Automatic multi-label temporal bone computed tomography segmentation with deep learning.

Abstract

Manually segmenting temporal bone computed tomography (CT) images is difficult. Despite accurate automatic segmentation in previous studies using deep learning, they did not consider clinical differences, such as variations in CT scanners. Such differences can significantly affect the accuracy of segmentation. Our dataset included 147 scans from three different scanners, and we used Res U-Net, SegResNet, and UNETR neural networks to segment four structures: the ossicular chain (OC), internal auditory canal (IAC), facial nerve (FN), and labyrinth (LA). The experimental results yielded high mean Dice similarity coefficients of 0.8121, 0.8809, 0.6858, 0.9329, and a low mean of 95% Hausdorff distances of 0.1431mm, 0.1518mm, 0.2550mm, and 0.0640mm for OC, IAC, FN, and LA, respectively. This study shows that automated deep learning-based segmentation techniques successfully segment temporal bone structures using CT data from different scanners. Our research can further promote its clinical application.