UADSN: Uncertainty-Aware Dual-Stream Network for Facial Nerve Segmentation

TL;DR

This paper introduces UADSN, a dual-stream neural network that improves facial nerve segmentation in CT scans by leveraging uncertainty estimation, specialized modules, and topology-preserving loss functions.

Contribution

The paper presents a novel dual-stream network with uncertainty-aware supervision, channel squeeze & spatial excitation modules, and a topology-preserving loss for improved nerve segmentation.

Findings

UADSN outperforms existing methods on facial nerve segmentation.

The dual-stream approach effectively identifies uncertain regions.

The proposed modules enhance segmentation accuracy and topology preservation.

Abstract

Facial nerve segmentation is crucial for preoperative path planning in cochlear implantation surgery. Recently, researchers have proposed some segmentation methods, such as atlas-based and deep learning-based methods. However, since the facial nerve is a tubular organ with a diameter of only 1.0-1.5mm, it is challenging to locate and segment the facial nerve in CT scans. In this work, we propose an uncertainty-aware dualstream network (UADSN). UADSN consists of a 2D segmentation stream and a 3D segmentation stream. Predictions from two streams are used to identify uncertain regions, and a consistency loss is employed to supervise the segmentation of these regions. In addition, we introduce channel squeeze & spatial excitation modules into the skip connections of U-shaped networks to extract meaningful spatial information. In order to consider topologypreservation, a clDice loss is introduced into the supervised loss function. Experimental results on the facial nerve dataset demonstrate the effectiveness of UADSN and our submodules.