Automated extraction of the cortical sulci based on a supervised learning approach.

Automated extraction of the cortical sulci based on a supervised learning approach. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Automated extraction of the cortical sulci based on a supervised learning approach. Abstract Text:

Zhuowen Tu,Songfeng Zheng,Alan L Yuille,Allan L Reiss,Rebecca A Dutton,Agatha D Lee,Albert M Galaburda,Ivo Dinov,Paul M Thompson,Arthur W Toga,

It is important to detect and extract the major cortical sulci from brain images, but manually annotating these sulci is a time-consuming task and requires the labeler to follow complex protocols. This paper proposes a learning-based algorithm for automated extraction of the major cortical sulci from magnetic resonance imaging (MRI) volumes and cortical surfaces. Unlike alternative methods for detecting the major cortical sulci, which use a small number of predefined rules based on properties of the cortical surface such as the mean curvature, our approach learns a discriminative model using the probabilistic boosting tree algorithm (PBT). PBT is a supervised learning approach which selects and combines hundreds of features at different scales, such as curvatures, gradients and shape index. Our method can be applied to either MRI volumes or cortical surfaces. It first outputs a probability map which indicates how likely each voxel lies on a major sulcal curve. Next, it applies dynamic programming to extract the best curve based on the probability map and a shape prior. The algorithm has almost no parameters to tune for extracting different major sulci. It is very fast (it runs in under 1 min per sulcus including the time to compute the discriminative models) due to efficient implementation of the features (e.g., using the integral volume to rapidly compute the responses of 3-D Haar filters). Because the algorithm can be applied to MRI volumes directly, there is no need to perform preprocessing such as tissue segmentation or mapping to a canonical space. The learning aspect of our approach makes the system very flexible and general. For illustration, we use volumes of the right hemisphere with several major cortical sulci manually labeled. The algorithm is tested on two groups of data, including some brains from patients with Williams Syndrome, and the results are very encouraging.

Automated extraction of the cortical sulci based on a supervised learning approach. Publishing Authors By Initials

Z Tu,S Zheng,AL Yuille,AL Reiss,RA Dutton,AD Lee,AM Galaburda,I Dinov,PM Thompson,AW Toga,

For similar investigative techniques: epidemiologic methods: statistics as topic: sensitivity and specificity research abstracts see: investigative techniques: epidemiologic methods: statistics as topic: sensitivity and specificity research

PUBMED ID PMID:

MEDLINE DATE:

Automated extraction of the cortical sulci based on a supervised learning approach. Journal Published:

PUBLICATION TYPE: Research Support, N.I.H., Extr

Journal: IEEE transactions on medical imaging

VOLUME: 26

Page Numbers: 541-52

Journal Abbreviation:

ISSN: 0278-0062

DAY: 3

MONTH: Apr

YEAR: 2007

Automated extraction of the cortical sulci based on a supervised learning approach. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 8310780

Automated extraction of the cortical sulci based on a supervised learning approach. Keywords Mesh Terms:

KEYWORDS: Sensitivity and Specificity

MESH TERMS: methods

Chemical & Substance for Abstract: Automated extraction of the cortical sulci based on a supervised learning approach. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for Automated extraction of the cortical sulci based on a supervised learning approach.

AFFILIATION: Laboratory of Neuro Imaging, University of California-Los Angeles, School of Medicine, Los Angeles, CA 90095, USA.

Country: United States

AGENCY: United States NCRR

GRANT: U54 RR021813

ACRONYM: RR

MEDLINETA: IEEE Trans Med Imaging

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Automated extraction of the cortical sulci based on a supervised learning approach Related Publications

• A learning based algorithm for automatic extraction of the cortical sulci.
• A surface-based technique for warping three-dimensional images of the brain.
• Abnormal cortical thickness and brain behavior correlation patterns in individuals with heavy prenatal alcohol exposure.
• Abnormal development of the anterior cingulate in childhood-onset schizophrenia: a preliminary quantitative MRI study.
• Age effects on hippocampal structural changes in old men: The HAAS.
• Asymmetries of cortical shape: Effects of handedness, sex and schizophrenia.
• Asymmetries of cortical thickness: effects of handedness, sex, and schizophrenia.
• Automated extraction of the cortical sulci based on a supervised learning approach.
• Brain anatomical structure segmentation by hybrid discriminative/generative models.
• Brain atlases and neuroanatomic imaging.
• Construction of a 3D probabilistic atlas of human cortical structures.
• Detection and segmentation of pathological structures by the extended graph-shifts algorithm.
• Direct cortical mapping via solving partial differential equations on implicit surfaces.
• Direct mapping of hippocampal surfaces with intrinsic shape context.
• Genetic algorithms for finite mixture model based voxel classification in neuroimaging.
• Hamilton-jacobi skeleton on cortical surfaces.
• Joint sulci detection using graphical models and boosted priors.
• LONI visualization environment.
• Mapping cortical asymmetry and complexity patterns in normal children.
• Not Available
• Pharmacological effect of capsaicin on rat avoidance behaviours elicited by sine-wave electrical stimulation of different frequencies by Neurometer.
• Regional specificity of cerebrospinal fluid abnormalities in first episode schizophrenia.
• Segmentation of brain MR images using a charged fluid model.
• Segmentation of sub-cortical structures by the graph-shifts algorithm.
• Temporal profiles and 2-dimensional oxy-, deoxy-, and total-hemoglobin somatosensory maps in rat versus mouse cortex.
• Towards whole brain segmentation by a hybrid model.
• Tracking Alzheimer's disease.
• [A case of broncholithiasis lithoptysis occurring spontaneously after repeated pneumonia]
• [Encephalopathy subsequent to criminal abortion; (1) development of dementia in brain disease caused by criminal abortion; (2) anatomical findings in a case of rapid death.]
• iTools: a framework for classification, categorization and integration of computational biology resources.