Brain MAPS: An automated, accurate and robust brain extraction technique using a template library
ABSTRACT Whole brain extraction is an important pre-processing step in neuroimage analysis. Manual or semi-automated brain delineations are labour-intensive and thus not desirable in large studies, meaning that automated techniques are preferable. The accuracy and robustness of automated methods are crucial because human expertise may be required to correct any suboptimal results, which can be very time consuming. 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(1)-weighted MR baseline images from the Alzheimer's Disease Neuroimaging Initiative database. Semi-automated brain segmentations with manual editing and checking were used as the gold-standard to compare with the results. The median Jaccard index of MAPS was higher than HWA, BET and BSE in 1.5T and 3T scans (p<0.05, all tests), and the 1st to 99th centile range of the Jaccard index of MAPS was smaller than HWA, BET and BSE in 1.5T and 3T scans ( p<0.05, all tests). HWA and MAPS were found to be best at including all brain tissues (median false negative rate ≤0.010% for 1.5T scans and ≤0.019% for 3T scans, both methods). The median Jaccard index of MAPS were similar in both 1.5T and 3T scans, whereas those of BET, BSE and HWA were higher in 1.5T scans than 3T scans (p<0.05, all tests). We found that the diagnostic group had a small effect on the median Jaccard index of all four methods. In conclusion, MAPS had relatively high accuracy and low variability compared to HWA, BET and BSE in MR scans with and without atrophy.
- SourceAvailable from: Nigel J. Cairns
[Show abstract] [Hide abstract]
- "Beyond the standardization of methods and data sets, MRI studies carried out with the ADNI cohort have impacted clinical trials in a number of ways. Fox and coworkers developed improved methods for measuring the rate of atrophy across multiple sites and for reducing required sample sizes   , and also developed automated methods to measure brain and hippocampal volume and rates of atrophy   . These have been incorporated into large commercial clinical trials and submitted to the European Medicines Agency, leading to guidance on hippocampal volume measurement in trials . "
ABSTRACT: The Alzheimer's Disease Neuroimaging Initiative (ADNI) was established in 2004 to facilitate the development of effective treatments for Alzheimer's disease (AD) by validating biomarkers for AD clinical trials. We searched for ADNI publications using established methods. ADNI has (1) developed standardized biomarkers for use in clinical trial subject selection and as surrogate outcome measures; (2) standardized protocols for use across multiple centers; (3) initiated worldwide ADNI; (4) inspired initiatives investigating traumatic brain injury and post-traumatic stress disorder in military populations, and depression, respectively, as an AD risk factor; (5) acted as a data-sharing model; (6) generated data used in over 600 publications, leading to the identification of novel AD risk alleles, and an understanding of the relationship between biomarkers and AD progression; and (7) inspired other public-private partnerships developing biomarkers for Parkinson's disease and multiple sclerosis. ADNI has made myriad impacts in its first decade. A competitive renewal of the project in 2015 would see the use of newly developed tau imaging ligands, and the continued development of recruitment strategies and outcome measures for clinical trials. Copyright © 2015 The Alzheimer's Association. All rights reserved.Alzheimer's & dementia: the journal of the Alzheimer's Association 07/2015; 11(7):865-84. DOI:10.1016/j.jalz.2015.04.005 · 17.47 Impact Factor
[Show abstract] [Hide abstract]
- "In the context of segmentation of structural human brain MRI, multiatlas techniques have also been applied to preprocessing tasks such as skull stripping (Leung et al., 2011; Weisenfeld and Warfield, 2011b) and tissue classification (Bouix et al., 2007; Crum, 2009), as well as to the segmentation of tumors (Wang and Yushkevich, 2013b; Warfield et al., 2004). The multi-atlas approach has been employed for the segmentation of cortical and subcortical structures in MRI data from neonates and infants, too (Gholipour et al., 2012; Gousias et al., 2008, 2010, 2013; Shi et al., 2010; Wang et al., 2014b), in which the contrast inversion due to the ongoing myelination complicates the segmentation. "
ABSTRACT: Multi-atlas segmentation (MAS), first introduced and popularized by the pioneering work of Rohlfing, et al. (2004), Klein, et al. (2005), and Heckemann, et al. (2006), is becoming one of the most widely-used and successful image segmentation techniques in biomedical applications. By manipulating and utilizing the entire dataset of "atlases" (training images that have been previously labeled, e.g., manually by an expert), rather than some model-based average representation, MAS has the flexibility to better capture anatomical variation, thus offering superior segmentation accuracy. This benefit, however, typically comes at a high computational cost. Recent advancements in computer hardware and image processing software have been instrumental in addressing this challenge and facilitated the wide adoption of MAS. Today, MAS has come a long way and the approach includes a wide array of sophisticated algorithms that employ ideas from machine learning, probabilistic modeling, optimization, and computer vision, among other fields. This paper presents a survey of published MAS algorithms and studies that have applied these methods to various biomedical problems. In writing this survey, we have three distinct aims. Our primary goal is to document how MAS was originally conceived, later evolved, and now relates to alternative methods. Second, this paper is intended to be a detailed reference of past research activity in MAS, which now spans over a decade (2003-2014) and entails novel methodological developments and application-specific solutions. Finally, our goal is to also present a perspective on the future of MAS, which, we believe, will be one of the dominant approaches in biomedical image segmentation. Copyright © 2015 Elsevier B.V. All rights reserved.Medical image analysis 12/2014; 24(1). DOI:10.1016/j.media.2015.06.012 · 3.68 Impact Factor
[Show abstract] [Hide abstract]
- "International Journal of Biomedical Imaging by using nonlinear registration atlas-based approaches  . More recent works of special interest for the brain extraction problem are methods like MAPS  and BEaST . Both methods rely on the application of a multiatlas label fusion strategy. "
ABSTRACT: Automatic and accurate methods to estimate normalized regional brain volumes from MRI data are valuable tools which may help to obtain an objective diagnosis and followup of many neurological diseases. To estimate such regional brain volumes, the intracranial cavity volume (ICV) is often used for normalization. However, the high variability of brain shape and size due to normal intersubject variability, normal changes occurring over the lifespan, and abnormal changes due to disease makes the ICV estimation problem challenging. In this paper, we present a new approach to perform ICV extraction based on the use of a library of prelabeled brain images to capture the large variability of brain shapes. To this end, an improved nonlocal label fusion scheme based on BEaST technique is proposed to increase the accuracy of the ICV estimation. The proposed method is compared with recent state-of-the-art methods and the results demonstrate an improved performance both in terms of accuracy and reproducibility while maintaining a reduced computational burden.International Journal of Biomedical Imaging 09/2014; 2014:820205. DOI:10.1155/2014/820205