A Self-Configuring Deep Learning Network for Segmentation of Temporal Bone Anatomy in Cone-Beam CT Imaging

ObjectivePreoperative planning for otologic or neurotologic procedures often requires manual segmentation of relevant structures, which can be tedious and time-consuming. Automated methods for segmenting multiple geometrically complex structures can not only streamline preoperative planning but also augment minimally invasive and/or robot-assisted procedures in this space. This study evaluates a state-of-the-art deep learning pipeline for semantic segmentation of temporal bone anatomy. Study DesignA descriptive study of a segmentation network. SettingAcademic institution. MethodsA total of 15 high-resolution cone-beam temporal bone computed tomography (CT) data sets were included in this study. All images were co-registered, with relevant anatomical structures (eg, ossicles, inner ear, facial nerve, chorda tympani, bony labyrinth) manually segmented. Predicted segmentations from no new U-Net (nnU-Net), an open-source 3-dimensional semantic segmentation neural network, were compared against ground-truth segmentations using modified Hausdorff distances (mHD) and Dice scores. ResultsFivefold cross-validation with nnU-Net between predicted and ground-truth labels were as follows: malleus (mHD: 0.044 +/- 0.024 mm, dice: 0.914 +/- 0.035), incus (mHD: 0.051 +/- 0.027 mm, dice: 0.916 +/- 0.034), stapes (mHD: 0.147 +/- 0.113 mm, dice: 0.560 +/- 0.106), bony labyrinth (mHD: 0.038 +/- 0.031 mm, dice: 0.952 +/- 0.017), and facial nerve (mHD: 0.139 +/- 0.072 mm, dice: 0.862 +/- 0.039). Comparison against atlas-based segmentation propagation showed significantly higher Dice scores for all structures (p < .05). ConclusionUsing an open-source deep learning pipeline, we demonstrate consistently submillimeter accuracy for semantic CT segmentation of temporal bone anatomy compared to hand-segmented labels. This pipeline has the potential to greatly improve preoperative planning workflows for a variety of otologic and neurotologic procedures and augment existing image guidance and robot-assisted systems for the temporal bone.

Automated summary

This study evaluates a state-of-the-art deep learning pipeline for semantic segmentation of temporal bone anatomy. The results show that this method has consistently submillimeter accuracy compared to hand-segmented labels, which can greatly improve preoperative planning workflows.