Semantic Feature Attention Network for Liver Tumor Segmentation in Large-scale CT database

TL;DR

This paper introduces a Semantic Feature Attention Network (SFAN) that leverages both low-level and high-level features with novel attention modules to improve liver tumor segmentation accuracy in large-scale CT datasets.

Contribution

The paper proposes a new SFAN architecture with SAT and GCA modules for enhanced feature fusion and localization in liver tumor segmentation tasks.

Findings

Achieves state-of-the-art Dice scores on LiTS database

Outperforms existing algorithms on large-scale clinical data

Demonstrates effectiveness of attention modules in medical image segmentation

Abstract

Liver tumor segmentation plays an important role in hepatocellular carcinoma diagnosis and surgical planning. In this paper, we propose a novel Semantic Feature Attention Network (SFAN) for liver tumor segmentation from Computed Tomography (CT) volumes, which exploits the impact of both low-level and high-level features. In the SFAN, a Semantic Attention Transmission (SAT) module is designed to select discriminative low-level localization details with the guidance of neighboring high-level semantic information. Furthermore, a Global Context Attention (GCA) module is proposed to effectively fuse the multi-level features with the guidance of global context. Our experiments are based on 2 challenging databases, the public Liver Tumor Segmentation (LiTS) Challenge database and a large-scale in-house clinical database with 912 CT volumes. Experimental results show that our proposed framework can not only achieve the state-of-the-art performance with the Dice per case on liver tumor segmentation in LiTS database, but also outperform some widely used segmentation algorithms in the large-scale clinical database.