Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge.

Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge. Abstract Text:

Marie Chupin,Alexander Hammers,Eric Bardinet,Olivier Colliot,Rebecca S N Liu,John S Duncan,Line Garnero,Louis Lemieux,Marie Chupin,Alexander Hammers,Eric Bardinet,Olivier Colliot,Rebecca S N Liu,John S Duncan,Line Garnero,Louis Lemieux,

The segmentation of macroscopically ill-defined and highly variable structures, such as the hippocampus Hc and the amygdala Am, from MRI requires specific constraints. Here, we describe and evaluate a hybrid segmentation method that uses knowledge derived from a probabilistic atlas and from anatomical landmarks based on stable anatomical characteristics of the structures. Combined in a previously published semi-automatic segmentation method, they lead to a fast, robust and accurate fully automatic segmentation of Hc and Am. The probabilistic atlas was built from 16 young controls and registered with the "unified segmentation" of SPM5. The algorithm was quantitatively evaluated with respect to manual segmentation on two MRI datasets: the 16 young controls, with a leave-one-out strategy, and a mixed cohort of 8 controls and 15 subjects with epilepsy with variable hippocampal sclerosis. The segmentation driven by hybrid knowledge leads to greatly improved results compared to that obtained by registration of the thresholded atlas alone: mean overlap for Hc on the 16 young controls increased from 78% to 87% (p < 0.001) and on the mixed cohort from 73% to 82% (p < 0.001) while the error on volumes decreased from 10% to 7% (p < 0.005) and from 18% to 8% (p < 0.001), respectively. Automatic results were better than the semi-automatic results: for the 16 young controls, average overlap increased from 84% to 87% (p < 0.001) for Hc and from 81% to 84% (p < 0.002) for Am, with equivalent improvements in volume error.

Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge. Publishing Authors By Initials

M Chupin,A Hammers,E Bardinet,O Colliot,RS Liu,JS Duncan,L Garnero,L Lemieux,M Chupin,A Hammers,E Bardinet,O Colliot,RS Liu,JS Duncan,L Garnero,L Lemieux,

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:

Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge. Journal Published:

PUBLICATION TYPE: Research Support, Non-U.S. Gov

Journal: Medical image computing and computer-assisted inte

VOLUME: 10

Page Numbers: 875-82

Journal Abbreviation:

ISSN:

DAY: 3

MONTH: 01

YEAR: 2007

Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 101249582

Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge. Keywords Mesh Terms:

KEYWORDS: Sensitivity and Specificity

MESH TERMS: methods

Chemical & Substance for Abstract: Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge.

AFFILIATION: Department of Clinical and Experimental Epilepsy, IoN, UCL, London, UK. m.chupin@ion.ucl.ac.uk

Country: Germany

AGENCY:

GRANT:

ACRONYM:

MEDLINETA: Med Image Comput Comput Assist

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge Related Publications

• A nutritional intervention promoting a mediterranean food pattern does not affect total daily dietary cost in north american women in free-living conditions.
• BOLD and perfusion changes during epileptic generalised spike wave activity.
• CD5+ B cell-dependent regulation of the murine T-cell independent immune response against the human blood group A antigen.
• Changes in the population pattern as revealed by the 1951 census.
• Coronary thrombolysis: adjuvant revascularization surgery.
• Defined weight expectations in overweight women: anthropometrical, psychological and eating behavioral correlates.
• Effect of a nutritional intervention promoting the Mediterranean food pattern on anthropometric profile in healthy women from the Québec city metropolitan area.
• Fully automatic segmentation of the hippocampus and the amygdala from MRI using hybrid prior knowledge.
• Immunomodulatory and anti-inflammatory potential of a malleable protein matrix composed of concentrated fermented whey proteins.
• Independent component analysis of interictal fMRI in focal epilepsy: comparison with general linear model-based EEG-correlated fMRI.
• Isolation and characterization of eceriferum (cer) mutants induced by T-DNA insertions in Arabidopsis thaliana.
• Molecular recognition in chiral smectic liquid crystals: The effect of core-core interactions and chirality transfer on polar order.
• Myotonic dystrophy type I in childhood Long-term evolution in patients surviving the neonatal period.
• Not Available
• Personality traits in overweight and obese women: Associations with BMI and eating behaviors.
• Photoinduced polarization inversion in a ferroelectric liquid crystal using an ambidextrous chiral thioindigo dopant.
• Postcoronary thrombolysis management.
• Psychiatry and rehabilitation.
• Synthesis of the t [beta-D-Gal-(1 goes to 3)-alpha-D-GalNAc]-antigenic determinant in a form useful for the preparation of an effective artificial antigen and the corresponding immunoadsorbent.
• Temporal lobe interictal epileptic discharges affect cerebral activity in "default mode" brain regions.
• The NK2.1 receptor is encoded by Ly-49C and its expression is regulated by MHC class I alleles.
• The WHO and NCEP/ATPIII Definitions of the Metabolic Syndrome in Postmenopausal Women: Are They So Different?
• The murine NK2.1 antigen: a 130 kD glycoprotein dimer expressed by a natural killer cell subset of the spleen, thymus and lymph nodes.
• Transmission of influenza A in human beings - Authors' reply.
• [" Erasme " shelter.]
• [Elaboration and application of a program of public dental health]
• [Encephalopathy of hepatic origin. I. Clinical syndrome & pathogenic conception.]
• [Group experience : risks and stakes.]
• [Not Available.]
• [Prevention and chronicity in community psychiatry.]