Automated Extraction of Anatomical Measurements From Temporal Bone CT Imaging

Abstract

Objective Proposed methods of minimally invasive and robot-assisted procedures within the temporal bone require measurements of surgically relevant distances and angles, which often require time-consuming manual segmentation of preoperative imaging. This study aims to describe an automatic segmentation and measurement extraction pipeline of temporal bone cone-beam computed tomography (CT) scans. Study Design Descriptive study of temporal bone measurements. Setting Academic institution. Methods A propagation template composed of 16 temporal bone CT scans was formed with relevant anatomical structures and landmarks manually segmented. Next, 52 temporal bone CT scans were autonomously segmented using deformable registration techniques from the Advanced Normalization Tools Python package. Anatomical measurements were extracted via in-house Python algorithms. Extracted measurements were compared to ground truth values from manual segmentations. Results Paired t test analyses showed no statistical difference between measurements using this pipeline and ground truth measurements from manually segmented images. Mean (SD) malleus manubrium length was 4.39 (0.34) mm. Mean (SD) incus short and long processes were 2.91 (0.18) mm and 3.53 (0.38) mm, respectively. The mean (SD) maximal diameter of the incus long process was 0.74 (0.17) mm. The first and second facial nerve genus had mean (SD) angles of 68.6 (6.7) degrees and 111.1 (5.3) degrees, respectively. The facial recess had a mean (SD) span of 3.21 (0.46) mm. Mean (SD) minimum distance between the external auditory canal and tegmen was 3.79 (1.05) mm. Conclusions This is the first study to automatically extract relevant temporal bone anatomical measurements from CT scans using segmentation propagation. Measurements from these models can streamline preoperative planning, improve future segmentation techniques, and help develop future image-guided or robot-assisted systems for temporal bone procedures.

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

“…Atlas-based segmentation methods, in which a presegmented reference volume is co-registered to a patient CT, have been the traditional technique for automatically segmenting patient anatomy. While our group has previously validated this technique for temporal bone anatomy, [10][11][12][13] a few key shortcomings preclude its clinical use. First, anatomy-altering pathologies, such as Mondini dysplasia, cholesteatoma, and vestibular schwannoma, are difficult to label with atlas-based methods due to the differences in shape and structure of target anatomy and their counterparts in the labeled atlas.…”

ANTsX neuroimaging-derived structural phenotypes of UK Biobank

“… 19 ANTsX-based IDPs have demonstrated utility in several studies spanning a variety of organ systems, species, and imaging modalities. 20 – 22 These IDPs include those which have been previously reported, such as global brain tissue volumes 23 and more localized, FreeSurfer-analogous cortical thickness values 16 , 24 , 25 averaged over the Desikan-Killiany-Tourville (DKT) regions. 26 In addition, recently developed ANTsX functionality includes a medial temporal lobe (MTL) parcellation framework known as “DeepFLASH,” a neural network for segmenting hippocampal subfields and extra-hippocampal regions which extends previous work.…”

ANTsX neuroimaging-derived structural phenotypes of UK Biobank

“…Analogously, the Advanced Normalization Tools Ecosystem (ANTsX) is a collection of interrelated, open-source software libraries for biological and medical image processing and analysis [Tustison et al, 2021b] with developmental roots in high-performing medical image registration [Avants et al, 2011a; Avants et al, 2014] and built on the Insight Toolkit (ITK) [Yoo and Metaxas, 2005]. ANTsX-based IDPs have demonstrated utility in several studies spanning a variety of organ systems, species, and imaging modalities (e.g., [Diamond et al, 2022; Ding et al, 2022; Kini et al, 2021]). These IDPs include those which have been previously reported, such as global brain tissue volumes [Avants et al, 2011b] and more localized, FreeSurfer-analogous cortical thickness values [Tustison et al, 2014; Tustison et al, 2019; Tustison et al, 2021b] averaged over the Desikan-Killiany-Tourville (DKT) regions [Klein and Tourville, 2012].…”

“…19 ANTsX-based IDPs have demonstrated utility in several studies spanning a variety of organ systems, species, and imaging modalities (e.g.,). [20][21][22] These IDPs include those which have been previously reported, such as global brain tissue volumes 23 and more localized, FreeSurfer-analogous cortical thickness values 16,24,25 averaged over the Desikan-Killiany-Tourville (DKT) regions. 26 In addition, recently developed ANTsX functionality includes a medial temporal lobe (MTL) parcellation framework known as "DeepFLASH," a neural network for segmenting hippocampal subfields and extrahippocampal regions which extends previous work.…”