3D Brain Segmentation Using Active Appearance Models and Local Regressors

Babalola, Kola; Cootes, Timothy F.; Twining, Carole J.; Petrovic, V.; Taylor, Chris

doi:10.1007/978-3-540-85988-8_48

Cited by 29 publications

(22 citation statements)

References 15 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A 3D surface mesh, composed of around 1, 000 vertices, is created for each reconstructed structures in brains. The results from traditional marching cubes may contain many artifacts, thus all meshes are post-processed using isotropic remeshing and detail preserving smoothing tools 1 . To obtain the one-to-one correspondence for each vertex, we choose one specific mesh as the reference mesh and use a local deformation technique [13] to warp it into all other meshes.…”

Section: Methodsmentioning

confidence: 99%

“…These approaches have been widely used in tubular structure and 3D cortex segmentation tasks since they are topologically free and can be easily used in any dimension. Statistical modeling approaches such as Active Shape Model (ASM) [3] or Active Appearance Model (AAM) [2] are also widely used and have been successfully applied in cardiac [14] and brain [1] segmentation. These methods may need a large amount of 3D training data, whose creation and maintenance can be difficult and time consuming in practice.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

3D segmentation of rodent brain structures using Active Volume Model with shape priors

Zhang

Huang

Uzunbaş

et al. 2011

2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro

View full text Add to dashboard Cite

Object boundary extraction is an important task in brain image analysis. Acquiring detailed 3D representations of the brain structures could improve the detection rate of diseases at earlier stages. Deformable model based segmentation methods have been widely used with considerable success. Recently, 3D Active Volume Model (AVM) was proposed, which incorporates both gradient and region information for robustness. However, the segmentation performance of this model depends on the position, size and shape of the initialization, especially for data with complex texture. Furthermore, there is no shape prior information integrated. In this paper, we present an approach combining AVM and Active Shape Model (ASM). Our method uses shape information from training data to constrain the deformation of AVM. Experiments have been made on the segmentation of complex structures of the rodent brain from MR images, and the proposed method performed better than the original AVM.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

3D segmentation of rodent brain structures using Active Volume Model with shape priors

Zhang

Huang

Uzunbaş

et al. 2011

2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro

View full text Add to dashboard Cite

show abstract

“…Several o ther methods for segmentation of a natomical st ructures i n 3D brai n i mages h ave been propos ed [6] [24] [1]. We show that our method enables for robust annotation of small anatomical structures with a high shape variation such as the optic nerve.…”

Section: Introductionmentioning

confidence: 94%

Toward knowledge-enhanced viewing using encyclopedias and model-based segmentation

Kneser

Lehmann

Geller

et al. 2009

Medical Imaging 2009: Computer-Aided Diagnosis

View full text Add to dashboard Cite

To m ake accu rate deci sions based on i maging data, radiolog ists must as sociate t he viewed i maging data with t he corresponding anatomical structures. Furthermore, given a disease hypothesis possible image findings which verify the hypothesis must be considered and where and how they are expressed in the viewed images. If rare anatomical variants, rare pathologies, unfamiliar protocols, or am biguous findings are pres ent, external knowledge sources such as medical encyclopedias are con sulted. T hese s ources are acces sed u sing keywords t ypically de scribing a natomical s tructures, image findings, pathologies.In th is paper we pres ent o ur v ision of how a patie nt's i maging data can be a utomatically e nhanced with an atomical knowledge as well as knowledge about image findings. On one hand, we propose the automatic annotation of the images with labels from a standard anatomical ontology. These labels are used as keywords for a medical encyclopedia such as STATdx to acces s an atomical des criptions, inf ormation abou t path ologies an d i mage findings. O n th e ot her h and we envision e ncyclopedias to contain links to region-and finding-specific i mage processing algorithms. T hen a f inding is evaluated on an image by applying the respective algorithm in the associated anatomical region.Towards realization of our vision, we present our method and results of automatic annotation of anatomical structures in 3D MRI brain i mages. Thereby we develop a co mplex surface mesh model incorporating major structures of the brain and a model-based segmentation method. We dem onstrate the validity b y a nalyzing t he results of several training and segmentation experiments with clinical data focusing particularly on the visual pathway.

show abstract

“…For each subject, the following SERT-rich ROIs were extracted from their T 1 -weighted MRI using an automated method (Babalola et al, 2008): putamen (PUT), caudate (CAU), thalamus (THA) and brainstem (BS; comprising SERT-rich midbrain plus pons and medulla). The region of reference (ROR) was manually delineated on the MRI, using Analyze (Mayo Clinic, MN, USA), in posterior cerebellar cortex, excluding vermis and central white matter and keeping at least one FWHM from venous sinuses and occipital cortex (Meyer, 2007).…”

Section: Image Analysismentioning

confidence: 99%

Brain Serotonin Transporter Occupancy by Oral Sibutramine Dosed to Steady State: A PET Study Using 11C-DASB in Healthy Humans

Talbot

Bradley²,

Clarke³

et al. 2009

Neuropsychopharmacol

View full text Add to dashboard Cite

Sibutramine is a centrally acting monoamine reuptake inhibitor prescribed as an appetite suppressant in the management of obesity. Its effects are mostly attributable to serotonin and norepinephrine transporter (SERT and NET, respectively) inhibition by its potent metabolites mono-desmethylsibutramine (M1) and di-desmethylsibutramine (M2). However, there is a paucity of in vivo data in humans about mechanisms underlying both clinical efficacy and the dose-independent non-response observed in a minority of patients. Twelve healthy male patients (mean age 41 years) completed a double-blind, placebo-controlled, within-subject crossover investigation of brain SERT occupancy by sibutramine 15 mg daily at steady state. Correlations were measured between occupancy and (i) plasma concentrations of sibutramine, M1 and M2; (ii) appetite suppression.11 C-DASB PET scans were performed on the HRRT camera. Binding potentials (BP ND ) were calculated by the Logan reference tissue (cerebellum) method. SERT occupancy was modest (mean 30 ± 10%), was similar across brain regions, but varied widely across subjects (15-46%). Occupancy was correlated positively (p ¼ 0.09) with M2 concentration, but not with sibutramine or M1. No significant appetite suppression was seen at o25% occupancy and greatest suppression was associated with highest occupancy (25-46%). However, several subjects with occupancy (36-39%) in the higher range had no appetite suppression. SERT occupancy by clinical doses of sibutramine is of modest magnitude and may be mediated predominantly by M2 in humans. 5-HT reuptake inhibition may be necessary but is not sufficient for sibutramine's efficacy in humans, supporting preclinical data suggesting that the hypophagic effect requires the co-inhibition of both SERT and NET.

show abstract

3D Brain Segmentation Using Active Appearance Models and Local Regressors

Cited by 29 publications

References 15 publications

3D segmentation of rodent brain structures using Active Volume Model with shape priors

3D segmentation of rodent brain structures using Active Volume Model with shape priors

Toward knowledge-enhanced viewing using encyclopedias and model-based segmentation

Brain Serotonin Transporter Occupancy by Oral Sibutramine Dosed to Steady State: A PET Study Using 11C-DASB in Healthy Humans

Contact Info

Product

Resources

About