Consistent and robust 4D whole-brain segmentation

Application to traumatic brain injury

Christian Ledig, Wenzhe Shi, Antonious Makropoulos, Juha Koikkalainen, Rolf A. Heckemann, Alexander Hammers, Jyrki Lötjönen, Olli Tenovuo, Daniel Rueckert

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

2 Citations (Scopus)

Abstract

We propose a consistent approach to automatically segmenting longitudinal magnetic resonance scans of pathological brains. Using symmetric intra-subject registration, we align corresponding scans. In an expectation-maximization framework we exploit the availability of probabilistic segmentation estimates to perform a symmetric intensity normalisation. We introduce a novel technique to perform symmetric differential bias correction for images in presence of pathologies. To achieve a consistent multi-time-point segmentation, we propose a patch-based coupling term using a spatially and temporally varying Markov random field. We demonstrate the superior consistency of our method by segmenting repeat scans into 134 regions. Furthermore, the approach has been applied to segment baseline and six month follow-up scans from 56 patients who have sustained traumatic brain injury (TBI). We find significant correlations between regional atrophy rates and clinical outcome: Patients with poor outcome showed a much higher thalamic atrophy rate (4.9 ± 3.4%) than patients with favourable outcome (0.6 ± 1.9%).
Original languageEnglish
Title of host publicationIEEE 11th International Symposium on Biomedical Imaging, ISBI 2014
PublisherInstitute of Electrical and Electronic Engineers IEEE
Pages673-676
ISBN (Electronic)978-1-4673-1961-4
ISBN (Print)978-1-4673-1959-1
DOIs
Publication statusPublished - 2014
MoE publication typeA4 Article in a conference publication
Event11th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2014 - Peking, China
Duration: 29 Apr 20142 May 2014

Conference

Conference11th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2014
Abbreviated titleISBI 2014
CountryChina
CityPeking
Period29/04/142/05/14

Fingerprint

Atrophy
Brain
Magnetic Resonance Spectroscopy
Pathology
Traumatic Brain Injury

Keywords

  • brain MRI
  • longitudinal segmentation
  • EM optimisation
  • temporal consistency
  • traumatic brain injury

Cite this

Ledig, C., Shi, W., Makropoulos, A., Koikkalainen, J., Heckemann, R. A., Hammers, A., ... Rueckert, D. (2014). Consistent and robust 4D whole-brain segmentation: Application to traumatic brain injury. In IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014 (pp. 673-676). Institute of Electrical and Electronic Engineers IEEE. https://doi.org/10.1109/ISBI.2014.6867960
Ledig, Christian ; Shi, Wenzhe ; Makropoulos, Antonious ; Koikkalainen, Juha ; Heckemann, Rolf A. ; Hammers, Alexander ; Lötjönen, Jyrki ; Tenovuo, Olli ; Rueckert, Daniel. / Consistent and robust 4D whole-brain segmentation : Application to traumatic brain injury. IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronic Engineers IEEE, 2014. pp. 673-676
@inproceedings{d02a74ff6584474495ed03b7df0fd2b4,
title = "Consistent and robust 4D whole-brain segmentation: Application to traumatic brain injury",
abstract = "We propose a consistent approach to automatically segmenting longitudinal magnetic resonance scans of pathological brains. Using symmetric intra-subject registration, we align corresponding scans. In an expectation-maximization framework we exploit the availability of probabilistic segmentation estimates to perform a symmetric intensity normalisation. We introduce a novel technique to perform symmetric differential bias correction for images in presence of pathologies. To achieve a consistent multi-time-point segmentation, we propose a patch-based coupling term using a spatially and temporally varying Markov random field. We demonstrate the superior consistency of our method by segmenting repeat scans into 134 regions. Furthermore, the approach has been applied to segment baseline and six month follow-up scans from 56 patients who have sustained traumatic brain injury (TBI). We find significant correlations between regional atrophy rates and clinical outcome: Patients with poor outcome showed a much higher thalamic atrophy rate (4.9 ± 3.4{\%}) than patients with favourable outcome (0.6 ± 1.9{\%}).",
keywords = "brain MRI, longitudinal segmentation, EM optimisation, temporal consistency, traumatic brain injury",
author = "Christian Ledig and Wenzhe Shi and Antonious Makropoulos and Juha Koikkalainen and Heckemann, {Rolf A.} and Alexander Hammers and Jyrki L{\"o}tj{\"o}nen and Olli Tenovuo and Daniel Rueckert",
note = "Project code: 70554",
year = "2014",
doi = "10.1109/ISBI.2014.6867960",
language = "English",
isbn = "978-1-4673-1959-1",
pages = "673--676",
booktitle = "IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014",
publisher = "Institute of Electrical and Electronic Engineers IEEE",
address = "United States",

}

Ledig, C, Shi, W, Makropoulos, A, Koikkalainen, J, Heckemann, RA, Hammers, A, Lötjönen, J, Tenovuo, O & Rueckert, D 2014, Consistent and robust 4D whole-brain segmentation: Application to traumatic brain injury. in IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronic Engineers IEEE, pp. 673-676, 11th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2014, Peking, China, 29/04/14. https://doi.org/10.1109/ISBI.2014.6867960

Consistent and robust 4D whole-brain segmentation : Application to traumatic brain injury. / Ledig, Christian; Shi, Wenzhe; Makropoulos, Antonious; Koikkalainen, Juha; Heckemann, Rolf A.; Hammers, Alexander; Lötjönen, Jyrki; Tenovuo, Olli; Rueckert, Daniel.

IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronic Engineers IEEE, 2014. p. 673-676.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Consistent and robust 4D whole-brain segmentation

T2 - Application to traumatic brain injury

AU - Ledig, Christian

AU - Shi, Wenzhe

AU - Makropoulos, Antonious

AU - Koikkalainen, Juha

AU - Heckemann, Rolf A.

AU - Hammers, Alexander

AU - Lötjönen, Jyrki

AU - Tenovuo, Olli

AU - Rueckert, Daniel

N1 - Project code: 70554

PY - 2014

Y1 - 2014

N2 - We propose a consistent approach to automatically segmenting longitudinal magnetic resonance scans of pathological brains. Using symmetric intra-subject registration, we align corresponding scans. In an expectation-maximization framework we exploit the availability of probabilistic segmentation estimates to perform a symmetric intensity normalisation. We introduce a novel technique to perform symmetric differential bias correction for images in presence of pathologies. To achieve a consistent multi-time-point segmentation, we propose a patch-based coupling term using a spatially and temporally varying Markov random field. We demonstrate the superior consistency of our method by segmenting repeat scans into 134 regions. Furthermore, the approach has been applied to segment baseline and six month follow-up scans from 56 patients who have sustained traumatic brain injury (TBI). We find significant correlations between regional atrophy rates and clinical outcome: Patients with poor outcome showed a much higher thalamic atrophy rate (4.9 ± 3.4%) than patients with favourable outcome (0.6 ± 1.9%).

AB - We propose a consistent approach to automatically segmenting longitudinal magnetic resonance scans of pathological brains. Using symmetric intra-subject registration, we align corresponding scans. In an expectation-maximization framework we exploit the availability of probabilistic segmentation estimates to perform a symmetric intensity normalisation. We introduce a novel technique to perform symmetric differential bias correction for images in presence of pathologies. To achieve a consistent multi-time-point segmentation, we propose a patch-based coupling term using a spatially and temporally varying Markov random field. We demonstrate the superior consistency of our method by segmenting repeat scans into 134 regions. Furthermore, the approach has been applied to segment baseline and six month follow-up scans from 56 patients who have sustained traumatic brain injury (TBI). We find significant correlations between regional atrophy rates and clinical outcome: Patients with poor outcome showed a much higher thalamic atrophy rate (4.9 ± 3.4%) than patients with favourable outcome (0.6 ± 1.9%).

KW - brain MRI

KW - longitudinal segmentation

KW - EM optimisation

KW - temporal consistency

KW - traumatic brain injury

U2 - 10.1109/ISBI.2014.6867960

DO - 10.1109/ISBI.2014.6867960

M3 - Conference article in proceedings

SN - 978-1-4673-1959-1

SP - 673

EP - 676

BT - IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014

PB - Institute of Electrical and Electronic Engineers IEEE

ER -

Ledig C, Shi W, Makropoulos A, Koikkalainen J, Heckemann RA, Hammers A et al. Consistent and robust 4D whole-brain segmentation: Application to traumatic brain injury. In IEEE 11th International Symposium on Biomedical Imaging, ISBI 2014. Institute of Electrical and Electronic Engineers IEEE. 2014. p. 673-676 https://doi.org/10.1109/ISBI.2014.6867960