A comprehensive testing protocol for MRI neuroanatomical segmentation techniques: Evaluation of a novel lateral ventricle segmentation method

Kempton, Matthew J.; Underwood, Tracy; Brunton, Simon; Stylios, F.; Schmechtig, Anne; Ettinger, Ulrich; Smith, Miles H.; Lovestone, Simon; Crum, William R.; Frangou, Sophia; Williams, Steven; Simmons, Andrew

doi:10.1016/j.neuroimage.2011.06.080

Cited by 114 publications

(108 citation statements)

References 52 publications

Supporting

Mentioning

104

Contrasting

Unclassified

Order By: Relevance

“…The assumption is that brains of healthy subjects do not change substantially within short periods. ICC is widely used to quantify test-retest reliability (Kempton et al, 2011;Nugent et al, 2013).…”

Section: Test-retest Reliabilitymentioning

confidence: 99%

Robust whole-brain segmentation: Application to traumatic brain injury

Ledig

Heckemann

Hammers

et al. 2015

Medical Image Analysis

162

155

View full text Add to dashboard Cite

We propose a framework for the robust and fully-automatic segmentation of magnetic resonance (MR) brain images called "Multi-Atlas Label Propagation with Expectation-Maximisation based refinement" (MALP-EM). The presented approach is based on a robust registration approach (MAPER), highly performant label fusion (joint label fusion) and intensity-based label refinement using EM. We further adapt this framework to be applicable for the segmentation of brain images with gross changes in anatomy. We propose to account for consistent registration errors by relaxing anatomical priors obtained by multi-atlas propagation and a weighting scheme to locally combine anatomical atlas priors and intensity-refined posterior probabilities. The method is evaluated on a benchmark dataset used in a recent MICCAI segmentation challenge. In this context we show that MALP-EM is competitive for the segmentation of MR brain scans of healthy adults when compared to state-of-the-art automatic labelling techniques. To demonstrate the versatility of the proposed approach, we employed MALP-EM to segment 125 MR brain images into 134 regions from subjects who had sustained traumatic brain injury (TBI). We employ a protocol to assess segmentation quality if no manual reference labels are available. Based on this protocol, three independent, blinded raters confirmed on 13 MR brain scans with pathology that MALP-EM is superior to established label fusion techniques. We visually confirm the robustness of our segmentation approach on the full cohort and investigate the potential of derived symmetry-based imaging biomarkers that correlate with and predict clinically relevant variables in TBI such as the Marshall Classification (MC) or Glasgow Outcome Score (GOS). Specifically, we show that we are able to stratify TBI patients with favourable outcomes from non-favourable outcomes with 64.7% accuracy using acute-phase MR images and 66.8% accuracy using follow-up MR images. Furthermore, we are able to differentiate subjects with the presence of a mass lesion or midline shift from those with diffuse brain injury with 76.0% accuracy. The thalamus, putamen, pallidum and hippocampus are particularly affected. Their involvement predicts TBI disease progression.

show abstract

Section: Test-retest Reliabilitymentioning

confidence: 99%

Robust whole-brain segmentation: Application to traumatic brain injury

Ledig

Heckemann

Hammers

et al. 2015

Medical Image Analysis

162

155

View full text Add to dashboard Cite

show abstract

“…23 Briefly, the SPMmodulated, normalized cerebrospinal fluid segmentation outputs for each participant were multiplied with a mask of the lateral ventricles created from 275 healthy individuals aged 18-94 years. This automated approach has been shown to be reliable in elderly individuals, with an interclass correlation coefficient of 0.97 compared with manual segmentations.…”

Section: Determining Lateral Ventricular Volumementioning

confidence: 99%

“…This automated approach has been shown to be reliable in elderly individuals, with an interclass correlation coefficient of 0.97 compared with manual segmentations. 23 …”

Section: Determining Lateral Ventricular Volumementioning

confidence: 99%

Grey matter volume increase following electroconvulsive therapy in patients with late life depression: a longitudinal MRI study

Bouckaert

Winter

Emsell

et al. 2016

jpn

View full text Add to dashboard Cite

“…Ventricular CSF: To avoid errors due to partial volume near the edges of the brain, voxels used to compute the CSF reference signal were limited to the ventricles, which were automatically segmented on the IR TI = 1500 ms or 3500 ms images using the ALVIN 1.06 program [46]. CSF voxels were then further limited to remove those that demonstrated major flow effects and partial volume by imposing a threshold for sum of squares of the T 2 fit and eliminating voxels with a "CSF fraction" (fraction of signal with T 2 N 600 ms) b 99%.…”

Section: Normalization To a Pure Water Standardmentioning

confidence: 99%