Cargando…
Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets
Reliable biomarkers quantifying neurodegeneration and neuroinflammation in central nervous system disorders such as Multiple Sclerosis, Alzheimer’s dementia or Parkinson’s disease are an unmet clinical need. Intraretinal layer thicknesses on macular optical coherence tomography (OCT) images are prom...
Autores principales: | , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9146486/ https://www.ncbi.nlm.nih.gov/pubmed/35621903 http://dx.doi.org/10.3390/jimaging8050139 |
_version_ | 1784716575321882624 |
---|---|
author | Yadav, Sunil Kumar Kafieh, Rahele Zimmermann, Hanna Gwendolyn Kauer-Bonin, Josef Nouri-Mahdavi, Kouros Mohammadzadeh, Vahid Shi, Lynn Kadas, Ella Maria Paul, Friedemann Motamedi, Seyedamirhosein Brandt, Alexander Ulrich |
author_facet | Yadav, Sunil Kumar Kafieh, Rahele Zimmermann, Hanna Gwendolyn Kauer-Bonin, Josef Nouri-Mahdavi, Kouros Mohammadzadeh, Vahid Shi, Lynn Kadas, Ella Maria Paul, Friedemann Motamedi, Seyedamirhosein Brandt, Alexander Ulrich |
author_sort | Yadav, Sunil Kumar |
collection | PubMed |
description | Reliable biomarkers quantifying neurodegeneration and neuroinflammation in central nervous system disorders such as Multiple Sclerosis, Alzheimer’s dementia or Parkinson’s disease are an unmet clinical need. Intraretinal layer thicknesses on macular optical coherence tomography (OCT) images are promising noninvasive biomarkers querying neuroretinal structures with near cellular resolution. However, changes are typically subtle, while tissue gradients can be weak, making intraretinal segmentation a challenging task. A robust and efficient method that requires no or minimal manual correction is an unmet need to foster reliable and reproducible research as well as clinical application. Here, we propose and validate a cascaded two-stage network for intraretinal layer segmentation, with both networks being compressed versions of U-Net (CCU-INSEG). The first network is responsible for retinal tissue segmentation from OCT B-scans. The second network segments eight intraretinal layers with high fidelity. At the post-processing stage, we introduce Laplacian-based outlier detection with layer surface hole filling by adaptive non-linear interpolation. Additionally, we propose a weighted version of focal loss to minimize the foreground–background pixel imbalance in the training data. We train our method using 17,458 B-scans from patients with autoimmune optic neuropathies, i.e., multiple sclerosis, and healthy controls. Voxel-wise comparison against manual segmentation produces a mean absolute error of 2.3 μm, outperforming current state-of-the-art methods on the same data set. Voxel-wise comparison against external glaucoma data leads to a mean absolute error of 2.6 μm when using the same gold standard segmentation approach, and 3.7 μm mean absolute error in an externally segmented data set. In scans from patients with severe optic atrophy, 3.5% of B-scan segmentation results were rejected by an experienced grader, whereas this was the case in 41.4% of B-scans segmented with a graph-based reference method. The validation results suggest that the proposed method can robustly segment macular scans from eyes with even severe neuroretinal changes. |
format | Online Article Text |
id | pubmed-9146486 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-91464862022-05-29 Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets Yadav, Sunil Kumar Kafieh, Rahele Zimmermann, Hanna Gwendolyn Kauer-Bonin, Josef Nouri-Mahdavi, Kouros Mohammadzadeh, Vahid Shi, Lynn Kadas, Ella Maria Paul, Friedemann Motamedi, Seyedamirhosein Brandt, Alexander Ulrich J Imaging Article Reliable biomarkers quantifying neurodegeneration and neuroinflammation in central nervous system disorders such as Multiple Sclerosis, Alzheimer’s dementia or Parkinson’s disease are an unmet clinical need. Intraretinal layer thicknesses on macular optical coherence tomography (OCT) images are promising noninvasive biomarkers querying neuroretinal structures with near cellular resolution. However, changes are typically subtle, while tissue gradients can be weak, making intraretinal segmentation a challenging task. A robust and efficient method that requires no or minimal manual correction is an unmet need to foster reliable and reproducible research as well as clinical application. Here, we propose and validate a cascaded two-stage network for intraretinal layer segmentation, with both networks being compressed versions of U-Net (CCU-INSEG). The first network is responsible for retinal tissue segmentation from OCT B-scans. The second network segments eight intraretinal layers with high fidelity. At the post-processing stage, we introduce Laplacian-based outlier detection with layer surface hole filling by adaptive non-linear interpolation. Additionally, we propose a weighted version of focal loss to minimize the foreground–background pixel imbalance in the training data. We train our method using 17,458 B-scans from patients with autoimmune optic neuropathies, i.e., multiple sclerosis, and healthy controls. Voxel-wise comparison against manual segmentation produces a mean absolute error of 2.3 μm, outperforming current state-of-the-art methods on the same data set. Voxel-wise comparison against external glaucoma data leads to a mean absolute error of 2.6 μm when using the same gold standard segmentation approach, and 3.7 μm mean absolute error in an externally segmented data set. In scans from patients with severe optic atrophy, 3.5% of B-scan segmentation results were rejected by an experienced grader, whereas this was the case in 41.4% of B-scans segmented with a graph-based reference method. The validation results suggest that the proposed method can robustly segment macular scans from eyes with even severe neuroretinal changes. MDPI 2022-05-17 /pmc/articles/PMC9146486/ /pubmed/35621903 http://dx.doi.org/10.3390/jimaging8050139 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Yadav, Sunil Kumar Kafieh, Rahele Zimmermann, Hanna Gwendolyn Kauer-Bonin, Josef Nouri-Mahdavi, Kouros Mohammadzadeh, Vahid Shi, Lynn Kadas, Ella Maria Paul, Friedemann Motamedi, Seyedamirhosein Brandt, Alexander Ulrich Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets |
title | Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets |
title_full | Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets |
title_fullStr | Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets |
title_full_unstemmed | Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets |
title_short | Intraretinal Layer Segmentation Using Cascaded Compressed U-Nets |
title_sort | intraretinal layer segmentation using cascaded compressed u-nets |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9146486/ https://www.ncbi.nlm.nih.gov/pubmed/35621903 http://dx.doi.org/10.3390/jimaging8050139 |
work_keys_str_mv | AT yadavsunilkumar intraretinallayersegmentationusingcascadedcompressedunets AT kafiehrahele intraretinallayersegmentationusingcascadedcompressedunets AT zimmermannhannagwendolyn intraretinallayersegmentationusingcascadedcompressedunets AT kauerboninjosef intraretinallayersegmentationusingcascadedcompressedunets AT nourimahdavikouros intraretinallayersegmentationusingcascadedcompressedunets AT mohammadzadehvahid intraretinallayersegmentationusingcascadedcompressedunets AT shilynn intraretinallayersegmentationusingcascadedcompressedunets AT kadasellamaria intraretinallayersegmentationusingcascadedcompressedunets AT paulfriedemann intraretinallayersegmentationusingcascadedcompressedunets AT motamediseyedamirhosein intraretinallayersegmentationusingcascadedcompressedunets AT brandtalexanderulrich intraretinallayersegmentationusingcascadedcompressedunets |