EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

SAM2-FNet: A Frequency-Domain Mul-ti-Expert Fusion Network for Medical Image Segmentation

Zihua Zhang, Shaoli Li, Bing Ge, Peng Lu

计算机科学辑要 · 2026

DOI: 10.63313/cs.8023 ↗

At a glance

Journal article in 计算机科学辑要, 2026. Written by Zihua Zhang and 3 co-authors. 24 references. The full text is freely available (open access, CC BY 4.0).

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

In recent years, deep learning has achieved substantial progress in medical image segmentation; however, existing methods remain constrained by the challenge of effectively coupling local detail with global semantic context. To address this issue, we propose SAM2-FNet, a frequency-domain expert-fusion network built upon an improved SAM2-UNet. SAM2-FNet attains fine-grained, multi-scale feature enhancement through frequency-domain decoupling and a multi-expert collaborative mechanism, leading to marked improvements in segmentation accuracy.Specifically, SAM2-FNet provides three primary capabilities:(1) Frequency-domain decoupling and enhancement— input features are decomposed into high-frequency and low-frequency components via a two-dimensional Fourier transform; the resulting components are processed by a dual-branch heterogeneous pipeline and adaptively fused using channel-wise attention to preserve both texture details and global structure.(2) Dynamic expert decision-making — an improved Expert Fusion Module (FEM) implements a multi-expert architecture composed of five sub-networks (SubNets), enabling dynamic, data-driven expert weighting and enhancing the model’s generalization to lesion heterogeneity.(3) Decoder optimization — a Local Refinement Module (LRM) is introduced in the decoder: an atrous (dilated) convolutional pyramid combined with a spatial-attention mechanism narrows the encoder–decoder semantic gap and improves boundary reconstruction fidelity.Experiments on the Kvasir-SEG dataset demonstrate that SAM2-FNet yields a 3.0% absolute increase in Dice coefficient and a 4.1% absolute increase in IoU relative to the baseline SAM2-UNet. Moreover, compared with benchmark models such as umambabot and SwinUNETR, SAM2-FNet exhibits superior robustness under high-noise and low-contrast imaging conditions

Cite

APA

Zhang, Z., Li, S., Ge, B., & Lu, P. (2026). SAM2-FNet: A Frequency-Domain Mul-ti-Expert Fusion Network for Medical Image Segmentation. 计算机科学辑要. https://doi.org/10.63313/cs.8023

Vancouver

Zhang Z, Li S, Ge B, Lu P. SAM2-FNet: A Frequency-Domain Mul-ti-Expert Fusion Network for Medical Image Segmentation. 计算机科学辑要. 2026. doi:10.63313/cs.8023

BibTeX
@article{Zhang2026,
  author = {Zhang, Zihua and Li, Shaoli and Ge, Bing and Lu, Peng},
  title = {SAM2-FNet: A Frequency-Domain Mul-ti-Expert Fusion Network for Medical Image Segmentation},
  journal = {计算机科学辑要},
  year = {2026},
  doi = {10.63313/cs.8023}
}
Start for free →