Deep Learning Method for Rapid Simultaneous Multistructure Temporal Bone Segmentation.

OBJECTIVE: To develop and validate a deep learning algorithm for the automated segmentation of key temporal bone structures from clinical computed tomography (CT) data sets. STUDY DESIGN: Cross-sectional study. SETTING: A total of 325 CT scans from a clinical database. METHOD: A state-of-the-art deep learning (DL) algorithm (SwinUNETR) was used to train a prediction model for rapid segmentation of 9 key temporal bone structures in a data set of 325 clinical CTs. The data set was manually annotated by a specialist to serve as the ground truth. The data set was randomly split into training (n = 260) and testing (n = 65) sets. The model's performance was objectively assessed through external validation on the test set using metrics including Dice, Balanced accuracy, Hausdorff distances, and processing time. RESULTS: The model achieved an average Dice coefficient of 0.87 for all structures, an average balanced accuracy of 0.94, an average Hausdorff distance of 0.79 mm, and an average processing time of 9.1 seconds per CT. CONCLUSION: The present DL model for the automated simultaneous segmentation of multiple structures within the temporal bone from CTs achieved high accuracy according to currently commonly employed objective analysis. The results demonstrate the potential of the method to improve preoperative evaluation and intraoperative guidance in otologic surgery.

Estimation of Cochlear Implant Insertion Depth Using 2D-3D Registration of Postoperative X-Ray and Preoperative CT Images.

OBJECTIVE: To improve estimation of cochlear implant (CI) insertion depth in postoperative skull x-rays using synthesized information from preoperative CT scans. STUDY DESIGN: Retrospective cohort. SETTING: Tertiary referral center. PATIENTS: Ten adult cochlear implant recipients with preoperative and postoperative temporal bone computed tomography (CT)scans and postoperative skull x-ray imaging. INTERVENTIONS: Postoperative x-rays and digitally reconstructed radiographs (DRR) from preoperative CTs were registered using 3D Slicer and MATLAB to enhance localization of the round window and modiolus. Angular insertion depth (AID) was estimated in unmodified and registration-enhanced x-rays and DRRs in the cochlear view. Linear insertion depth (LID) was estimated in registered images by two methods that localized the proximal CI electrode or segmented the cochlea. Ground truth assessments were made in postoperative CTs. MAIN OUTCOME MEASURES: Errors of insertion depth estimates were calculated relative to ground truth measurements and compared with paired t t ests. Pearson correlation coefficient was used to assess inter-rater reliability of two reviewer's measurements of AID in unmodified x-rays. RESULTS: In postoperative x-rays, AID estimation errors were similar with and without registration enhancement (-1.3 ± 20.7° and -4.8 ± 24.9°, respectively; mean ± SD; p = 0.6). AID estimation in unmodified x-rays demonstrated strong interrater agreement (ρ = 0.79, p < 0.05) and interrater differences (-15.0 ± 35.3°) comparable to estimate errors. Registering images allowed measurement of AID in the cochlear view with estimation errors of 14.6 ± 30.6° and measurement of LID, with estimate errors that were similar between proximal electrode localization and cochlear segmentation methods (-0.9 ± 2.2 mm and -2.1 ± 2.7 mm, respectively; p = 0.3). CONCLUSIONS: 2D-3D image registration allows measurement of AID in the cochlear view and LID using postoperative x-rays and preoperative CT imaging. The use of this technique may reduce the need for postimplantation CT studies to assess these metrics of CI electrode position. Further work is needed to improve the accuracy of AID assessment in the postoperative x-ray view with registered images compared with established methods.

Automated Radiomic Analysis of Vestibular Schwannomas and Inner Ears Using Contrast-Enhanced T1-Weighted and T2-Weighted Magnetic Resonance Imaging Sequences and Artificial Intelligence.

OBJECTIVE: To objectively evaluate vestibular schwannomas (VSs) and their spatial relationships with the ipsilateral inner ear (IE) in magnetic resonance imaging (MRI) using deep learning. STUDY DESIGN: Cross-sectional study. PATIENTS: A total of 490 adults with VS, high-resolution MRI scans, and no previous neurotologic surgery. INTERVENTIONS: MRI studies of VS patients were split into training (390 patients) and test (100 patients) sets. A three-dimensional convolutional neural network model was trained to segment VS and IE structures using contrast-enhanced T1-weighted and T2-weighted sequences, respectively. Manual segmentations were used as ground truths. Model performance was evaluated on the test set and on an external set of 100 VS patients from a public data set (Vestibular-Schwannoma-SEG). MAIN OUTCOME MEASURES: Dice score, relative volume error, average symmetric surface distance, 95th-percentile Hausdorff distance, and centroid locations. RESULTS: Dice scores for VS and IE volume segmentations were 0.91 and 0.90, respectively. On the public data set, the model segmented VS tumors with a Dice score of 0.89 ± 0.06 (mean ± standard deviation), relative volume error of 9.8 ± 9.6%, average symmetric surface distance of 0.31 ± 0.22 mm, and 95th-percentile Hausdorff distance of 1.26 ± 0.76 mm. Predicted VS segmentations overlapped with ground truth segmentations in all test subjects. Mean errors of predicted VS volume, VS centroid location, and IE centroid location were 0.05 cm 3 , 0.52 mm, and 0.85 mm, respectively. CONCLUSIONS: A deep learning system can segment VS and IE structures in high-resolution MRI scans with excellent accuracy. This technology offers promise to improve the clinical workflow for assessing VS radiomics and enhance the management of VS patients.

Augmented Reality for Retrosigmoid Craniotomy Planning.

While medical imaging data have traditionally been viewed on two-dimensional (2D) displays, augmented reality (AR) allows physicians to project the medical imaging data on patient's bodies to locate important anatomy. We present a surgical AR application to plan the retrosigmoid craniotomy, a standard approach to access the posterior fossa and the internal auditory canal. As a simple and accurate alternative to surface landmarks and conventional surgical navigation systems, our AR application augments the surgeon's vision to guide the optimal location of cortical bone removal. In this work, two surgeons performed a retrosigmoid approach 14 times on eight cadaver heads. In each case, the surgeon manually aligned a computed tomography (CT)-derived virtual rendering of the sigmoid sinus on the real cadaveric heads using a see-through AR display, allowing the surgeon to plan and perform the craniotomy accordingly. Postprocedure CT scans were acquired to assess the accuracy of the retrosigmoid craniotomies with respect to their intended location relative to the dural sinuses. The two surgeons had a mean margin of d avg = 0.6 ± 4.7 mm and d avg = 3.7 ± 2.3 mm between the osteotomy border and the dural sinuses over all their cases, respectively, and only positive margins for 12 of the 14 cases. The intended surgical approach to the internal auditory canal was successfully achieved in all cases using the proposed method, and the relatively small and consistent margins suggest that our system has the potential to be a valuable tool to facilitate planning a variety of similar skull-base procedures.

Fully Automated Measurement of Cochlear Duct Length From Clinical Temporal Bone Computed Tomography.

OBJECTIVES/HYPOTHESIS: To present and validate a novel fully automated method to measure cochlear dimensions, including cochlear duct length (CDL). STUDY DESIGN: Cross-sectional study. METHODS: The computational method combined 1) a deep learning (DL) algorithm to segment the cochlea and otic capsule and 2) geometric analysis to measure anti-modiolar distances from the round window to the apex. The algorithm was trained using 165 manually segmented clinical computed tomography (CT). A Testing group of 159 CTs were then measured for cochlear diameter and width (A- and B-values) and CDL using the automated system and compared against manual measurements. The results were also compared with existing approaches and historical data. In addition, pre- and post-implantation scans from 27 cochlear implant recipients were studied to compare predicted versus actual array insertion depth. RESULTS: Measurements were successfully obtained in 98.1% of scans. The mean CDL to 900° was 35.52 mm (SD, 2.06; range, [30.91-40.50]), the mean A-value was 8.88 mm (0.47; [7.67-10.49]), and mean B-value was 6.38 mm (0.42; [5.16-7.38]). The R2 fit of the automated to manual measurements was 0.87 for A-value, 0.70 for B-value, and 0.71 for CDL. For anti-modiolar arrays, the distance between the imaged and predicted array tip location was 0.57 mm (1.25; [0.13-5.28]). CONCLUSION: Our method provides a fully automated means of cochlear analysis from clinical CTs. The distribution of CDL, dimensions, and cochlear quadrant lengths is similar to those from historical data. This approach requires no radiographic experience and is free from user-related variation. LEVEL OF EVIDENCE: 3 Laryngoscope, 132:449-458, 2022.

Application of holographic augmented reality for external approaches to the frontal sinus.

BACKGROUND: External approaches to the frontal sinus such as osteoplastic flaps are challenging because they require blind entry into the sinus, posing risks of injury to the brain or orbit. Intraoperative computed tomography (CT)-based navigation is the current standard for planning the approach, but still necessitates blind entry into the sinus. The aim of this work was to describe a novel technique for external approaches to the frontal sinus using a holographic augmented reality (AR) application. METHODS: Our team developed an AR system to create a 3-dimensional (3D) hologram of key anatomical structures, based on CT scans images. Using Magic Leap AR goggles for visualization, the frontal sinus hologram was aligned to the surface anatomy in 6 fresh cadaveric heads' anatomic boundaries, and the boundaries of the frontal sinus were demarcated based on the margins of the fused image. Trephinations and osteoplastic flap approaches were performed. The specimens were re-scanned to assess the accuracy of the osteotomy with respect to the actual frontal sinus perimeter. RESULTS: Registration and surgery were completed successfully in all specimens. Registration required an average of 2 minutes. The postprocedure CT showed a mean difference of 1.4 ± 4.1 mm between the contour of the osteotomy and the contour of the frontal sinus. One surgical complication (posterior table perforation) occurred (16%). CONCLUSION: We describe proof of concept of a novel technique utilizing AR to enhance external approaches to the frontal sinus. Holographic AR-enhanced surgical navigation holds promise for enhanced visualization of target structures during surgical approaches to the sinuses.

Impact of Dorsal Preservation Rhinoplasty Versus Dorsal Hump Resection on the Internal Nasal Valve: a Quantitative Radiological Study.

BACKGROUND: This study evaluates the impact of different hump takedown techniques, namely the conventional hump resection with midvault reconstruction, the push-down (PD) and the let-down (LD) procedures, on the INV dimensions. METHODS: In this cadaveric study, six heads were divided randomly into either the conventional hump resection technique (Group A; n = 6 sides) or DPR techniques (n = 6 sides). This latter group was subdivided such that initially a PD procedure was performed (Group B; n = 6 sides), followed by a LD procedure on the same heads (Group C; n = 6 sides). A validated radiological method was used to measure the INV angle and cross-sectional area (CSA) in a modified coronal plane both pre- and post-procedurally. RESULTS: Group A did not show significant reduction in the INV angle nor in CSA (p = 0.068 and p = 0.156, respectively). In the push-down group (B), we observed a mean change of 2.05° in the angles and 0.3 cm2 in the CSA (p = 0.0163 and p < 0.001, respectively). The LD group (C) did not show significant reduction in the INV angle nor in CSA (p = 0.437 and p = 0.331, respectively). CONCLUSION: Neither the conventional hump resection nor the LD DPR technique reduced the INV dimensions. However, the PD preservation technique significantly reduced the INV dimensions. LEVEL OF EVIDENCE III: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266.