A probabilistic atlas of the human inner ear's bony labyrinth enables reliable atlas-based segmentation of the total fluid space

Improving rehabilitation of deaf patients by advanced imaging before cochlear implantation

INTRODUCTION

Cochlear implants have advanced the management of severe to profound deafness. However, there is a strong disparity in hearing performance after implantation from one patient to another. Moreover, there are several advanced kinds of imaging assessment before cochlear implantation. Microstructural white fiber degeneration can be studied with Diffusion weighted MRI (DWI) or tractography of the central auditory pathways. Functional MRI (fMRI) allows us to evaluate brain function, and CT or MRI segmentation to better detect inner ear anomalies.

OBJECTIVE

This literature review aims to evaluate how helpful pre-implantation anatomic imaging can be to predict hearing rehabilitation outcomes in deaf patients. These techniques include DWI and fMRI of the central auditory pathways, and automated labyrinth segmentation by CT scan, cone beam CT and MRI.

DESIGN

This systematic review was performed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Studies were selected by searching in PubMed and by checking the reference lists of relevant articles. Inclusion criteria were adults over 18, with unilateral or bilateral hearing loss, who had DWI acquisition or fMRI or CT/ Cone Beam CT/ MRI image segmentation.

RESULTS

After reviewing 172 articles, we finally included 51. Studies on DWI showed changes in the central auditory pathways affecting the white matter, extending to the primary and non-primary auditory cortices, even in sudden and mild hearing impairment. Hearing loss patients show a reorganization of brain activity in various areas, such as the auditory and visual cortices, as well as regions involved in language and emotions, according to fMRI studies. Deep Learning's automatic segmentation produces the best CT segmentation in just a few seconds. MRI segmentation is mainly used to evaluate fluid space of the inner ear and determine the presence of an endolymphatic hydrops.

CONCLUSION

Before cochlear implantation, a DWI with tractography can evaluate the central auditory pathways up to the primary and non-primary auditory cortices. This data is then used to generate predictions on the auditory rehabilitation of patients. A CT segmentation with systematic 3D reconstruction allow a better evaluation of cochlear malformations and predictable difficulties during surgery.

Towards fully automated inner ear analysis with deep-learning-based joint segmentation and landmark detection framework

Automated analysis of the inner ear anatomy in radiological data instead of time-consuming manual assessment is a worthwhile goal that could facilitate preoperative planning and clinical research. We propose a framework encompassing joint semantic segmentation of the inner ear and anatomical landmark detection of helicotrema, oval and round window. A fully automated pipeline with a single, dual-headed volumetric 3D U-Net was implemented, trained and evaluated using manually labeled in-house datasets from cadaveric specimen ([Formula: see text]) and clinical practice ([Formula: see text]). The model robustness was further evaluated on three independent open-source datasets ([Formula: see text] scans) consisting of cadaveric specimen scans. For the in-house datasets, Dice scores of [Formula: see text], intersection-over-union scores of [Formula: see text] and average Hausdorff distances of [Formula: see text] and [Formula: see text] voxel units were achieved. The landmark localization task was performed automatically with an average localization error of [Formula: see text] voxel units. A robust, albeit reduced performance could be attained for the catalogue of three open-source datasets. Results of the ablation studies with 43 mono-parametric variations of the basal architecture and training protocol provided task-optimal parameters for both categories. Ablation studies against single-task variants of the basal architecture showed a clear performance benefit of coupling landmark localization with segmentation and a dataset-dependent performance impact on segmentation ability.

IE-Vnet: Deep Learning-Based Segmentation of the Inner Ear's Total Fluid Space

Background

In-vivo MR-based high-resolution volumetric quantification methods of the endolymphatic hydrops (ELH) are highly dependent on a reliable segmentation of the inner ear's total fluid space (TFS). This study aimed to develop a novel open-source inner ear TFS segmentation approach using a dedicated deep learning (DL) model.

Methods

The model was based on a V-Net architecture (IE-Vnet) and a multivariate (MR scans: T1, T2, FLAIR, SPACE) training dataset (D1, 179 consecutive patients with peripheral vestibulocochlear syndromes). Ground-truth TFS masks were generated in a semi-manual, atlas-assisted approach. IE-Vnet model segmentation performance, generalizability, and robustness to domain shift were evaluated on four heterogenous test datasets (D2-D5, n = 4 × 20 ears).

Results

The IE-Vnet model predicted TFS masks with consistently high congruence to the ground-truth in all test datasets (Dice overlap coefficient: 0.9 ± 0.02, Hausdorff maximum surface distance: 0.93 ± 0.71 mm, mean surface distance: 0.022 ± 0.005 mm) without significant difference concerning side (two-sided Wilcoxon signed-rank test, p>0.05), or dataset (Kruskal-Wallis test, p>0.05; post-hoc Mann-Whitney U, FDR-corrected, all p>0.2). Prediction took 0.2 s, and was 2,000 times faster than a state-of-the-art atlas-based segmentation method.

Conclusion

IE-Vnet TFS segmentation demonstrated high accuracy, robustness toward domain shift, and rapid prediction times. Its output works seamlessly with a previously published open-source pipeline for automatic ELS segmentation. IE-Vnet could serve as a core tool for high-volume trans-institutional studies of the inner ear. Code and pre-trained models are available free and open-source under https://github.com/pydsgz/IEVNet.

Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study

BACKGROUND

Segmentation of important structures in temporal bone CT is the basis of image-guided otologic surgery. Manual segmentation of temporal bone CT is time- consuming and laborious. We assessed the feasibility and generalization ability of a proposed deep learning model for automated segmentation of critical structures in temporal bone CT scans.

METHODS

Thirty-nine temporal bone CT volumes including 58 ears were divided into normal (n = 20) and abnormal groups (n = 38). Ossicular chain disruption (n = 10), facial nerve covering vestibular window (n = 10), and Mondini dysplasia (n = 18) were included in abnormal group. All facial nerves, auditory ossicles, and labyrinths of the normal group were manually segmented. For the abnormal group, aberrant structures were manually segmented. Temporal bone CT data were imported into the network in unmarked form. The Dice coefficient (DC) and average symmetric surface distance (ASSD) were used to evaluate the accuracy of automatic segmentation.

RESULTS

In the normal group, the mean values of DC and ASSD were respectively 0.703, and 0.250 mm for the facial nerve; 0.910, and 0.081 mm for the labyrinth; and 0.855, and 0.107 mm for the ossicles. In the abnormal group, the mean values of DC and ASSD were respectively 0.506, and 1.049 mm for the malformed facial nerve; 0.775, and 0.298 mm for the deformed labyrinth; and 0.698, and 1.385 mm for the aberrant ossicles.

CONCLUSIONS

The proposed model has good generalization ability, which highlights the promise of this approach for otologist education, disease diagnosis, and preoperative planning for image-guided otology surgery.

Intravenous Delayed Gadolinium-Enhanced MR Imaging of the Endolymphatic Space: A Methodological Comparative Study

In-vivo non-invasive verification of endolymphatic hydrops (ELH) by means of intravenous delayed gadolinium (Gd) enhanced magnetic resonance imaging of the inner ear (iMRI) is rapidly developing into a standard clinical tool to investigate peripheral vestibulo-cochlear syndromes. In this context, methodological comparative studies providing standardization and comparability between labs seem even more important, but so far very few are available. One hundred eight participants [75 patients with Meniere's disease (MD; 55.2 ± 14.9 years) and 33 vestibular healthy controls (HC; 46.4 ± 15.6 years)] were examined. The aim was to understand (i) how variations in acquisition protocols influence endolymphatic space (ELS) MR-signals; (ii) how ELS quantification methods correlate to each other or clinical data; and finally, (iii) how ELS extent influences MR-signals. Diagnostics included neuro-otological assessment, video-oculography during caloric stimulation, head-impulse test, audiometry, and iMRI. Data analysis provided semi-quantitative (SQ) visual grading and automatic algorithmic quantitative segmentation of ELS area [2D, mm²] and volume [3D, mm³] using deep learning-based segmentation and volumetric local thresholding. Within the range of 0.1-0.2 mmol/kg Gd dosage and a 4 h ± 30 min time delay, SQ grading and 2D- or 3D-quantifications were independent of signal intensity (SI) and signal-to-noise ratio (SNR; FWE corrected, p < 0.05). The ELS quantification methods used were highly reproducible across raters or thresholds and correlated strongly (0.3-0.8). However, 3D-quantifications showed the least variability. Asymmetry indices and normalized ELH proved the most useful for predicting quantitative clinical data. ELH size influenced SI (cochlear basal turn p < 0.001), but not SNR. SI could not predict the presence of ELH. In conclusion, (1) Gd dosage of 0.1-0.2 mmol/kg after 4 h ± 30 min time delay suffices for ELS quantification. (2) A consensus is needed on a clinical SQ grading classification including a standardized level of evaluation reconstructed to anatomical fixpoints. (3) 3D-quantification methods of the ELS are best suited for correlations with clinical variables and should include both ears and ELS values reported relative or normalized to size. (4) The presence of ELH increases signal intensity in the basal cochlear turn weakly, but cannot predict the presence of ELH.

Endolymphatic Hydrops in Patients With Vestibular Migraine and Concurrent Meniere's Disease

Objective: Intravenous contrast agent enhanced, high-resolution magnetic resonance imaging of the inner ear (iMRI) confirmed that patients with Menière's disease (MD) and vestibular migraine (VM) could present with endolymphatic hydrops (EH). The present study aimed to investigate EH characteristics and their interrelation to neurotologic testing in patients with VM, MD, or VM with concurrent MD (VM-MD).

Methods: Sixty–two patients (45 females, aged 23–81 years) with definite or probable VM (n = 25, 19 definite), MD (n = 29, 17 definite), or showing characteristics of both diseases (n = 8) were included in this study. Diagnostic workup included neurotologic assessments including video-oculography (VOG) during caloric stimulation and head-impulse test (HIT), ocular and cervical vestibular evoked myogenic potentials (o/cVEMP), pure tone audiometry (PTA), as well as iMRI. EH's degree was assessed visually and via volumetric quantification using a probabilistic atlas-based segmentation of the bony labyrinth and volumetric local thresholding (VOLT).

Results: Although a relevant number of VM patients reported varying auditory symptoms (13 of 25, 52.0%), EH in VM was only observed twice. In contrast, EH in VM-MD was prevalent (2/8, 25%) and in MD frequent [23/29, 79.3%; χ²(2) = 29.1, p < 0.001, φ = 0.7]. Location and laterality of EH and neurophysiological testing classifications were highly associated (Fisher exact test, p < 0.005). In MD, visual semi-quantitative grading and volumetric quantification correlated highly to each other (r_S = 0.8, p < 0.005, two-sided) and to side differences in VOG during caloric irrigation (vestibular EH ipsilateral: r_S = 0.6, p < 0.05, two-sided). In VM, correlations were less pronounced. VM-MD assumed an intermediate position between VM and MD.

Conclusion: Cochlear and vestibular hydrops can occur in MD and VM patients with auditory symptoms; this suggests inner ear damage irrespective of the diagnosis of MD or VM. The EH grades often correlated with auditory symptoms such as hearing impairment and tinnitus. Further research is required to uncover whether migraine is one causative factor of EH or whether EH in VM patients with auditory symptoms suggests an additional pathology due to MD.

IE-Map: a novel in-vivo atlas and template of the human inner ear

Brain atlases and templates are core tools in scientific research with increasing importance also in clinical applications. Advances in neuroimaging now allowed us to expand the atlas domain to the vestibular and auditory organ, the inner ear. In this study, we present IE-Map, an in-vivo template and atlas of the human labyrinth derived from multi-modal high-resolution magnetic resonance imaging (MRI) data, in a fully non-invasive manner without any contrast agent or radiation. We reconstructed a common template from 126 inner ears (63 normal subjects) and annotated it with 94 established landmarks and semi-automatic segmentations of all relevant macroscopic vestibular and auditory substructures. We validated the atlas by comparing MRI templates to a novel CT/micro-CT atlas, which we reconstructed from 21 publicly available post-mortem images of the bony labyrinth. Templates in MRI and micro-CT have a high overlap, and several key anatomical measures of the bony labyrinth in IE-Map are in line with micro-CT literature of the inner ear. A quantitative substructural analysis based on the new template, revealed a correlation of labyrinth parameters with total intracranial volume. No effects of gender or laterality were found. We provide the validated templates, atlas segmentations, surface meshes and landmark annotations as open-access material, to provide neuroscience researchers and clinicians in neurology, neurosurgery, and otorhinolaryngology with a widely applicable tool for computational neuro-otology.

Deep learning for the fully automated segmentation of the inner ear on MRI

Segmentation of anatomical structures is valuable in a variety of tasks, including 3D visualization, surgical planning, and quantitative image analysis. Manual segmentation is time-consuming and deals with intra and inter-observer variability. To develop a deep-learning approach for the fully automated segmentation of the inner ear in MRI, a 3D U-net was trained on 944 MRI scans with manually segmented inner ears as reference standard. The model was validated on an independent, multicentric dataset consisting of 177 MRI scans from three different centers. The model was also evaluated on a clinical validation set containing eight MRI scans with severe changes in the morphology of the labyrinth. The 3D U-net model showed precise Dice Similarity Coefficient scores (mean DSC-0.8790) with a high True Positive Rate (91.5%) and low False Discovery Rate and False Negative Rates (14.8% and 8.49% respectively) across images from three different centers. The model proved to perform well with a DSC of 0.8768 on the clinical validation dataset. The proposed auto-segmentation model is equivalent to human readers and is a reliable, consistent, and efficient method for inner ear segmentation, which can be used in a variety of clinical applications such as surgical planning and quantitative image analysis.

The Correlation of a 2D Volume-Referencing Endolymphatic-Hydrops Grading System With Extra-Tympanic Electrocochleography in Patients With Definite Ménière's Disease

Background: Although magnetic resonance imaging (MRI) of the membranous labyrinth and electrocochleography (ECochG) have been used to diagnose endolymphatic hydrops (ELH) in patients with Ménière's disease (MD), the relationship between imaging and ECochG is not well-documented. Objectives: This study evaluates the ELH using 3D-FLAIR MRI and extra-tympanic ECochG (ET-ECochG) and correlates the results from 3D-FLAIR MRI to those from ET-ECochG. Materials and Methods: 3D-FLAIR MRI images of 50 patients were assessed using a 2D volume-referencing grading system (VR scores, relative scores according to the known volumes of the cochlea, vestibule, and semicircular canals). Forty healthy subjects were included and compared to 51 definite MD ears of 50 patients while analyzing the ET-ECochG, which used a self-made bronze foil electrode. The amplitude ratio of the summating potential (SP) to the action potential (AP) (SP/AP) and the area ratio of SP to AP (Asp/Aap) were collected. Relative ELH grade scores were then correlated to ET-ECochG (SP/AP, Asp/Aap). Results: The VR scores showed a better correlation (r = 0.88) with the pure tone average (PTA), disease duration, and vertigo frequency of MD than the Bernaerts scores (grading the cochlea and vestibule separately) (r = 0.22). The SP/AP and Asp/Aap of the unilateral MD patients were statistically comparable to those measured in contralateral ears and the results between the definite MD ears with healthy ears were statistically comparable (p < 0.05). In a ROC analysis Asp/Aap (area under curve, AUC 0.98) significantly (p = 0.01) outperformed SP/AP (AUC 0.91). The total score of ELH, vestibular ELH, and cochlear ELH were also correlated with SP/AP and Asp/Aap. The strongest correlation was found between the Asp/Aap and cochlear ELH (r = 0.60). Conclusion: The 2D volume-referencing grading system was more meaningful than the Bernaerts scores. A correlation was found between ELH revealed by 3D-FLAIR MRI and the SP/AP of ET-ECochG in evaluating definite MD patients. The Asp/Aap appeared a more sensitive and reliable parameter than SP/AP for diagnosing the ELH of the membranous labyrinth.