Microanatomy of the human tunnel of Corti structures and cochlear partition-tonotopic variations and transcellular signaling.

Auditory sensitivity and frequency resolution depend on the optimal transfer of sound-induced vibrations from the basilar membrane (BM) to the inner hair cells (IHCs), the principal auditory receptors. There remains a paucity of information on how this is accomplished along the frequency range in the human cochlea. Most of the current knowledge is derived either from animal experiments or human tissue processed after death, offering limited structural preservation and optical resolution. In our study, we analyzed the cytoarchitecture of the human cochlear partition at different frequency locations using high-resolution microscopy of uniquely preserved normal human tissue. The results may have clinical implications and increase our understanding of how frequency-dependent acoustic vibrations are carried to human IHCs. A 1-micron-thick plastic-embedded section (mid-modiolar) from a normal human cochlea uniquely preserved at lateral skull base surgery was analyzed using light and transmission electron microscopy (LM, TEM). Frequency locations were estimated using synchrotron radiation phase-contrast imaging (SR-PCI). Archival human tissue prepared for scanning electron microscopy (SEM) and super-resolution structured illumination microscopy (SR-SIM) were also used and compared in this study. Microscopy demonstrated great variations in the dimension and architecture of the human cochlear partition along the frequency range. Pillar cell geometry was closely regulated and depended on the reticular lamina slope and tympanic lip angle. A type II collagen-expressing lamina extended medially from the tympanic lip under the inner sulcus, here named "accessory basilar membrane." It was linked to the tympanic lip and inner pillar foot, and it may contribute to the overall compliance of the cochlear partition. Based on the findings, we speculate on the remarkable microanatomic inflections and geometric relationships which relay different sound-induced vibrations to the IHCs, including their relevance for the evolution of human speech reception and electric stimulation with auditory implants. The inner pillar transcellular microtubule/actin system's role of directly converting vibration energy to the IHC cuticular plate and ciliary bundle is highlighted.

Development and validation of a surgical planning tool for bone-conduction implants.

Background: The BONEBRIDGE® (Med-El GmbH) is a bone-conduction device comprising an external audio processor and an internal Bone Conduction-Floating Mass Transducer (BC-FMT) surgically anchored to the temporal bone. Due to the implant's size, its placement may be challenging in certain anatomies, necessitating thorough surgical planning. Manual planning methods are laborious, time-intensive, and prone to errors. This study aimed to develop and validate an automated algorithm for determining skull thickness, aiding in the surgical planning of the BONEBRIDGE and other devices requiring similar bone thickness estimations. Materials and methods: Twelve cadaveric temporal bones underwent clinical computed tomography (CT). A custom Python algorithm was developed to automatically segment bone from soft tissue, generate 3D models, and perform ray-tracing to estimate bone thickness. Two thickness colormaps were generated for each sample: the cortical thickness to the first air cell and the total thickness down to the dura. The algorithm was validated against expert manual measurements to achieve consensus interpretation. Results: The algorithm estimated bone-to-air thicknesses (mean = 4.7 mm, 95% Confidence Interval [CI] of 4.3-5.0 mm) that closely matched the expert measurements (mean = 4.7 mm, CI of 4.4-5.0 mm), with a mean absolute difference (MAD) of 0.3 mm. Similarly, the algorithm's estimations to the dura (6.0 mm, CI of 5.4-6.5 mm) were comparable to the expert markings (5.9 mm, CI of 5.4-6.5 mm), with a MAD of 0.3 mm. Conclusions: The first automated algorithm to calculate skull thickness to both the air cells and dura in the temporal bone was developed. Colormaps were optimized to aid with the surgical planning of BONEBRIDGE implantation, however the tool can be generalized to aid in the surgical planning of any bone thickness application. The tool was published as a freely available extension to the open-source 3D Slicer software program (www.slicer.org).

Morphologic Analysis of the Scala Tympani Using Synchrotron: Implications for Cochlear Implantation.

OBJECTIVES: To use synchrotron radiation phase-contrast imaging (SR-PCI) to visualize and measure the morphology of the entire cochlear scala tympani (ST) and assess cochlear implant (CI) electrode trajectories. METHODS: SR-PCI images were used to obtain geometric measurements of the cochlear scalar diameter and area at 5-degree increments in 35 unimplanted and three implanted fixed human cadaveric cochleae. RESULTS: The cross-sectional diameter and area of the cochlea were found to decrease from the base to the apex. This study represents a wide variability in cochlear morphology and suggests that even in the smallest cochlea, the ST can accommodate a 0.4 mm diameter electrode up to 720°. Additionally, all lateral wall array trajectories were within the anatomically accommodating insertion zone. CONCLUSION: This is the first study to use SR-PCI to visualize and quantify the entire ST morphology, from the round window to the apical tip, and assess the post-operative trajectory of electrodes. These high-resolution anatomical measurements can be used to inform the angular insertion depth that can be accommodated in CI patients, accounting for anatomical variability. LEVEL OF EVIDENCE: N/A. Laryngoscope, 134:2889-2897, 2024.

Virtual Reality Simulation for the Middle Cranial Fossa Approach: A Validation Study.

BACKGROUND AND OBJECTIVES: Virtual reality (VR) surgical rehearsal is an educational tool that exists in a safe environment. Validation is necessary to establish the educational value of this platform. The middle cranial fossa (MCF) is ideal for simulation because trainees have limited exposure to this approach and it has considerable complication risk. Our objectives were to assess the face, content, and construct validities of an MCF VR simulation, as well as the change in performance across serial simulations. METHODS: Using high-resolution volumetric data sets of human cadavers, the authors generated a high-fidelity visual and haptic rendering of the MCF approach using CardinalSim software. Trainees from Neurosurgery and Otolaryngology-Head and Neck Surgery at two Canadian academic centers performed MCF dissections on this VR platform. Randomization was used to assess the effect of enhanced VR interaction. Likert scales were used to assess the face and content validities. Performance metrics and pre- and postsimulation test scores were evaluated. Construct validity was evaluated by examining the effect of the training level on simulation performance. RESULTS: Twenty trainees were enrolled. Face and content validities were achieved in all domains. Construct validity, however, was not demonstrated. Postsimulation test scores were significantly higher than presimulation test scores ( P < .001 ). Trainees demonstrated statistically significant improvement in the time to complete dissections ( P < .001 ), internal auditory canal skeletonization ( P < .001 ), completeness of the anterior petrosectomy ( P < .001 ), and reduced number of injuries to critical structures ( P = .001 ). CONCLUSION: This MCF VR simulation created using CardinalSim demonstrated face and content validities. Construct validity was not established because no trainee included in the study had previous MCF approach experience, which further emphasizes the importance of simulation. When used as a formative educational adjunct in both Neurosurgery and Otolaryngology-Head and Neck Surgery, this simulation has the potential to enhance understanding of the complex anatomic relationships of critical neurovascular structures.

Influence of the Frequency-to-Place Function on Recognition with Place-Based Cochlear Implant Maps.

OBJECTIVE: Comparison of acute speech recognition for cochlear implant (CI) alone and electric-acoustic stimulation (EAS) users listening with default maps or place-based maps using either a spiral ganglion (SG) or a new Synchrotron Radiation-Artificial Intelligence (SR-AI) frequency-to-place function. METHODS: Thirteen adult CI-alone or EAS users completed a task of speech recognition at initial device activation with maps that differed in the electric filter frequency assignments. The three map conditions were: (1) maps with the default filter settings (default map), (2) place-based maps with filters aligned to cochlear SG tonotopicity using the SG function (SG place-based map), and (3) place-based maps with filters aligned to cochlear Organ of Corti (OC) tonotopicity using the SR-AI function (SR-AI place-based map). Speech recognition was evaluated using a vowel recognition task. Performance was scored as the percent correct for formant 1 recognition due to the rationale that the maps would deviate the most in the estimated cochlear place frequency for low frequencies. RESULTS: On average, participants had better performance with the OC SR-AI place-based map as compared to the SG place-based map and the default map. A larger performance benefit was observed for EAS users than for CI-alone users. CONCLUSION: These pilot data suggest that EAS and CI-alone users may experience better performance with a patient-centered mapping approach that accounts for the variability in cochlear morphology (OC SR-AI frequency-to-place function) in the individualization of the electric filter frequencies (place-based mapping procedure). LEVEL OF EVIDENCE: 3 Laryngoscope, 133:3540-3547, 2023.

Finite element modelling of the human middle ear using synchrotron-radiation phase-contrast imaging.

Finite element (FE) models of the middle ear often lack accurate geometry of soft tissue structures, such as the suspensory ligaments, as they can be difficult to discern using conventional imaging modalities, such as computed tomography. Synchrotron-radiation phase-contrast imaging (SR-PCI) is a non-destructive imaging modality that has been shown to produce excellent visualization of soft tissue structures without the need for extensive sample preparation. The objectives of the investigation were to firstly use SR-PCI to create and evaluate a biomechanical FE model of the human middle ear that includes all soft tissue structures, and secondly, to investigate how modelling assumptions and simplifications of ligament representations affect the simulated biomechanical response of the FE model. The FE model included the suspensory ligaments, ossicular chain, tympanic membrane, the incudostapedial and incudomalleal joints, and the ear canal. Frequency responses obtained from the SR-PCI-based FE model agreed well with published laser doppler vibrometer measurements on cadaveric samples. Revised models with exclusion of the superior malleal ligament (SML), simplification of the SML, and modification of the stapedial annular ligament were studied, as these revised models represented modelling assumptions that have been made in literature.

Unlocking the human inner ear for therapeutic intervention.

The human inner ear contains minute three-dimensional neurosensory structures that are deeply embedded within the skull base, rendering them relatively inaccessible to regenerative therapies for hearing loss. Here we provide a detailed characterisation of the functional architecture of the space that hosts the cell bodies of the auditory nerve to make them safely accessible for the first time for therapeutic intervention. We used synchrotron phase-contrast imaging which offers the required microscopic soft-tissue contrast definition while simultaneously displaying precise bony anatomic detail. Using volume-rendering software we constructed highly accurate 3-dimensional representations of the inner ear. The cell bodies are arranged in a bony helical canal that spirals from the base of the cochlea to its apex; the canal volume is 1.6 µL but with a diffusion potential of 15 µL. Modelling data from 10 temporal bones enabled definition of a safe trajectory for therapeutic access while preserving the cochlea's internal architecture. We validated the approach through surgical simulation, anatomical dissection and micro-radiographic analysis. These findings will facilitate future clinical trials of novel therapeutic interventions to restore hearing.

High-Fidelity Virtual Reality Simulation for the Middle Cranial Fossa Approach-Modules for Surgical Rehearsal and Education.

BACKGROUND: Virtual reality simulation has gained prominence as a valuable surgical rehearsal and education tool in neurosurgery. Approaches to the internal auditory canal, cerebellopontine angle, and ventral brainstem region using the middle cranial fossa are not well explored by simulation. OBJECTIVE: We hope to contribute to this paucity in simulation tools devoted to the lateral skull base, specifically the middle cranial fossa approach. METHODS: Eight high-resolution microcomputed tomography scans of human cadavers were used as volumetric data sets to construct a high-fidelity visual and haptic rendering of the middle cranial fossa using CardinalSim software. Critical neurovascular structures related to this region of the skull base were segmented and incorporated into the modules. RESULTS: The virtual models illustrate the 3-dimensional anatomic relationships of neurovascular structures in the middle cranial fossa and allow a realistic interactive drilling environment. This is facilitated by the ability to render bone opaque or transparent to reveal the proximity to critical anatomy allowing for practice of the virtual dissection in a graduated fashion. CONCLUSION: We have developed a virtual library of middle cranial fossa approach models, which integrate relevant neurovascular structures with aims to improve surgical training and education. A ready extension is the potential for patient-specific application and pathology.

Machine learning approaches used to analyze auditory evoked responses from the human auditory brainstem: A systematic review.

BACKGROUND: The application of machine learning algorithms for assessing the auditory brainstem response has gained interest over recent years with a considerable number of publications in the literature. In this systematic review, we explore how machine learning has been used to develop algorithms to assess auditory brainstem responses. A clear and comprehensive overview is provided to allow clinicians and researchers to explore the domain and the potential translation to clinical care. METHODS: The systematic review was performed based on PRISMA guidelines. A search was conducted of PubMed, IEEE-Xplore, and Scopus databases focusing on human studies that have used machine learning to assess auditory brainstem responses. The duration of the search was from January 1, 1990, to April 3, 2021. The Covidence systematic review platform (www.covidence.org) was used throughout the process. RESULTS: A total of 5812 studies were found through the database search and 451 duplicates were removed. The title and abstract screening process further reduced the article count to 89 and in the proceeding full-text screening, 34 articles met our full inclusion criteria. CONCLUSION: Three categories of applications were found, namely neurologic diagnosis, hearing threshold estimation, and other (does not relate to neurologic or hearing threshold estimation). Neural networks and support vector machines were the most commonly used machine learning algorithms in all three categories. Only one study had conducted a clinical trial to evaluate the algorithm after development. Challenges remain in the amount of data required to train machine learning models. Suggestions for future research avenues are mentioned with recommended reporting methods for researchers.

A Synchrotron and Micro-CT Study of the Human Endolymphatic Duct System: Is Meniere's Disease Caused by an Acute Endolymph Backflow?

Background: The etiology of Meniere's disease (MD) and endolymphatic hydrops believed to underlie its symptoms remain unknown. One reason may be the exceptional complexity of the human inner ear, its vulnerability, and surrounding hard bone. The vestibular organ contains an endolymphatic duct system (EDS) bridging the different fluid reservoirs. It may be essential for monitoring hydraulic equilibrium, and a dysregulation may result in distension of the fluid spaces or endolymphatic hydrops. Material and Methods: We studied the EDS using high-resolution synchrotron phase contrast non-invasive imaging (SR-PCI), and micro-computed tomography (micro-CT). Ten fresh human temporal bones underwent SR-PCI. One bone underwent micro-CT after fixation and staining with Lugol's iodine solution (I2KI) to increase tissue resolution. Data were processed using volume-rendering software to create 3D reconstructions allowing orthogonal sectioning, cropping, and tissue segmentation. Results: Combined imaging techniques with segmentation and tissue modeling demonstrated the 3D anatomy of the human saccule, utricle, endolymphatic duct, and sac together with connecting pathways. The utricular duct (UD) and utriculo-endolymphatic valve (UEV or Bast's valve) were demonstrated three-dimensionally for the first time. The reunion duct was displayed with micro-CT. It may serve as a safety valve to maintain cochlear endolymph homeostasis under certain conditions. Discussion: The thin reunion duct seems to play a minor role in the exchange of endolymph between the cochlea and vestibule under normal conditions. The saccule wall appears highly flexible, which may explain occult hydrops occasionally preceding symptoms in MD on magnetic resonance imaging (MRI). The design of the UEV and connecting ducts suggests that there is a reciprocal exchange of fluid among the utricle, semicircular canals, and the EDS. Based on the anatomic framework and previous experimental data, we speculate that precipitous vestibular symptoms in MD arise from a sudden increase in endolymph pressure caused by an uncontrolled endolymphatic sac secretion. A rapid rise in UD pressure, mediated along the fairly wide UEV, may underlie the acute vertigo attack, refuting the rupture/K+-intoxication theory.

Comprehensive metrics for evaluating surgical microscope use during tympanostomy tube placement.

PURPOSE: Learning to use a surgical microscope is a fundamental step in otolaryngology training; however, there is currently no objective method to teach or assess this skill. Tympanostomy tube placement is a common otologic procedure that requires skilled use of a surgical microscope. This study was designed to (1) implement metrics capable of evaluating microscope use and (2) establish construct validity. STUDY DESIGN: This was a prospective cohort study. METHODS: Eight otolaryngology trainees and three otolaryngology experts were asked to use a microscope to insert a tympanostomy tube into a cadaveric myringotomy in a standardized setting. Microscope movements were tracked in a three-dimensional space, and tracking metrics were applied to the data. The procedure was video-recorded and then analyzed by blinded experts using operational metrics. Results from both groups were compared, and discriminatory metrics were determined. RESULTS: The following tracking metrics were identified as discriminatory between the trainee and expert groups: total completion time, operation time, still time, and jitter (movement perturbation). Many operational metrics were found to be discriminatory between the two groups, including several positioning metrics, optical metrics, and procedural metrics. CONCLUSIONS: Performance metrics were implemented, and construct validity was established for a subset of the proposed metrics by discriminating between expert and novice participants. These discriminatory metrics could form the basis of an automated system for providing feedback to residents during training while using a myringotomy surgical simulator. Additionally, these metrics may be useful in guiding a standardized teaching and evaluation methodology for training in the use of surgical microscopes.

Three-Dimensional Modeling and Measurement of the Human Cochlear Hook Region: Considerations for Tonotopic Mapping.

HYPOTHESIS: Measuring the length of the basilar membrane (BM) in the cochlear hook region will result in improved accuracy of cochlear duct length (CDL) measurements. BACKGROUND: Cochlear implant pitch mapping is generally performed in a patient independent approach, which has been shown to result in place-pitch mismatches. In order to customize cochlear implant pitch maps, accurate CDL measurements must be obtained. CDL measurements generally begin at the center of the round window (RW) and ignore the basal-most portion of the BM in the hook region. Measuring the size and morphology of the BM in the hook region can improve CDL measurements and our understanding of cochlear tonotopy. METHODS: Ten cadaveric human cochleae underwent synchrotron radiation phase-contrast imaging. The length of the BM through the hook region and CDL were measured. Two different CDL measurements were obtained for each sample, with starting points at the center of the RW (CDLRW) and the basal-most tip of the BM (CDLHR). Regression analysis was performed to relate CDLRW to CDLHR. A three-dimensional polynomial model was determined to describe the average BM hook region morphology. RESULTS: The mean CDLRW value was 33.03 ±â€Š1.62 mm, and the mean CDLHR value was 34.68 ±â€Š1.72 mm. The following relationship was determined between CDLRW and CDLHR: CDLHR  = 1.06(CDLRW)-0.26 (R2  = 0.99). CONCLUSION: The length and morphology of the hook region was determined. Current measurements underestimate CDL in the hook region and can be corrected using the results herein.

Micro-CT of the human ossicular chain: Statistical shape modeling and implications for otologic surgery.

The ossicular chain is a middle ear structure consisting of the small incus, malleus and stapes bones, which transmit tympanic membrane vibrations caused by sound to the inner ear. Despite being shown to be highly variable in shape, there are very few morphological studies of the ossicles. The objective of this study was to use a large sample of cadaveric ossicles to create a set of three-dimensional models and study their statistical variance. Thirty-three cadaveric temporal bone samples were scanned using micro-computed tomography (µCT) and segmented. Statistical shape models (SSMs) were then made for each ossicle to demonstrate the divergence of morphological features. Results revealed that ossicles were most likely to vary in overall size, but that more specific feature variability was found at the manubrium of the malleus, the long process and lenticular process of the incus, and the crura and footplate of the stapes. By analyzing samples as whole ossicular chains, it was revealed that when fixed at the malleus, changes along the chain resulted in a wide variety of final stapes positions. This is the first known study to create high-quality, three-dimensional SSMs of the human ossicles. This information can be used to guide otological surgical training and planning, inform ossicular prosthesis development, and assist with other ossicular studies and applications by improving automated segmentation algorithms. All models have been made publicly available.

An Approach for Individualized Cochlear Frequency Mapping Determined From 3D Synchrotron Radiation Phase-Contrast Imaging.

OBJECTIVE: Cochlear implants are traditionally programmed to stimulate according to a generalized frequency map, where individual anatomic variability is not considered when selecting the centre frequency of stimulation of each implant electrode. However, high variability in cochlear size and spatial frequency distributions exist among individuals. Generalized cochlear implant frequency maps can result in large pitch perception errors and reduced hearing outcomes for cochlear implant recipients. The objective of this work was to develop an individualized frequency mapping technique for the human cochlea to allow for patient-specific cochlear implant stimulation. METHODS: Ten cadaveric human cochleae were scanned using synchrotron radiation phase-contrast imaging (SR-PCI) combined with computed tomography (CT). For each cochlea, ground truth angle-frequency measurements were obtained in three-dimensions using the SR-PCI CT data. Using an approach designed to minimize perceptual error in frequency estimation, an individualized frequency function was determined to relate angular depth to frequency within the cochlea. RESULTS: The individualized frequency mapping function significantly reduced pitch errors in comparison to the current gold standard generalized approach. CONCLUSION AND SIGNIFICANCE: This paper presents for the first time a cochlear frequency map which can be individualized using only the angular length of cochleae. This approach can be applied in the clinical setting and has the potential to revolutionize cochlear implant programming for patients worldwide.

Vestibular Organ and Cochlear Implantation-A Synchrotron and Micro-CT Study.

Background: Reports vary on the incidence of vestibular dysfunction and dizziness in patients following cochlear implantation (CI). Disequilibrium may be caused by surgery at the cochlear base, leading to functional disturbances of the vestibular receptors and endolymphatic duct system (EDS) which are located nearby. Here, we analyzed the three-dimensional (3D) anatomy of this region, aiming to optimize surgical approaches to limit damage to the vestibular organ. Material and Methods: A total of 22 fresh-frozen human temporal bones underwent synchrotron radiation phase-contrast imaging (SR-PCI). One temporal bone underwent micro-computed tomography (micro-CT) after fixation and staining with Lugol's iodine solution (I2KI) to increase tissue contrast. We used volume-rendering software to create 3D reconstructions and tissue segmentation that allowed precise assessment of anatomical relationships and topography. Macerated human ears belonging to the Uppsala collection were also used. Drilling and insertion of CI electrodes was performed with metric analyses of different trajectories. Results and Conclusions: SR-PCI and micro-CT imaging demonstrated the complex 3D anatomy of the basal region of the human cochlea, vestibular apparatus, and EDS. Drilling of a cochleostomy may disturb vestibular organ function by injuring the endolymphatic space and disrupting fluid barriers. The saccule is at particular risk due to its proximity to the surgical area and may explain immediate and long-term post-operative vertigo. Round window insertion may be less traumatic to the inner ear, however it may affect the vestibular receptors.

Aeration of the Human Prussak's Space: A 3D Synchrotron Imaging Study.

OBJECTIVES: Prussak's space (PS) is an intricate middle ear region which may play an essential role in the development of middle ear disease. The three-dimensional (3D) anatomy of the human PS and its drainage routes remain relatively unknown. Earlier studies have histologically analyzed PS, by micro-dissection and endoscopy. Here, we used synchrotron-radiation phase-contrast imaging (SR-PCI), 3D reconstructions, and modeling to study the framework of the human PS, including aeration pathways. It may lead to increased understanding of development of middle ear pathology. DESIGN: Nine human temporal bone specimens underwent in-line SR-PCI at the Canadian Light Source in Saskatoon, Saskatchewan, Canada. Data were processed with volume-rendering software to create 3D reconstructions using scalar opacity mapping and segmentations to visualize its walls in fixed, undecalcified human temporal bones. RESULTS: The PS was found to be an irregular, variably shaped chamber with different aeration systems. Three different drainage pathways were found: 1) via the posterior malleolar pouch of von Tröltsch in seven of nine ears; 2) directly posterior-inferior into the mesotympanum medial to the posterior malleolar pouch in one ear; and 3) anteriorly in another. The posterior-inferior communications depended on the anatomy of the posterior malleolar fold. In one bilateral case, the aeration differed between the ears. Earlier descriptions of upper ventilation routes between the PS and the epitympanic spaces could not be substantiated. CONCLUSIONS: The 3D anatomy of the membrane folds organizing the PS in humans was demonstrated for the first time using in-line SR-PCI. The PS was always aerated into the mesotympanum, suggesting its relative independence of attic ventilation. The impact of its various drainage routes on middle ear ventilation and disease were discussed.

Three-dimensional tonotopic mapping of the human cochlea based on synchrotron radiation phase-contrast imaging.

The human cochlea transforms sound waves into electrical signals in the acoustic nerve fibers with high acuity. This transformation occurs via vibrating anisotropic membranes (basilar and tectorial membranes) and frequency-specific hair cell receptors. Frequency-positions can be mapped within the cochlea to create a tonotopic chart which fits an almost-exponential function with lowest frequencies positioned apically and highest frequencies positioned at the cochlear base (Bekesy 1960, Greenwood 1961). To date, models of frequency positions have been based on a two-dimensional analysis with inaccurate representations of the cochlear hook region. In the present study, the first three-dimensional frequency analysis of the cochlea using dendritic mapping to obtain accurate tonotopic maps of the human basilar membrane/organ of Corti and the spiral ganglion was performed. A novel imaging technique, synchrotron radiation phase-contrast imaging, was used and a spiral ganglion frequency function was estimated by nonlinear least squares fitting a Greenwood-like function (F = A (10ax - K)) to the data. The three-dimensional tonotopic data presented herein has large implications for validating electrode position and creating customized frequency maps for cochlear implant recipients.

Comparison of machine learning models to classify Auditory Brainstem Responses recorded from children with Auditory Processing Disorder.

INTRODUCTION: Auditory brainstem responses (ABRs) offer a unique opportunity to assess the neural integrity of the peripheral auditory nervous system in individuals presenting with listening difficulties. ABRs are typically recorded and analyzed by an audiologist who manually measures the timing and quality of the waveforms. The interpretation of ABRs requires considerable experience and training, and inappropriate interpretation can lead to incorrect judgments about the integrity of the system. Machine learning (ML) techniques may be a suitable approach to automate ABR interpretation and reduce human error. OBJECTIVES: The main objective of this paper was to identify a suitable ML technique to automate the analysis of ABR responses recorded as a part of the electrophysiological testing in the Auditory Processing Disorder clinical test battery. METHODS: ABR responses recorded during routine clinical assessment from 136 children being evaluated for auditory processing difficulties were analyzed using several common ML algorithms: Support Vector Machines (SVM), Random Forests (RF), Decision Trees (DT), Gradient Boosting (GB), Extreme Gradient Boosting (Xgboost), and Neural Networks (NN). A variety of signal feature extraction techniques were used to extract features from the ABR waveforms as inputs to the ML algorithms. Statistical significance testing and confusion matrices were used to identify the most robust model capable of accurately identifying neurological abnormalities present in ABRs. RESULTS: Clinically significant features in the time-frequency representation of the signal were identified. The ML model trained using the Xgboost algorithm was identified as the most robust model with an accuracy of 92% compared to other models. CONCLUSION: The findings of the present study demonstrate that it is possible to develop accurate ML models to automate the process of analyzing ABR waveforms recorded at suprathreshold levels. There is currently no ML-based application to screen children with listening difficulties. Therefore, it is expected that this work will be translated into an evaluation tool that can be used by audiologists in the clinic. Furthermore, this work may aid future researchers in exploring ML paradigms to improve clinical test batteries used by audiologists in achieving accurate diagnoses.

PWD-3DNet: A Deep Learning-Based Fully-Automated Segmentation of Multiple Structures on Temporal Bone CT Scans.

The temporal bone is a part of the lateral skull surface that contains organs responsible for hearing and balance. Mastering surgery of the temporal bone is challenging because of this complex and microscopic three-dimensional anatomy. Segmentation of intra-temporal anatomy based on computed tomography (CT) images is necessary for applications such as surgical training and rehearsal, amongst others. However, temporal bone segmentation is challenging due to the similar intensities and complicated anatomical relationships among critical structures, undetectable small structures on standard clinical CT, and the amount of time required for manual segmentation. This paper describes a single multi-class deep learning-based pipeline as the first fully automated algorithm for segmenting multiple temporal bone structures from CT volumes, including the sigmoid sinus, facial nerve, inner ear, malleus, incus, stapes, internal carotid artery and internal auditory canal. The proposed fully convolutional network, PWD-3DNet, is a patch-wise densely connected (PWD) three-dimensional (3D) network. The accuracy and speed of the proposed algorithm was shown to surpass current manual and semi-automated segmentation techniques. The experimental results yielded significantly high Dice similarity scores and low Hausdorff distances for all temporal bone structures with an average of 86% and 0.755 millimeter (mm), respectively. We illustrated that overlapping in the inference sub-volumes improves the segmentation performance. Moreover, we proposed augmentation layers by using samples with various transformations and image artefacts to increase the robustness of PWD-3DNet against image acquisition protocols, such as smoothing caused by soft tissue scanner settings and larger voxel sizes used for radiation reduction. The proposed algorithm was tested on low-resolution CTs acquired by another center with different scanner parameters than the ones used to create the algorithm and shows potential for application beyond the particular training data used in the study.

The BONEBRIDGE active transcutaneous bone conduction implant: effects of location, lifts and screws on sound transmission.

BACKGROUND: The BONEBRIDGE (MED-EL, Innsbruck, Austria) is a bone-conduction implant used in the treatment of conductive and mixed hearing loss. The BONEBRIDGE consists of an external audio processor and a bone-conduction floating mass transducer that is surgically implanted into the skull in either the transmastoid, retrosigmoid or middle fossa regions. The manufacturer includes self-tapping screws to secure the transducer; however, self-drilling screws have also been used with success. In cases where the skull is not thick enough to house the transducer, lifts are available in a variety of sizes to elevate the transducer away from the skull. The objective of the present study was to investigate the effects of screw type, lift thickness, and implant location on the sound transmission of the BONEBRIDGE. METHOD: Six cadaveric temporal bones were embalmed and dried for use in this study. In each sample, a hole was drilled in each of the three implant locations to house the implant transducer. At the middle fossa, six pairs of screw holes were pre-drilled; four pairs to be used with self-tapping screws and lifts (1, 2, 3, and 4 mm thick lifts, respectively), one pair with self-tapping screws and no lifts, and one pair with self-drilling screws and no lifts. At the transmastoid and retrosigmoid locations, one pair of screw holes were pre-drilled in each for the use of the self-tapping screws. The vibration of transmitted sound to the cochlea was measured using a laser Doppler vibrometry technique. The measurements were performed on the cochlear promontory at eight discrete frequencies (0.5, 0.75, 1, 1.5, 2, 3, 4 and 6 kHz). Vibration velocity of the cochlear wall was measured in all samples. Measurements were analyzed using a single-factor ANOVA to investigate the effect of each modification. RESULTS: No significant differences were found related to either screw type, lift thickness, or implant location. CONCLUSIONS: This is the first known study to evaluate the effect of screw type, lift thickness, and implant location on the sound transmission produced by the BONEBRIDGE bone-conduction implant. Further studies may benefit from analysis using fresh cadaveric samples or in-vivo measurements.