Validating Automated Segmentation Tools in the Assessment of Caudate Atrophy in Huntington’s Disease

Abstract

Background: Neuroimaging shows considerable promise in generating sensitive and objective outcome measures for therapeutic trials across a range of neurodegenerative conditions. For volumetric measures the current gold standard is manual delineation, which is unfeasible for samples sizes required for large clinical trials.Methods: Using a cohort of early Huntington’s disease (HD) patients (n = 46) and controls (n = 35), we compared the performance of four automated segmentation tools (FIRST, FreeSurfer, STEPS, MALP-EM) with manual delineation for generating cross-sectional caudate volume, a region known to be vulnerable in HD. We then examined the effect of each of these baseline regions on the ability to detect change over 15 months using the established longitudinal Caudate Boundary Shift Integral (cBSI) method, an automated longitudinal pipeline requiring a baseline caudate region as an input.Results: All tools, except Freesurfer, generated significantly smaller caudate volumes than the manually derived regions. Jaccard indices showed poorer levels of overlap between each automated segmentation and manual delineation in the HD patients compared with controls. Nevertheless, each method was able to demonstrate significant group differences in volume (p < 0.001). STEPS performed best qualitatively as well as quantitively in the baseline analysis. Caudate atrophy measures generated by the cBSI using automated baseline regions were largely consistent with those derived from a manually segmented baseline, with STEPS providing the most robust cBSI values across both control and HD groups.Conclusions: Atrophy measures from the cBSI were relatively robust to differences in baseline segmentation technique, suggesting that fully automated pipelines could be used to generate outcome measures for clinical trials.

Freesurfer Software Update Significantly Impacts Striatal Volumes in the Huntington’s Disease Young Adult Study and Will Influence HD-ISS Staging

“…However, the confines of this dataset have also resulted in a smaller and less heterogenous sample for comparing FS measurements. Automated segmentation techniques have previously demonstrated greater overlap in controls than HD participants [20,30]. Near-normal brain volumes may therefore have resulted in closer proximity of measurements than can be expected for participants with more advanced disease.…”

“…Bland-Altman analysis showed FS7 calculated larger raw volumes, and this difference was greater for larger rather than smaller volumes. Contrary to the majority of previous studies [3,[26][27][28][29][30], the comparison between automated segmentation techniques must include cTICV since raw volumes are regularly divided by cTICV to adjust for variation with maximal brain volume. This is also what is required for the HD-ISS.…”

Convolutional Neural Networks Enable Robust Automatic Segmentation of the Rat Hippocampus in MRI After Traumatic Brain Injury

“…While few methods have been proposed for the anatomical segmentation of brain MRIs with lesions on human data ( 10 – 13 ), the literature comparing the region segmentation accuracy of different methods in lesioned brains is limited and the potential biases arising from difference of the segmentation accuracy between healthy and lesioned brains has been rarely analyzed. In this regard ( 14 ) documented a significant drop in the performance of registration-based segmentation of the hippocampus due to atrophy, and ( 15 ) detected a drop in segmentation quality as a consequence of Huntington's disease across different segmentation methods.…”