Validated automatic brain extraction of head CT images

Abstract

Background X-ray Computed Tomography (CT) imaging of the brain is commonly used in diagnostic settings. Although CT scans are primarily used in clinical practice, they are increasingly used in research. A fundamental processing step in brain imaging research is brain extraction – the process of separating the brain tissue from all other tissues. Methods for brain extraction have either been 1) validated but not fully automated, or 2) fully automated and informally proposed, but never formally validated. Aim To systematically analyze and validate the performance of FSL's brain extraction tool (BET) on head CT images of patients with intracranial hemorrhage. This was done by comparing the manual gold standard with the results of several versions of automatic brain extraction and by estimating the reliability of automated segmentation of longitudinal scans. The effects of the choice of BET parameters and data smoothing is studied and reported. Methods All images were thresholded using a 0 – 100 Hounsfield units (HU) range. In one variant of the pipeline, data were smoothed using a 3-dimensional Gaussian kernel (σ = 1mm3) and re-thresholded to 0 – 100 HU; in the other, data were not smoothed. BET was applied using 1 of 3 fractional intensity (FI) thresholds: 0.01, 0.1, or 0.35 and any holes in the brain mask were filled. For validation against a manual segmentation, 36 images from patients with intracranial hemorrhage were selected from 19 different centers from the MISTIE (Minimally Invasive Surgery plus recombinant-tissue plasminogen activator for Intracerebral Evacuation) stroke trial. Intracranial masks of the brain were manually created by one expert CT reader. The resulting brain tissue masks were quantitatively compared to the manual segmentations using sensitivity, specificity, accuracy, and the Dice Similarity Index (DSI). Brain extraction performance across smoothing and FI thresholds was compared using the Wilcoxon signed-rank test. The intracranial volume (ICV) of each scan was estimated by multiplying the number of voxels in the brain mask by the dimensions of each voxel for that scan. From this, we calculated the ICV ratio comparing manual and automated segmentation: 1ICVautomatedICVmanual. To estimate the performance in a large number of scans, brain masks were generated from the 6 BET pipelines for 1095 longitudinal scans from 129 patients. Failure rates were estimated from visual inspection. ICV of each scan was estimated and and an intraclass correlation (ICC) was estimated using a one-way ANOVA. Results Smoothing images improves brain extraction results using BET for all measures except specificity (all p < 0.01, uncorrected), irrespective of the FI threshold. Using an FI of 0.01 or 0.1 performed better than 0.35. Thus, all reported results refer only to smoothed data using an FI of 0.01 or 0.1. Using an FI of 0.01 had a higher median sensitivity (0.9901) than an FI of 0.1 (0.9884, median difference: 0.0014, p < 0.001), accuracy (0.9971 vs. 0.9971; median difference: 0.0001, p < 0.001), and...

Intracranial Volume and Head Circumference in Children with Unoperated Syndromic Craniosynostosis

“…ICV was calculated automatically using FSL (Analysis Group, FMRIB, Oxford, UK) 21 . In those cases where the automatic technique failed to extract the entire cranial vault, a semiautomatic approach using Simpleware ScanIP (Simpleware Ltd., Exeter, UK) was adopted.…”

A Method to Estimate Brain Volume from Head CT Images and Application to Detect Brain Atrophy in Alzheimer Disease

“…This outcome was expected because the MR imaging-based default tissue probabilistic atlas map (TPM; https://www.fil.ion.ucl.ac.uk/spm/toolbox/TPM/) that we used did not model some of the anatomy present in CT images, and binarizing the masks by thresholding mitigated these errors. Additionally, the systematic bias in the TIV estimate using the binary masks was better than TIV estimated using the BET-based method by Muschelli et al 13 The utility of CTSeg was demonstrated in a cross-sectional dataset containing AD and control groups. We found that CTSeg-estimated volumes had a significant %TBV (P , .05) difference between the AD and control groups in a linear regression model with age, sex, and AD diagnosis as covariates.…”

“…24 The TIV estimates of CTSeg were also compared with the state-of-the-art FSL Brain Extraction Tool for CT (BET; http://bit.ly/CTBET_BASH). 13 CTSeg-estimated volumes from the images of age-matched subjects with AD and controls were used to compare brain atrophy between patients with AD and controls. Subjects with AD and controls were age-matched by minimizing the age difference using the MatchIt package 25 in R (https://www.rdocumentation.org/ packages/MatchIt/versions/3.0.2/topics/matchit).…”

“…5,9 Methods available for segmenting CT images to measure global volume metrics such as total intracrancial volume (TIV) and TBV from images with no detectable pathology were not formally validated. [10][11][12] Some wellvalidated methods segment only TIV 13,14 but not TBV. However, TBV is more indicative of disease conditions in neurodegenerative dieseases, 15 and TIV is used merely as a nuisance variable for normalization purposes.…”

High-resolution T2-FLAIR and non-contrast CT brain atlas of the elderly

“…The brain extraction is a six-step process, which was implemented using the Insight Segmentation and Registration Toolkit (ITK, https://itk.org/). The framework used for this follows the approach described by Muschelli et al 20 , but was implemented in a slice-by-slice fashion. Therefore, each slice of the scan is first smoothed using a Gaussian filter (variance = 4 pixels), intensity thresholded between 0 and 100 HU, and then eroded using a circular structuring element (radius = 1 pixel).…”