A comparison of manual and automated neural architecture search for white matter tract segmentation
Abstract Segmentation of white matter tracts in diffusion magnetic resonance images is an important first step in many imaging studies of the brain in health and disease. Similar to medical image segmentation in general, a popular approach to white matter tract segmentation is to use U-Net based art...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2023-01-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-023-28210-1 |
_version_ | 1811175892864466944 |
---|---|
author | Ari Tchetchenian Yanming Zhu Fan Zhang Lauren J. O’Donnell Yang Song Erik Meijering |
author_facet | Ari Tchetchenian Yanming Zhu Fan Zhang Lauren J. O’Donnell Yang Song Erik Meijering |
author_sort | Ari Tchetchenian |
collection | DOAJ |
description | Abstract Segmentation of white matter tracts in diffusion magnetic resonance images is an important first step in many imaging studies of the brain in health and disease. Similar to medical image segmentation in general, a popular approach to white matter tract segmentation is to use U-Net based artificial neural network architectures. Despite many suggested improvements to the U-Net architecture in recent years, there is a lack of systematic comparison of architectural variants for white matter tract segmentation. In this paper, we evaluate multiple U-Net based architectures specifically for this purpose. We compare the results of these networks to those achieved by our own various architecture changes, as well as to new U-Net architectures designed automatically via neural architecture search (NAS). To the best of our knowledge, this is the first study to systematically compare multiple U-Net based architectures for white matter tract segmentation, and the first to use NAS. We find that the recently proposed medical imaging segmentation network UNet3+ slightly outperforms the current state of the art for white matter tract segmentation, and achieves a notably better mean Dice score for segmentation of the fornix (+ 0.01 and + 0.006 mean Dice increase for left and right fornix respectively), a tract that the current state of the art model struggles to segment. UNet3+ also outperforms the current state of the art when little training data is available. Additionally, manual architecture search found that a minor segmentation improvement is observed when an additional, deeper layer is added to the U-shape of UNet3+. However, all networks, including those designed via NAS, achieve similar results, suggesting that there may be benefit in exploring networks that deviate from the general U-Net paradigm. |
first_indexed | 2024-04-10T19:43:21Z |
format | Article |
id | doaj.art-a8b4be1780504122958ad5eac839cd70 |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-10T19:43:21Z |
publishDate | 2023-01-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-a8b4be1780504122958ad5eac839cd702023-01-29T12:10:32ZengNature PortfolioScientific Reports2045-23222023-01-0113111710.1038/s41598-023-28210-1A comparison of manual and automated neural architecture search for white matter tract segmentationAri Tchetchenian0Yanming Zhu1Fan Zhang2Lauren J. O’Donnell3Yang Song4Erik Meijering5Biomedical Image Computing Group, School of Computer Science and Engineering, University of New South Wales (UNSW)Biomedical Image Computing Group, School of Computer Science and Engineering, University of New South Wales (UNSW)Brigham and Women’s Hospital, Harvard Medical SchoolBrigham and Women’s Hospital, Harvard Medical SchoolBiomedical Image Computing Group, School of Computer Science and Engineering, University of New South Wales (UNSW)Biomedical Image Computing Group, School of Computer Science and Engineering, University of New South Wales (UNSW)Abstract Segmentation of white matter tracts in diffusion magnetic resonance images is an important first step in many imaging studies of the brain in health and disease. Similar to medical image segmentation in general, a popular approach to white matter tract segmentation is to use U-Net based artificial neural network architectures. Despite many suggested improvements to the U-Net architecture in recent years, there is a lack of systematic comparison of architectural variants for white matter tract segmentation. In this paper, we evaluate multiple U-Net based architectures specifically for this purpose. We compare the results of these networks to those achieved by our own various architecture changes, as well as to new U-Net architectures designed automatically via neural architecture search (NAS). To the best of our knowledge, this is the first study to systematically compare multiple U-Net based architectures for white matter tract segmentation, and the first to use NAS. We find that the recently proposed medical imaging segmentation network UNet3+ slightly outperforms the current state of the art for white matter tract segmentation, and achieves a notably better mean Dice score for segmentation of the fornix (+ 0.01 and + 0.006 mean Dice increase for left and right fornix respectively), a tract that the current state of the art model struggles to segment. UNet3+ also outperforms the current state of the art when little training data is available. Additionally, manual architecture search found that a minor segmentation improvement is observed when an additional, deeper layer is added to the U-shape of UNet3+. However, all networks, including those designed via NAS, achieve similar results, suggesting that there may be benefit in exploring networks that deviate from the general U-Net paradigm.https://doi.org/10.1038/s41598-023-28210-1 |
spellingShingle | Ari Tchetchenian Yanming Zhu Fan Zhang Lauren J. O’Donnell Yang Song Erik Meijering A comparison of manual and automated neural architecture search for white matter tract segmentation Scientific Reports |
title | A comparison of manual and automated neural architecture search for white matter tract segmentation |
title_full | A comparison of manual and automated neural architecture search for white matter tract segmentation |
title_fullStr | A comparison of manual and automated neural architecture search for white matter tract segmentation |
title_full_unstemmed | A comparison of manual and automated neural architecture search for white matter tract segmentation |
title_short | A comparison of manual and automated neural architecture search for white matter tract segmentation |
title_sort | comparison of manual and automated neural architecture search for white matter tract segmentation |
url | https://doi.org/10.1038/s41598-023-28210-1 |
work_keys_str_mv | AT aritchetchenian acomparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT yanmingzhu acomparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT fanzhang acomparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT laurenjodonnell acomparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT yangsong acomparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT erikmeijering acomparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT aritchetchenian comparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT yanmingzhu comparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT fanzhang comparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT laurenjodonnell comparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT yangsong comparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation AT erikmeijering comparisonofmanualandautomatedneuralarchitecturesearchforwhitemattertractsegmentation |