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

Seyed-Ahmad Ahmadi; Johann Frei; Gerome Vivar; Marianne Dieterich; Valerie Kirsch

doi:10.3389/fneur.2022.663200

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

Front Neurol. 2022 May 11:13:663200. doi: 10.3389/fneur.2022.663200. eCollection 2022.

Authors

Seyed-Ahmad Ahmadi^{1

2

3}, Johann Frei⁴, Gerome Vivar^{1

5}, Marianne Dieterich^{1

2

6

7}, Valerie Kirsch^{1

2

6}

Affiliations

¹ German Center for Vertigo and Balance Disorders, University Hospital, Ludwig-Maximilians-Universität, Munich, Germany.
² Department of Neurology, University Hospital, Ludwig-Maximilians-Universität, Munich, Germany.
³ NVIDIA GmbH, Munich, Germany.
⁴ IT-Infrastructure for Translational Medical Research, University of Augsburg, Augsburg, Germany.
⁵ Computer Aided Medical Procedures (CAMP), Technical University of Munich (TUM), Munich, Germany.
⁶ Graduate School of Systemic Neuroscience (GSN), Ludwig-Maximilians-Universität, Munich, Germany.
⁷ Munich Cluster for Systems Neurology (SyNergy), Munich, Germany.

Abstract

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.

Keywords: MRI; VNet; convolutional neural network CNN; deep learning; endolymphatic and perilymphatic space; endolymphatic hydros; inner ear imaging; segmentation (image processing).