EUVIMEDEUVIMED entdecken
Crossref

STMNet: Spatial–Temporal Mamba Network for Breast Tumor Segmentation in DCE-MRI

Zelan Li, Meng Wang, Ya Ren, Sha Feng, Heng Zhang, Huan Wang, Yan Ma, Greta S.P. Mok, Jing Qin, Xin Liu, Dong Liang, Hairong Zheng und 3 weitere

Biomedical Signal Processing and Control · 2026-12 · 128 · 111231

DOI: 10.1016/j.bspc.2026.111231 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biomedical Signal Processing and Control, 2026-12. Verfasst von Zelan Li und 14 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben. Gefördert von: Guangdong Basic and Applied Basic Research Foundation, Fundamental Research Funds for the Central Universities, Guangdong Provincial Applied Science and Technology Research and Development Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate segmentation of breast tumors in Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) is critical for early cancer diagnosis and treatment planning. However, prevailing segmentation methods frequently fail to fully leverage the temporal enhancement dynamics inherent in DCE-MRI, which are essential for characterizing tumor pathology. To address this limitation, we propose STMNet, a novel deep learning framework designed for explicit 4D spatio-temporal modeling in breast DCE-MRI. The network incorporates a hierarchical encoder featuring dedicated Spatial Mamba and Temporal Mamba modules, which independently capture intra-phase spatial contexts and inter-phase temporal dependencies across multiple scales. Furthermore, to augment the representation of temporal features, we introduce a Global Temporal Attention Feature Fusion (GTAFF) module that constructs a global query to guide multi-phase integration in a clinically inspired manner. Extensive evaluations on two distinct breast DCE-MRI datasets demonstrate that STMNet consistently surpasses state-of-the-art methods, achieving superior segmentation accuracy and robustness across tumors with diverse morphological characteristics and enhancement kinetics. The code is available at STMNet-DCE-MRI

Förderung

  • Guangdong Basic and Applied Basic Research Foundation
  • Fundamental Research Funds for the Central Universities
  • Guangdong Provincial Applied Science and Technology Research and Development Program
  • Liaoning Provincial Natural Science Foundation
  • National Natural Science Foundation of China

Zitieren

APA

Li, Z., Wang, M., Ren, Y., Feng, S., Zhang, H., Wang, H., Ma, Y., Mok, G. S., Qin, J., Liu, X., Liang, D., Zheng, H., Chi, J., Liu, Z., & Zhang, N. (2026). STMNet: Spatial–Temporal Mamba Network for Breast Tumor Segmentation in DCE-MRI. Biomedical Signal Processing and Control, 128, 111231. https://doi.org/10.1016/j.bspc.2026.111231

Vancouver

Li Z, Wang M, Ren Y, Feng S, Zhang H, Wang H, et al. STMNet: Spatial–Temporal Mamba Network for Breast Tumor Segmentation in DCE-MRI. Biomedical Signal Processing and Control. 2026;128:111231. doi:10.1016/j.bspc.2026.111231

BibTeX
@article{Li2026,
  author = {Li, Zelan and Wang, Meng and Ren, Ya and Feng, Sha and Zhang, Heng and Wang, Huan and Ma, Yan and Mok, Greta S.P. and Qin, Jing and Liu, Xin and Liang, Dong and Zheng, Hairong and Chi, Jianning and Liu, Zhou and Zhang, Na},
  title = {STMNet: Spatial–Temporal Mamba Network for Breast Tumor Segmentation in DCE-MRI},
  journal = {Biomedical Signal Processing and Control},
  year = {2026},
  volume = {128},
  pages = {111231},
  doi = {10.1016/j.bspc.2026.111231}
}
Kostenlos starten →