Globally Guided Progressive Fusion Network for 3D Pancreas Segmentation

TL;DR

This paper introduces a novel 3D pancreas segmentation network that effectively combines global features and local 3D geometric information, achieving state-of-the-art results in medical image analysis.

Contribution

The proposed Globally Guided Progressive Fusion Network innovatively integrates global features with local 3D information for improved pancreas segmentation.

Findings

Achieves state-of-the-art performance on two datasets

Effectively combines global and local 3D features

Demonstrates efficiency with moderate slice usage

Abstract

Recently 3D volumetric organ segmentation attracts much research interest in medical image analysis due to its significance in computer aided diagnosis. This paper aims to address the pancreas segmentation task in 3D computed tomography volumes. We propose a novel end-to-end network, Globally Guided Progressive Fusion Network, as an effective and efficient solution to volumetric segmentation, which involves both global features and complicated 3D geometric information. A progressive fusion network is devised to extract 3D information from a moderate number of neighboring slices and predict a probability map for the segmentation of each slice. An independent branch for excavating global features from downsampled slices is further integrated into the network. Extensive experimental results demonstrate that our method achieves state-of-the-art performance on two pancreas datasets.