Automated segmentation of haematoma and perihaematomal oedema in MRI of acute spontaneous intracerebral haemorrhage

Stefan Pszczolkowski, Zhe Kang Law, Rebecca G. Gallagher, Dewen Meng, David J. Swienton, Paul S. Morgan, Philip M. Bath, Nikola Sprigg, Rob A. Dineen

Research output: Contribution to journalArticle

Abstract

Background: Spontaneous intracerebral haemorrhage (SICH) is a common condition with high morbidity and mortality. Segmentation of haematoma and perihaematoma oedema on medical images provides quantitative outcome measures for clinical trials and may provide important markers of prognosis in people with SICH. Methods: We take advantage of improved contrast seen on magnetic resonance (MR) images of patients with acute and early subacute SICH and introduce an automated algorithm for haematoma and oedema segmentation from these images. To our knowledge, there is no previously proposed segmentation technique for SICH that utilises MR images directly. The method is based on shape and intensity analysis for haematoma segmentation and voxel-wise dynamic thresholding of hyper-intensities for oedema segmentation. Results: Using Dice scores to measure segmentation overlaps between labellings yielded by the proposed algorithm and five different expert raters on 18 patients, we observe that our technique achieves overlap scores that are very similar to those obtained by pairwise expert rater comparison. A further comparison between the proposed method and a state-of-the-art Deep Learning segmentation on a separate set of 32 manually annotated subjects confirms the proposed method can achieve comparable results with very mild computational burden and in a completely training-free and unsupervised way. Conclusion: Our technique can be a computationally light and effective way to automatically delineate haematoma and oedema extent directly from MR images. Thus, with increasing use of MR images clinically after intracerebral haemorrhage this technique has the potential to inform clinical practice in the future.

Original languageEnglish
Pages (from-to)126-139
Number of pages14
JournalComputers in Biology and Medicine
Volume106
DOIs
Publication statusPublished - 1 Mar 2019

Fingerprint

Cerebral Hemorrhage
Magnetic resonance
Hematoma
Magnetic resonance imaging
Edema
Magnetic Resonance Spectroscopy
Outcome Assessment (Health Care)
Clinical Trials
Learning
Morbidity
Light
Mortality

Keywords

  • Brain MRI
  • Image segmentation
  • Spontaneous intracerebral haemorrhage
  • Stroke

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Automated segmentation of haematoma and perihaematomal oedema in MRI of acute spontaneous intracerebral haemorrhage. / Pszczolkowski, Stefan; Law, Zhe Kang; Gallagher, Rebecca G.; Meng, Dewen; Swienton, David J.; Morgan, Paul S.; Bath, Philip M.; Sprigg, Nikola; Dineen, Rob A.

In: Computers in Biology and Medicine, Vol. 106, 01.03.2019, p. 126-139.

Research output: Contribution to journalArticle

Pszczolkowski, Stefan ; Law, Zhe Kang ; Gallagher, Rebecca G. ; Meng, Dewen ; Swienton, David J. ; Morgan, Paul S. ; Bath, Philip M. ; Sprigg, Nikola ; Dineen, Rob A. / Automated segmentation of haematoma and perihaematomal oedema in MRI of acute spontaneous intracerebral haemorrhage. In: Computers in Biology and Medicine. 2019 ; Vol. 106. pp. 126-139.
@article{5439c5ee13824ab9aa6a6219ca2f53ef,
title = "Automated segmentation of haematoma and perihaematomal oedema in MRI of acute spontaneous intracerebral haemorrhage",
abstract = "Background: Spontaneous intracerebral haemorrhage (SICH) is a common condition with high morbidity and mortality. Segmentation of haematoma and perihaematoma oedema on medical images provides quantitative outcome measures for clinical trials and may provide important markers of prognosis in people with SICH. Methods: We take advantage of improved contrast seen on magnetic resonance (MR) images of patients with acute and early subacute SICH and introduce an automated algorithm for haematoma and oedema segmentation from these images. To our knowledge, there is no previously proposed segmentation technique for SICH that utilises MR images directly. The method is based on shape and intensity analysis for haematoma segmentation and voxel-wise dynamic thresholding of hyper-intensities for oedema segmentation. Results: Using Dice scores to measure segmentation overlaps between labellings yielded by the proposed algorithm and five different expert raters on 18 patients, we observe that our technique achieves overlap scores that are very similar to those obtained by pairwise expert rater comparison. A further comparison between the proposed method and a state-of-the-art Deep Learning segmentation on a separate set of 32 manually annotated subjects confirms the proposed method can achieve comparable results with very mild computational burden and in a completely training-free and unsupervised way. Conclusion: Our technique can be a computationally light and effective way to automatically delineate haematoma and oedema extent directly from MR images. Thus, with increasing use of MR images clinically after intracerebral haemorrhage this technique has the potential to inform clinical practice in the future.",
keywords = "Brain MRI, Image segmentation, Spontaneous intracerebral haemorrhage, Stroke",
author = "Stefan Pszczolkowski and Law, {Zhe Kang} and Gallagher, {Rebecca G.} and Dewen Meng and Swienton, {David J.} and Morgan, {Paul S.} and Bath, {Philip M.} and Nikola Sprigg and Dineen, {Rob A.}",
year = "2019",
month = "3",
day = "1",
doi = "10.1016/j.compbiomed.2019.01.022",
language = "English",
volume = "106",
pages = "126--139",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Automated segmentation of haematoma and perihaematomal oedema in MRI of acute spontaneous intracerebral haemorrhage

AU - Pszczolkowski, Stefan

AU - Law, Zhe Kang

AU - Gallagher, Rebecca G.

AU - Meng, Dewen

AU - Swienton, David J.

AU - Morgan, Paul S.

AU - Bath, Philip M.

AU - Sprigg, Nikola

AU - Dineen, Rob A.

PY - 2019/3/1

Y1 - 2019/3/1

N2 - Background: Spontaneous intracerebral haemorrhage (SICH) is a common condition with high morbidity and mortality. Segmentation of haematoma and perihaematoma oedema on medical images provides quantitative outcome measures for clinical trials and may provide important markers of prognosis in people with SICH. Methods: We take advantage of improved contrast seen on magnetic resonance (MR) images of patients with acute and early subacute SICH and introduce an automated algorithm for haematoma and oedema segmentation from these images. To our knowledge, there is no previously proposed segmentation technique for SICH that utilises MR images directly. The method is based on shape and intensity analysis for haematoma segmentation and voxel-wise dynamic thresholding of hyper-intensities for oedema segmentation. Results: Using Dice scores to measure segmentation overlaps between labellings yielded by the proposed algorithm and five different expert raters on 18 patients, we observe that our technique achieves overlap scores that are very similar to those obtained by pairwise expert rater comparison. A further comparison between the proposed method and a state-of-the-art Deep Learning segmentation on a separate set of 32 manually annotated subjects confirms the proposed method can achieve comparable results with very mild computational burden and in a completely training-free and unsupervised way. Conclusion: Our technique can be a computationally light and effective way to automatically delineate haematoma and oedema extent directly from MR images. Thus, with increasing use of MR images clinically after intracerebral haemorrhage this technique has the potential to inform clinical practice in the future.

AB - Background: Spontaneous intracerebral haemorrhage (SICH) is a common condition with high morbidity and mortality. Segmentation of haematoma and perihaematoma oedema on medical images provides quantitative outcome measures for clinical trials and may provide important markers of prognosis in people with SICH. Methods: We take advantage of improved contrast seen on magnetic resonance (MR) images of patients with acute and early subacute SICH and introduce an automated algorithm for haematoma and oedema segmentation from these images. To our knowledge, there is no previously proposed segmentation technique for SICH that utilises MR images directly. The method is based on shape and intensity analysis for haematoma segmentation and voxel-wise dynamic thresholding of hyper-intensities for oedema segmentation. Results: Using Dice scores to measure segmentation overlaps between labellings yielded by the proposed algorithm and five different expert raters on 18 patients, we observe that our technique achieves overlap scores that are very similar to those obtained by pairwise expert rater comparison. A further comparison between the proposed method and a state-of-the-art Deep Learning segmentation on a separate set of 32 manually annotated subjects confirms the proposed method can achieve comparable results with very mild computational burden and in a completely training-free and unsupervised way. Conclusion: Our technique can be a computationally light and effective way to automatically delineate haematoma and oedema extent directly from MR images. Thus, with increasing use of MR images clinically after intracerebral haemorrhage this technique has the potential to inform clinical practice in the future.

KW - Brain MRI

KW - Image segmentation

KW - Spontaneous intracerebral haemorrhage

KW - Stroke

UR - http://www.scopus.com/inward/record.url?scp=85060866485&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060866485&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2019.01.022

DO - 10.1016/j.compbiomed.2019.01.022

M3 - Article

C2 - 30711800

AN - SCOPUS:85060866485

VL - 106

SP - 126

EP - 139

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -