A fully-automatic caudate nucleus segmentation of brain MRI: Application in volumetric analysis of pediatric attention-deficit/hyperactivity disorder

Abstract

BackgroundAccurate automatic segmentation of the caudate nucleus in magnetic resonance images (MRI) of the brain is of great interest in the analysis of developmental disorders. Segmentation methods based on a single atlas or on multiple atlases have been shown to suitably localize caudate structure. However, the atlas prior information may not represent the structure of interest correctly. It may therefore be useful to introduce a more flexible technique for accurate segmentations.MethodWe present Cau-dateCut: a new fully-automatic method of segmenting the caudate nucleus in MRI. CaudateCut combines an atlas-based segmentation strategy with the Graph Cut energy-minimization framework. We adapt the Graph Cut model to make it suitable for segmenting small, low-contrast structures, such as the caudate nucleus, by defining new energy function data and boundary potentials. In particular, we exploit information concerning the intensity and geometry, and we add supervised energies based on contextual brain structures. Furthermore, we reinforce boundary detection using a new multi-scale edgeness measure.ResultsWe apply the novel CaudateCut method to the segmentation of the caudate nucleus to a new set of 39 pediatric attention-deficit/hyperactivity disorder (ADHD) patients and 40 control children, as well as to a public database of 18 subjects. We evaluate the quality of the segmentation using several volumetric and voxel by voxel measures. Our results show improved performance in terms of segmentation compared to state-of-the-art approaches, obtaining a mean overlap of 80.75%. Moreover, we present a quantitative volumetric analysis of caudate abnormalities in pediatric ADHD, the results of which show strong correlation with expert manual analysis.ConclusionCaudateCut generates segmentation results that are comparable to gold-standard segmentations and which are reliable in the analysis of differentiating neuroanatomical abnormalities between healthy controls and pediatric ADHD.

Functional MRI-guided probabilistic tractography of cortico-cortical and cortico-subcortical language networks in children

“…Therefore and despite the developer's good experience in applying these tools in children, a bias when using adult prior information cannot wholly be excluded. Consequently, an important future development would be to develop and apply methods (Igual et al, 2011;Wilke et al, 2008) to specifically analyze the pediatric brain. Further the cortical templates used here for anatomical tracing and the search masked used for localizing the seed and target areas for functional driven tractography were also derived from an adult template.…”

Supervised brain segmentation and classification in diagnostic of Attention-Deficit/Hyperactivity Disorder

“…See [4] for more details. Finally, by applying the min-cut algorithm over the defined energy function and image graph, the final caudate segmentation is obtained.…”

“…The volume of each voxel is 0.94 × 0.94 × 2 mm 3 . Ground truth was build by means of an expert team as is described in [4] and [9].…”

“…The approach applied in this paper combines the power of atlas-based segmentation with a new supervised energybased scheme based on the Graph Cut (GC) framework to obtain a globally optimal segmentation of the caudate structure in MRI [4]. GC theory has been used in many computer vision problems [5], such as binary segmentation [6], [7].…”

Cerebrospinal fluid image segmentation using spatial fuzzy clustering method with improved evolutionary Expectation Maximization

“…The cerebrospinal fluid (CSF) flow plays an important role in detecting neurological diseases; one of them is Alzheimer's disease [1][2][3]. Often, these diseases are detected by analysing the substantial changes in the normal CSF volume and pressure.…”