Evaluation of automated brain MR image segmentation and volumetry methods

Abstract

We compare three widely used brain volumetry methods available in the software packages FSL, SPM5, and FreeSurfer and evaluate their performance using simulated and real MR brain data sets. We analyze the accuracy of gray and white matter volume measurements and their robustness against changes of image quality using the BrainWeb MRI database. These images are based on "gold-standard" reference brain templates. This allows us to assess between- (same data set, different method) and also within-segmenter (same method, variation of image quality) comparability, for both of which we find pronounced variations in segmentation results for gray and white matter volumes. The calculated volumes deviate up to >10% from the reference values for gray and white matter depending on method and image quality. Sensitivity is best for SPM5, volumetric accuracy for gray and white matter was similar in SPM5 and FSL and better than in FreeSurfer. FSL showed the highest stability for white (<5%), FreeSurfer (6.2%) for gray matter for constant image quality BrainWeb data. Between-segmenter comparisons show discrepancies of up to >20% for the simulated data and 24% on average for the real data sets, whereas within-method performance analysis uncovered volume differences of up to >15%. Since the discrepancies between results reach the same order of magnitude as volume changes observed in disease, these effects limit the usability of the segmentation methods for following volume changes in individual patients over time and should be taken into account during the planning and analysis of brain volume studies.

Whole‐brain atrophy assessed by proportional‐ versus registration‐based pipelines from 3T MRI in multiple sclerosis

“…As prior authors have noted, the FSL BET can also be a significant source of error (Popescu et al., 2012; Zivadinov et al., 2005) and we found tissue misclassification in several subjects using the default settings; neck cropping and changing the default parameters (−f 0.2 and −B enabled) allowed an optimal solution for our dataset without any significant misclassification errors (Chu et al., 2016). Without any visually prominent errors, several groups have concluded that brain extraction methods are generally a very small source of variance (Clark, Woods, Rottenberg, Toga, & Mazziotta, 2006; Klauschen, Goldman, Barra, Meyer‐Lindenberg, & Lundervold, 2009) and we feel this preprocessing step is unlikely to be a significant source of variance between methods.…”

Mapping the Brain’s electric fields with Magnetoelectric nanoparticles

“…Brain segmentation (WM, GM, and CSF) of the template was performed using BrainSuite software (Klauschen et al, 2009). The finite element (FE) mesh required for the segmented brain was generated using Computer Geometry Algorithm Library (CGAL) according to previously described method (Lee et al, 2012).…”

A comparative study of automatic image segmentation algorithms for target tracking in MR‐IGRT

“…Compared to the segmentation task using diagnostic quality MR images, automatic segmentation of targets and/or OARs using the ViewRay images is more challenging, primarily because soft‐tissue contrast and spatial resolution have to be compromised to achieve sufficient temporal resolution. In addition, most MR image segmentation studies focused on a single anatomical site, mostly brain 14 , 15 and cardiac tissue 10 , 16 , 17 , 18 . However, for MR‐IGRT, it is necessary to be able to segment and track a broad range of organs and tumors (e.g., bladder, kidney, duodenum, liver tumor).…”