmentation in microscopy images, skin lesion segmentation in dermoscopic images, fetal cerebellum segmentation in ultrasound images, and polyp segmentation in colonoscopy images, demonstrate that DIG-MambaNet achieves consistent and competitive performance across diverse target structures and imaging conditions, with improved boundary delineation and favorable overlap-based accuracy compared with representative CNN-, Transformer-, and Mamba-based methods.

Schlagwörter

Stichwörter der Autor:innen

Mambadual-path complementary modeling blockinter-layer detail refinement fusion modulemedical image segmentationsource image-guided module

Autor:innen und Institutionen

  • School of Computer Science, Jiangsu University of Science and Technology, Zhenjiang 212100, China.

ORCID-Profile: Xin Shu

Zitieren

APA

Zhu, Y., Yu, T., Li, H., & Shu, X. (2026). DIG-MambaNet: A Dual-Path Interactive Guided Mamba Network for Medical Image Segmentation. Journal of Imaging, 12(8), 343. https://doi.org/10.3390/jimaging12080343

Vancouver

Zhu Y, Yu T, Li H, Shu X. DIG-MambaNet: A Dual-Path Interactive Guided Mamba Network for Medical Image Segmentation. Journal of Imaging. 2026;12(8):343. doi:10.3390/jimaging12080343

BibTeX
@article{Zhu2026,
  author = {Zhu, Yongkang and Yu, Tianyue and Li, Hongmei and Shu, Xin},
  title = {DIG-MambaNet: A Dual-Path Interactive Guided Mamba Network for Medical Image Segmentation},
  journal = {Journal of Imaging},
  year = {2026},
  volume = {12},
  number = {8},
  pages = {343},
  doi = {10.3390/jimaging12080343}
}
Kostenlos starten →