Cargando…
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...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9130477/ https://www.ncbi.nlm.nih.gov/pubmed/35645963 http://dx.doi.org/10.3389/fneur.2022.663200 |
_version_ | 1784712978656919552 |
---|---|
author | Ahmadi, Seyed-Ahmad Frei, Johann Vivar, Gerome Dieterich, Marianne Kirsch, Valerie |
author_facet | Ahmadi, Seyed-Ahmad Frei, Johann Vivar, Gerome Dieterich, Marianne Kirsch, Valerie |
author_sort | Ahmadi, Seyed-Ahmad |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-9130477 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-91304772022-05-26 IE-Vnet: Deep Learning-Based Segmentation of the Inner Ear's Total Fluid Space Ahmadi, Seyed-Ahmad Frei, Johann Vivar, Gerome Dieterich, Marianne Kirsch, Valerie Front Neurol Neurology 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. Frontiers Media S.A. 2022-05-11 /pmc/articles/PMC9130477/ /pubmed/35645963 http://dx.doi.org/10.3389/fneur.2022.663200 Text en Copyright © 2022 Ahmadi, Frei, Vivar, Dieterich and Kirsch. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neurology Ahmadi, Seyed-Ahmad Frei, Johann Vivar, Gerome Dieterich, Marianne Kirsch, Valerie IE-Vnet: Deep Learning-Based Segmentation of the Inner Ear's Total Fluid Space |
title | IE-Vnet: Deep Learning-Based Segmentation of the Inner Ear's Total Fluid Space |
title_full | IE-Vnet: Deep Learning-Based Segmentation of the Inner Ear's Total Fluid Space |
title_fullStr | IE-Vnet: Deep Learning-Based Segmentation of the Inner Ear's Total Fluid Space |
title_full_unstemmed | IE-Vnet: Deep Learning-Based Segmentation of the Inner Ear's Total Fluid Space |
title_short | IE-Vnet: Deep Learning-Based Segmentation of the Inner Ear's Total Fluid Space |
title_sort | ie-vnet: deep learning-based segmentation of the inner ear's total fluid space |
topic | Neurology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9130477/ https://www.ncbi.nlm.nih.gov/pubmed/35645963 http://dx.doi.org/10.3389/fneur.2022.663200 |
work_keys_str_mv | AT ahmadiseyedahmad ievnetdeeplearningbasedsegmentationoftheinnerearstotalfluidspace AT freijohann ievnetdeeplearningbasedsegmentationoftheinnerearstotalfluidspace AT vivargerome ievnetdeeplearningbasedsegmentationoftheinnerearstotalfluidspace AT dieterichmarianne ievnetdeeplearningbasedsegmentationoftheinnerearstotalfluidspace AT kirschvalerie ievnetdeeplearningbasedsegmentationoftheinnerearstotalfluidspace |