Automated brain extraction using Multi-Atlas Propagation and Segmentation (MAPS)

Abstract

Whole brain extraction is an important pre-processing step in neuro-image analysis. We compared the accuracy of four automated brain extraction methods: Brain Extraction Tool (BET), Brain Surface Extractor (BSE), Hybrid Watershed Algorithm (HWA) and a Multi-Atlas Propagation and Segmentation (MAPS) technique we have previously developed for hippocampal segmentation. The four methods were applied to extract whole brains from 682 1.5T and 157 3T T <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -weighted MR baseline images from the Alzheimer's Disease Neuroimaging Initiative database. Using semi-automated brain segmentations with manual editing and checking as the gold-standard, the median (1st-99th centile range) Jaccard indices of MAPS, HWA, BET and BSE were 0.981 (0.041), 0.970 (0.126), 0.969 (0.826) and 0.953 (0.217) in 1.5T scans, and 0.980 (0.047), 0.962 (0.701), 0.965 (0.731) and 0.900 (0.550) in 3T scans. In conclusion, MAPS had relatively high accuracy and low variability compared to HWA, BET and BSE in MR scans with and without atrophy.