EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Liver Tumor Segmentation via State Space Modeling and Multi-Scale Detail Enhancement

Yuhang Feng

Academic Journal of Applied Sciences · 25.03.2026 · 1 (1) · 44-52

DOI: 10.54097/qd9dgg96 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Journal of Applied Sciences, online erschienen am 25.03.2026. Verfasst von Yuhang Feng. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate liver tumor segmentation from CT images is challenging because tumors present blurred boundaries, irregular shapes, and substantial scale variation. To address these issues, we propose a liver tumor segmentation network that combines state-space modeling with multi-scale detail enhancement (SSMDENet). SSMDENet follows an encoder-decoder architecture and introduces a Global-Local Modeling (GLM) block as the basic feature extractor. Within GLM, the Spatial Dependency Modeling (SMD) module captures long-range spatial dependencies to encode global anatomical context, while the Multi-scale Feature Enhancement (MFE) module uses parallel depthwise convolutions and channel recalibration to strengthen local boundary and texture information. In this way, the proposed network jointly models global semantics and local details. Experiments on the LiTS2017 and 3DIRCADB-01 datasets demonstrate the effectiveness of the method. SSMDENet achieves Dice scores of 85.79% and 84.12% on LiTS2017 and 3DIRCADB-01, respectively, outperforming several representative segmentation methods. Ablation studies further confirm the complementary benefits of the SMD and MFE modules. These results indicate that SSMDENet is an effective and robust solution for liver tumor segmentation.

Zitieren

APA

Feng, Y. (2026). Liver Tumor Segmentation via State Space Modeling and Multi-Scale Detail Enhancement. Academic Journal of Applied Sciences, 1(1), 44-52. https://doi.org/10.54097/qd9dgg96

Vancouver

Feng Y. Liver Tumor Segmentation via State Space Modeling and Multi-Scale Detail Enhancement. Academic Journal of Applied Sciences. 2026;1(1):44-52. doi:10.54097/qd9dgg96

BibTeX
@article{Feng2026,
  author = {Feng, Yuhang},
  title = {Liver Tumor Segmentation via State Space Modeling and Multi-Scale Detail Enhancement},
  journal = {Academic Journal of Applied Sciences},
  year = {2026},
  volume = {1},
  number = {1},
  pages = {44--52},
  doi = {10.54097/qd9dgg96}
}
Kostenlos starten →