Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Deep learning from MRI-derived labels enables automatic brain tissue classification on human brain CT

Srikrishna, Meera ; Pereira, Joana B. LU ; Heckemann, Rolf A. ; Volpe, Giovanni ; van Westen, Danielle LU orcid ; Zettergren, Anna ; Kern, Silke ; Wahlund, Lars Olof ; Westman, Eric and Skoog, Ingmar , et al. (2021) In NeuroImage 244.
Abstract

Automatic methods for feature extraction, volumetry, and morphometric analysis in clinical neuroscience typically operate on images obtained with magnetic resonance (MR) imaging equipment. Although CT scans are less expensive to acquire and more widely available than MR scans, their application is currently limited to the visual assessment of brain integrity and the exclusion of co-pathologies. CT has rarely been used for tissue classification because the contrast between grey matter and white matter was considered insufficient. In this study, we propose an automatic method for segmenting grey matter (GM), white matter (WM), cerebrospinal fluid (CSF), and intracranial volume (ICV) from head CT images. A U-Net deep learning model was... (More)

Automatic methods for feature extraction, volumetry, and morphometric analysis in clinical neuroscience typically operate on images obtained with magnetic resonance (MR) imaging equipment. Although CT scans are less expensive to acquire and more widely available than MR scans, their application is currently limited to the visual assessment of brain integrity and the exclusion of co-pathologies. CT has rarely been used for tissue classification because the contrast between grey matter and white matter was considered insufficient. In this study, we propose an automatic method for segmenting grey matter (GM), white matter (WM), cerebrospinal fluid (CSF), and intracranial volume (ICV) from head CT images. A U-Net deep learning model was trained and validated on CT images with MRI-derived segmentation labels. We used data from 744 participants of the Gothenburg H70 Birth Cohort Studies for whom CT and T1-weighted MR images had been acquired on the same day. Our proposed model predicted brain tissue classes accurately from unseen CT images (Dice coefficients of 0.79, 0.82, 0.75, 0.93 and 0.98 for GM, WM, CSF, brain volume and ICV, respectively). To contextualize these results, we generated benchmarks based on established MR-based methods and intentional image degradation. Our findings demonstrate that CT-derived segmentations can be used to delineate and quantify brain tissues, opening new possibilities for the use of CT in clinical practice and research.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Brain image segmentation, computed tomography (CT), Convolutional neural networks (CNN), Deep learning
in
NeuroImage
volume
244
article number
118606
publisher
Elsevier
external identifiers
  • pmid:34571160
  • scopus:85116037187
ISSN
1053-8119
DOI
10.1016/j.neuroimage.2021.118606
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2021 The Author(s)
id
4d990f0f-8a75-484c-bee8-17e21317e4a1
date added to LUP
2021-10-19 11:16:00
date last changed
2024-04-20 13:18:26
@article{4d990f0f-8a75-484c-bee8-17e21317e4a1,
  abstract     = {{<p>Automatic methods for feature extraction, volumetry, and morphometric analysis in clinical neuroscience typically operate on images obtained with magnetic resonance (MR) imaging equipment. Although CT scans are less expensive to acquire and more widely available than MR scans, their application is currently limited to the visual assessment of brain integrity and the exclusion of co-pathologies. CT has rarely been used for tissue classification because the contrast between grey matter and white matter was considered insufficient. In this study, we propose an automatic method for segmenting grey matter (GM), white matter (WM), cerebrospinal fluid (CSF), and intracranial volume (ICV) from head CT images. A U-Net deep learning model was trained and validated on CT images with MRI-derived segmentation labels. We used data from 744 participants of the Gothenburg H70 Birth Cohort Studies for whom CT and T1-weighted MR images had been acquired on the same day. Our proposed model predicted brain tissue classes accurately from unseen CT images (Dice coefficients of 0.79, 0.82, 0.75, 0.93 and 0.98 for GM, WM, CSF, brain volume and ICV, respectively). To contextualize these results, we generated benchmarks based on established MR-based methods and intentional image degradation. Our findings demonstrate that CT-derived segmentations can be used to delineate and quantify brain tissues, opening new possibilities for the use of CT in clinical practice and research.</p>}},
  author       = {{Srikrishna, Meera and Pereira, Joana B. and Heckemann, Rolf A. and Volpe, Giovanni and van Westen, Danielle and Zettergren, Anna and Kern, Silke and Wahlund, Lars Olof and Westman, Eric and Skoog, Ingmar and Schöll, Michael}},
  issn         = {{1053-8119}},
  keywords     = {{Brain image segmentation; computed tomography (CT); Convolutional neural networks (CNN); Deep learning}},
  language     = {{eng}},
  publisher    = {{Elsevier}},
  series       = {{NeuroImage}},
  title        = {{Deep learning from MRI-derived labels enables automatic brain tissue classification on human brain CT}},
  url          = {{http://dx.doi.org/10.1016/j.neuroimage.2021.118606}},
  doi          = {{10.1016/j.neuroimage.2021.118606}},
  volume       = {{244}},
  year         = {{2021}},
}