Feedback Chain Network For Hippocampus Segmentation

TL;DR

This paper introduces a hierarchical feedback chain network with attention mechanisms for improved hippocampus segmentation in medical images, achieving state-of-the-art results on multiple datasets.

Contribution

A novel hierarchical feedback chain network with feature aggregation and attention modules for enhanced hippocampus segmentation performance.

Findings

Achieves state-of-the-art accuracy on three datasets.

Effectively captures long-range contextual information.

Improves feature representation through feedback and attention mechanisms.

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 paper, 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 pair-wise 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.