Accurate Learning with Few Atlases (ALFA): an algorithm for MRI neonatal brain extraction and comparison with 11 publicly available methods

Serag, Ahmed; Blesa, Manuel; Moore, Emma J.; Pataky, Rozalia; Sparrow, Sarah; Wilkinson, A G; Macnaught, Gillian; Semple, Scott; Boardman, James P.

doi:10.1038/srep23470

Cited by 41 publications

(46 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These methods, such as MASS (Doshi et al, 2013), MAPS (Leung et al, 2011), BEMA (Rex et al, 2004), Pincram (Heckemann et al, 2015), ANTs (Avants et al, 2011), and others (Serag et al, 2016; Shi et al, 2012), involve deformable registrations of multiple atlases to a target image. The atlases contain accurate, often manually or semi-automatically drawn brain masks.…”

Section: Introductionmentioning

confidence: 99%

Robust skull stripping using multiple MR image contrasts insensitive to pathology

2017

View full text Add to dashboard Cite

Automatic skull-stripping or brain extraction of magnetic resonance (MR) images is often a fundamental step in many neuroimage processing pipelines. The accuracy of subsequent image processing relies on the accuracy of the skull-stripping. Although many automated stripping methods have been proposed in the past, it is still an active area of research particularly in the context of brain pathology. Most stripping methods are validated on T1-w MR images of normal brains, especially because high resolution T1-w sequences are widely acquired and ground truth manual brain mask segmentations are publicly available for normal brains. However, different MR acquisition protocols can provide complementary information about the brain tissues, which can be exploited for better distinction between brain, cerebrospinal fluid, and unwanted tissues such as skull, dura, marrow, or fat. This is especially true in the presence of pathology, where hemorrhages or other types of lesions can have similar intensities as skull in a T1-w image. In this paper, we propose a sparse patch based Multi-cONtrast brain STRipping method (MONSTR)1, where non-local patch information from one or more atlases, which contain multiple MR sequences and reference delineations of brain masks, are combined to generate a target brain mask. We compared MONSTR with four state-of-the-art, publicly available methods: BEaST, SPECTRE, ROBEX, and OptiBET. We evaluated the performance of these methods on 6 datasets consisting of both healthy subjects and patients with various pathologies. Three datasets (ADNI, MRBrainS, NAMIC) are publicly available, consisting of 44 healthy volunteers and 10 patients with schizophrenia. Other three in-house datasets, comprising 87 subjects in total, consisted of patients with mild to severe traumatic brain injury, brain tumors, and various movement disorders. A combination of T1-w, T2-w were used to skull-strip these datasets. We show significant improvement in stripping over the competing methods on both healthy and pathological brains. We also show that our multi-contrast framework is robust and maintains accurate performance across different types of acquisitions and scanners, even when using normal brains as atlases to strip pathological brains, demonstrating that our algorithm is applicable even when reference segmentations of pathological brains are not available to be used as atlases.

show abstract

Section: Introductionmentioning

confidence: 99%

Robust skull stripping using multiple MR image contrasts insensitive to pathology

2017

View full text Add to dashboard Cite

show abstract

“…For brain extraction, we used the brain masks which are provided with each dataset; except dataset I which was brain extracted using ALFA (Serag et al, 2016). All images from all datasets were corrected for intensity inhomogeneity using the N4 method (Tustison et al, 2010).…”

Section: Methodsmentioning

confidence: 99%

“…Therefore, we use in this work a sparsity-based technique to select a number of representative atlas images that capture population variability by determining a subset of n -dimensional samples that are “uniformly” distributed in the low-dimensional data space (Serag et al, 2016). The technique works by first linearly registering (12 degrees of freedom) all images from each dataset to an appropriate common coordinate space, and image intensities are normalized using the method described by (Nyul and Udupa, 2000).…”

Section: Methodsmentioning

confidence: 99%

“…The consecutive images are selected sequentially, based on the distances to the images already assigned to the subset. Further details can be found in (Serag et al, 2016). …”

Section: Methodsmentioning

confidence: 99%

“…SEGMA differs from current supervised approaches in the following ways. First, SEGMA uses a sparsity-based technique for training data selection by selecting training data samples that are “uniformly” distributed in the low-dimensional data space, and hence eliminates the need for target-specific training data (Serag et al, 2016). Second, SEGMA uses linear registration to provide an accurate segmentation (mainly to ensure the same orientation and size for all subjects).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

SEGMA: An Automatic SEGMentation Approach for Human Brain MRI Using Sliding Window and Random Forests

Serag

Wilkinson

Telford

et al. 2017

Front. Neuroinform.

Self Cite

View full text Add to dashboard Cite

Quantitative volumes from brain magnetic resonance imaging (MRI) acquired across the life course may be useful for investigating long term effects of risk and resilience factors for brain development and healthy aging, and for understanding early life determinants of adult brain structure. Therefore, there is an increasing need for automated segmentation tools that can be applied to images acquired at different life stages. We developed an automatic segmentation method for human brain MRI, where a sliding window approach and a multi-class random forest classifier were applied to high-dimensional feature vectors for accurate segmentation. The method performed well on brain MRI data acquired from 179 individuals, analyzed in three age groups: newborns (38–42 weeks gestational age), children and adolescents (4–17 years) and adults (35–71 years). As the method can learn from partially labeled datasets, it can be used to segment large-scale datasets efficiently. It could also be applied to different populations and imaging modalities across the life course.

show abstract

An efficient and accurate method for robust inter‐dataset brain extraction and comparisons with 9 other methods

Novosad

Collins

Initiative³

2018

Human Brain Mapping

View full text Add to dashboard Cite

Brain extraction is an important first step in many magnetic resonance neuroimaging studies. Due to variability in brain morphology and in the appearance of the brain due to differences in scanner acquisition parameters, the development of a generally applicable brain extraction algorithm has proven challenging. Learning-based brain extraction algorithms in particular perform well when the target and training images are sufficiently similar, but often perform worse when this condition is not met. In this study, we propose a new patch-based multi-atlas segmentation method for brain extraction which is specifically developed for accurate and robust processing across datasets. Using a diverse collection of labeled images from 5 different datasets, extensive comparisons were made with 9 other commonly used brain extraction methods, both before and after applying error correction (a machine learning method for automatically correcting segmentation errors) to each method. The proposed method performed equal to or better than the other methods in each of two segmentation scenarios: a challenging inter-dataset segmentation scenario in which no dataset-specific atlases were used (mean Dice coefficient 98.57%, volumetric correlation 0.994 across datasets following error correction), and an intra-dataset segmentation scenario in which only dataset-specific atlases were used (mean Dice coefficient 99.02%, volumetric correlation 0.998 across datasets following error correction). Furthermore, combined with error correction, the proposed method runs in less than one-tenth of the time required by the other top-performing methods in the challenging inter-dataset comparisons. Validation on an independent multi-centre dataset also confirmed the excellent performance of the proposed method.

show abstract

Accurate Learning with Few Atlases (ALFA): an algorithm for MRI neonatal brain extraction and comparison with 11 publicly available methods

Cited by 41 publications

References 65 publications

Robust skull stripping using multiple MR image contrasts insensitive to pathology

Robust skull stripping using multiple MR image contrasts insensitive to pathology

SEGMA: An Automatic SEGMentation Approach for Human Brain MRI Using Sliding Window and Random Forests

An efficient and accurate method for robust inter‐dataset brain extraction and comparisons with 9 other methods

Contact Info

Product

Resources

About