EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FED-UNet++: An Improved Nested UNet for Hippocampus Segmentation in Alzheimer’s Disease Diagnosis

Liping Yang, Wei Zhang iD, Shengyu Wang, Xiaoru Yu iD, Bin Jing iD, Nairui Sun, Tengchao Sun, Wei Wang

Sensors · 19.08.2025 · 25 (16) · 5155

DOI: 10.3390/s25165155 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 19.08.2025. Verfasst von Liping Yang und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science and Technology, Changchun University, No. 6543, Satellite Road, Changchun 130022, China. Hauptthemen laut MEDLINE: Alzheimer Disease, Hippocampus, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Education of Jilin Province, Department of Science and Technology of Jilin Province, Changchun Yaxin Technology Co., Ltd..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The hippocampus is a key structure involved in the early pathological progression of Alzheimer’s disease. Accurate segmentation of this region is vital for the quantitative assessment of brain atrophy and the support of diagnostic decision-making. To address limitations in current MRI-based hippocampus segmentation methods—such as indistinct boundaries, small target size, and limited feature representation—this study proposes an enhanced segmentation framework called FED-UNet++. The residual feature reconstruction block (FRBlock) is introduced to strengthen the network’s ability to capture boundary cues and fine-grained structural details in shallow layers. The efficient attention pyramid (EAP) module enhances the integration of multi-scale features and spatial contextual information. The dynamic frequency context network (DFCN) mitigates the decoder’s limitations in capturing long-range dependencies and global semantic structures. Experimental results on the benchmark dataset demonstrate that FED-UNet++ achieves superior performance across multiple evaluation metrics, with an IoU of 74.95% and a Dice coefficient of 84.43% ± 0.21%, outperforming the baseline model in both accuracy and robustness. These findings confirm that FED-UNet++ is highly effective in segmenting small and intricate brain structures like the hippocampus, providing a robust and practical tool for MRI-based analysis of neurodegenerative diseases.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Alzheimer DiseaseHippocampusImage Processing, Computer-AssistedHumansMagnetic Resonance ImagingAlgorithms

Stichwörter der Autor:innen

Alzheimer’s diseaseDynamic Frequency Context NetworkEfficient Attention PyramidFED-UNet++Residual Feature Reconstruction Blockhippocampus segmentation

Autor:innen und Institutionen

  • College of Computer Science and Technology, Changchun University, No. 6543, Satellite Road, Changchun 130022, China.

ORCID-Profile: Wei Zhang, Xiaoru Yu, Bin Jing

Förderung

  • Department of Education of Jilin Province
  • Department of Science and Technology of Jilin Province
  • Changchun Yaxin Technology Co., Ltd.

Zitieren

APA

Yang, L., Zhang, W., Wang, S., Yu, X., Jing, B., Sun, N., Sun, T., & Wang, W. (2025). FED-UNet++: An Improved Nested UNet for Hippocampus Segmentation in Alzheimer’s Disease Diagnosis. Sensors, 25(16), 5155. https://doi.org/10.3390/s25165155

Vancouver

Yang L, Zhang W, Wang S, Yu X, Jing B, Sun N, et al. FED-UNet++: An Improved Nested UNet for Hippocampus Segmentation in Alzheimer’s Disease Diagnosis. Sensors. 2025;25(16):5155. doi:10.3390/s25165155

BibTeX
@article{Yang2025,
  author = {Yang, Liping and Zhang, Wei and Wang, Shengyu and Yu, Xiaoru and Jing, Bin and Sun, Nairui and Sun, Tengchao and Wang, Wei},
  title = {FED-UNet++: An Improved Nested UNet for Hippocampus Segmentation in Alzheimer’s Disease Diagnosis},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {16},
  pages = {5155},
  doi = {10.3390/s25165155}
}
Kostenlos starten →