EUVIMEDEUVIMED entdecken
Crossref

SFFR-Transformer: Spatial and Frequency Feature Recalibration Transformer for Incomplete Multimodal Medical Image Segmentation

Jia Lin, Xinlong Liu, Like Li, Kesheng Zhang, Xiaopeng Sha, Ting Feng, Xiang Li

IEEE Sensors Journal · 01.08.2025 · 25 (15) · 29201-29212

DOI: 10.1109/jsen.2025.3582902 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, erschienen am 01.08.2025. Verfasst von Jia Lin und 6 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: Fundamental Research Funds for the Northeastern Universities, Natural Science Foundation of Hebei Province, Central Government Guides Local Funds for Science and Technology Development.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multimodal magnetic resonance imaging (MRI) is vital for the precise segmentation of brain tumors. However, missing or incomplete multimodal data is a frequent challenge in clinical practice, significantly affecting segmentation performance. Current advanced methods primarily focus on fusing multimodal images in the spatial domain, often neglecting the interplay between different modalities in the frequency domain. In this work, we propose a novel framework named SFFR-Transformer, which utilizes a frequency and spatial hybrid multi-head attention Transformer. This approach facilitates the complementary fusion of spatial and frequency domain information, enhancing the reconstruction of missing modalities. Moreover, most existing methods map fused modalities directly to all segmentation targets. Inspired by the correlation between single modalities and specific sub-targets, we introduce a modality-sub-target matching module. This module decouples the fusion modalities from the segmentation targets, enabling more accurate mapping between single modalities and their corresponding sub-targets. Comprehensive experiments on the publicly available BraTS2018 and BraTS2020 datasets demonstrate that our framework surpasses state-of-the-art methods, particularly in scenarios involving missing modalities.

Förderung

  • Fundamental Research Funds for the Northeastern Universities
  • Natural Science Foundation of Hebei Province
  • Central Government Guides Local Funds for Science and Technology Development

Zitieren

APA

Lin, J., Liu, X., Li, L., Zhang, K., Sha, X., Feng, T., & Li, X. (2025). SFFR-Transformer: Spatial and Frequency Feature Recalibration Transformer for Incomplete Multimodal Medical Image Segmentation. IEEE Sensors Journal, 25(15), 29201-29212. https://doi.org/10.1109/jsen.2025.3582902

Vancouver

Lin J, Liu X, Li L, Zhang K, Sha X, Feng T, et al. SFFR-Transformer: Spatial and Frequency Feature Recalibration Transformer for Incomplete Multimodal Medical Image Segmentation. IEEE Sensors Journal. 2025;25(15):29201-29212. doi:10.1109/jsen.2025.3582902

BibTeX
@article{Lin2025,
  author = {Lin, Jia and Liu, Xinlong and Li, Like and Zhang, Kesheng and Sha, Xiaopeng and Feng, Ting and Li, Xiang},
  title = {SFFR-Transformer: Spatial and Frequency Feature Recalibration Transformer for Incomplete Multimodal Medical Image Segmentation},
  journal = {IEEE Sensors Journal},
  year = {2025},
  volume = {25},
  number = {15},
  pages = {29201--29212},
  doi = {10.1109/jsen.2025.3582902}
}
Kostenlos starten →