Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Comparison of Two-Dimensional- and Three-Dimensional-Based U-Net Architectures for Brain Tissue Classification in One-Dimensional Brain CT

Srikrishna, Meera ; Heckemann, Rolf A. ; Pereira, Joana B. LU ; Volpe, Giovanni ; Zettergren, Anna ; Kern, Silke ; Westman, Eric ; Skoog, Ingmar and Schöll, Michael LU (2022) In Frontiers in Computational Neuroscience 15.
Abstract

Brain tissue segmentation plays a crucial role in feature extraction, volumetric quantification, and morphometric analysis of brain scans. For the assessment of brain structure and integrity, CT is a non-invasive, cheaper, faster, and more widely available modality than MRI. However, the clinical application of CT is mostly limited to the visual assessment of brain integrity and exclusion of copathologies. We have previously developed two-dimensional (2D) deep learning-based segmentation networks that successfully classified brain tissue in head CT. Recently, deep learning-based MRI segmentation models successfully use patch-based three-dimensional (3D) segmentation networks. In this study, we aimed to develop patch-based 3D... (More)

Brain tissue segmentation plays a crucial role in feature extraction, volumetric quantification, and morphometric analysis of brain scans. For the assessment of brain structure and integrity, CT is a non-invasive, cheaper, faster, and more widely available modality than MRI. However, the clinical application of CT is mostly limited to the visual assessment of brain integrity and exclusion of copathologies. We have previously developed two-dimensional (2D) deep learning-based segmentation networks that successfully classified brain tissue in head CT. Recently, deep learning-based MRI segmentation models successfully use patch-based three-dimensional (3D) segmentation networks. In this study, we aimed to develop patch-based 3D segmentation networks for CT brain tissue classification. Furthermore, we aimed to compare the performance of 2D- and 3D-based segmentation networks to perform brain tissue classification in anisotropic CT scans. For this purpose, we developed 2D and 3D U-Net-based deep learning models that were trained and validated on MR-derived segmentations from scans of 744 participants of the Gothenburg H70 Cohort with both CT and T1-weighted MRI scans acquired timely close to each other. Segmentation performance of both 2D and 3D models was evaluated on 234 unseen datasets using measures of distance, spatial similarity, and tissue volume. Single-task slice-wise processed 2D U-Nets performed better than multitask patch-based 3D U-Nets in CT brain tissue classification. These findings provide support to the use of 2D U-Nets to segment brain tissue in one-dimensional (1D) CT. This could increase the application of CT to detect brain abnormalities in clinical settings.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
brain image segmentation, convolutional neural networks, CT, deep learning, MRI
in
Frontiers in Computational Neuroscience
volume
15
article number
785244
publisher
Frontiers Media S. A.
external identifiers
  • pmid:35082608
  • scopus:85123384309
ISSN
1662-5188
DOI
10.3389/fncom.2021.785244
language
English
LU publication?
yes
id
f8df6075-b3f5-415e-80e8-a62776e48f1e
date added to LUP
2022-03-18 15:32:28
date last changed
2024-12-14 07:55:52
@article{f8df6075-b3f5-415e-80e8-a62776e48f1e,
  abstract     = {{<p>Brain tissue segmentation plays a crucial role in feature extraction, volumetric quantification, and morphometric analysis of brain scans. For the assessment of brain structure and integrity, CT is a non-invasive, cheaper, faster, and more widely available modality than MRI. However, the clinical application of CT is mostly limited to the visual assessment of brain integrity and exclusion of copathologies. We have previously developed two-dimensional (2D) deep learning-based segmentation networks that successfully classified brain tissue in head CT. Recently, deep learning-based MRI segmentation models successfully use patch-based three-dimensional (3D) segmentation networks. In this study, we aimed to develop patch-based 3D segmentation networks for CT brain tissue classification. Furthermore, we aimed to compare the performance of 2D- and 3D-based segmentation networks to perform brain tissue classification in anisotropic CT scans. For this purpose, we developed 2D and 3D U-Net-based deep learning models that were trained and validated on MR-derived segmentations from scans of 744 participants of the Gothenburg H70 Cohort with both CT and T1-weighted MRI scans acquired timely close to each other. Segmentation performance of both 2D and 3D models was evaluated on 234 unseen datasets using measures of distance, spatial similarity, and tissue volume. Single-task slice-wise processed 2D U-Nets performed better than multitask patch-based 3D U-Nets in CT brain tissue classification. These findings provide support to the use of 2D U-Nets to segment brain tissue in one-dimensional (1D) CT. This could increase the application of CT to detect brain abnormalities in clinical settings.</p>}},
  author       = {{Srikrishna, Meera and Heckemann, Rolf A. and Pereira, Joana B. and Volpe, Giovanni and Zettergren, Anna and Kern, Silke and Westman, Eric and Skoog, Ingmar and Schöll, Michael}},
  issn         = {{1662-5188}},
  keywords     = {{brain image segmentation; convolutional neural networks; CT; deep learning; MRI}},
  language     = {{eng}},
  publisher    = {{Frontiers Media S. A.}},
  series       = {{Frontiers in Computational Neuroscience}},
  title        = {{Comparison of Two-Dimensional- and Three-Dimensional-Based U-Net Architectures for Brain Tissue Classification in One-Dimensional Brain CT}},
  url          = {{http://dx.doi.org/10.3389/fncom.2021.785244}},
  doi          = {{10.3389/fncom.2021.785244}},
  volume       = {{15}},
  year         = {{2022}},
}