Feedback Chain Network for Hippocampus Segmentation

Heyu HUNG, Runmin CONG*, Lianhe YANG, Ling DU, Cong WANG, Sam KWONG

*Corresponding author for this work

Research output: Journal PublicationsJournal Article (refereed)peer-review

1 Citation (Scopus)

Abstract

The hippocampus plays a vital role in the diagnosis and treatment of many neurological disorders. Recent years, deep learning technology has made great progress in the field of medical image segmentation, and the performance of related tasks has been constantly refreshed. In this article, we focus on the hippocampus segmentation task and propose a novel hierarchical feedback chain network. The feedback chain structure unit learns deeper and wider feature representation of each encoder layer through the hierarchical feature aggregation feedback chains and achieves feature selection and feedback through the feature handover attention module. Then, we embed a global pyramid attention unit between the feature encoder and the decoder to further modify the encoder features, including the pairwise pyramid attention module for achieving adjacent attention interaction and the global context modeling module for capturing the long-range knowledge. The proposed approach achieves state-of-the-art performance on three publicly available datasets compared with existing hippocampus segmentation approaches. The code and results can be found from the link of https://github.com/easymoneysniper183/sematic_seg.

Original languageEnglish
Article number133
Number of pages18
JournalACM Transactions on Multimedia Computing, Communications and Applications
Volume19
Issue number3s
Early online date18 Nov 2022
DOIs
Publication statusPublished - Feb 2023
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 2023 Association for Computing Machinery.

Keywords

  • Deep learning
  • feedback chain
  • hippocampus segmentation
  • multi-level feature fusion

Fingerprint

Dive into the research topics of 'Feedback Chain Network for Hippocampus Segmentation'. Together they form a unique fingerprint.

Cite this