TY - JOUR
T1 - A Self-Configuring Deep Learning Network for Segmentation of Temporal Bone Anatomy in Cone-Beam CT Imaging
AU - Ding, Andy S.
AU - Lu, Alexander
AU - Li, Zhaoshuo
AU - Sahu, Manish
AU - Galaiya, Deepa
AU - Siewerdsen, Jeffrey H.
AU - Unberath, Mathias
AU - Taylor, Russell H.
AU - Creighton, Francis X.
N1 - Publisher Copyright:
© 2023 American Academy of Otolaryngology–Head and Neck Surgery Foundation.
PY - 2023/10
Y1 - 2023/10
N2 - Objective: Preoperative 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 Design: A descriptive study of a segmentation network. Setting: Academic institution. Methods: A 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. Results: Fivefold 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). Conclusion: Using 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.
AB - Objective: Preoperative 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 Design: A descriptive study of a segmentation network. Setting: Academic institution. Methods: A 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. Results: Fivefold 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). Conclusion: Using 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.
KW - automated segmentation
KW - deep learning
KW - neural network
KW - temporal bone
UR - http://www.scopus.com/inward/record.url?scp=85150412682&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85150412682&partnerID=8YFLogxK
U2 - 10.1002/ohn.317
DO - 10.1002/ohn.317
M3 - Article
C2 - 36883992
AN - SCOPUS:85150412682
SN - 0194-5998
VL - 169
SP - 988
EP - 998
JO - Otolaryngology - Head and Neck Surgery (United States)
JF - Otolaryngology - Head and Neck Surgery (United States)
IS - 4
ER -