Search PubMed⌕ Search
Home/Archive/PubMed

PubMed · 16685991

Fully automatic shape modelling using growing cell.

Luca Ferrarini·Hans Olofsen·Mark A van Buchem·Johan H C Reiber·Faiza Admiraal-Behloul
View original source ↗Export metadata ↓

Abstract

In this paper, we present a new framework for shape modelling and analysis: we suggest to look at the problem from a pattern recognition point of view, and claim that under this prospective several advantages are achieved. The modelling of a surface with a point distribution model is seen as an unsupervised clustering problem, and tackled by using growing cell structures. The adaptation of a model to new shapes is studied as a classification task, and provides a straightforward solution to the point correspondence problem in active shape modelling. The method is illustrated and tested in 3D synthetic datasets and applied to the modelling of brain ventricles in an elderly population.

Explore related subjects

Cerebral VentriclesComputer SimulationHumansImage Interpretation, Computer-AssistedModels, AnatomicModels, BiologicalNeural Networks, ComputerPattern Recognition, AutomatedEvaluation StudyJournal ArticleResearch Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Luca Ferrarini, Hans Olofsen, Mark A van Buchem, Johan H C Reiber, Faiza Admiraal-Behloul. 2005. Fully automatic shape modelling using growing cell.. https://doi.org/10.1007/11566489_56

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2006

Comparison of intracranial pressure measured simultaneously within the brain parenchyma and cerebral ventricles.

We report a 48-year-old man treated for acute subarachnoid hemorrhage (SAH) wherein intracranial pressure (ICP) was measured simultaneously within the ventricular cerebrospinal fluid (CSF) and the brain parenchyma (PAR). Single pressure waves within the continuous pressure signal were identified with determination of the single wave parameters pulse amplitude (i.e. pressure difference between diastolic minimum pressure and systolic maximum pressure), mean pressure (i.e. mean pressure from beginning to ending minimum diastolic minimum pressure), and latency (i.e. rise time from diastolic minimum pressure to systolic maximum pressure). A total of 218,589 CSF/PAR single pressure wave pairs were analyzed. For these CSF/PAR wave pairs the mean difference in pulse pressure amplitude was -0.13 mmHg [95% confidence interval (CI) -0.13 to -0.12 mmHg], mean difference in mean single wave pressure -0.71 mmHg (95% CI -0.74 to -0.68 mmHg), and mean difference in latency -0.01 seconds (95% CI -0.01 to -0.01 seconds). Hence, in this patient monitoring ICP within the ventricular CSF or brain parenchyma gave similar results. Moreover, the comparisons of single CSF/PAR wave pulse pressure amplitudes gave no evidence of a pressure gradient from brain parenchyma to the ventricular CSF in this patient.

Cerebral Ventricles↗
PubMed2006

Periventricular nodular heterotopia and Williams syndrome.

We report here on the first case of a child with bilateral periventricular nodular heterotopia (PNH) and Williams syndrome. Fluorescent in situ hybridization (FISH) analyses demonstrated a deletion of the elastin gene in the Williams syndrome critical region (WSCR). Further mapping by loss of heterozygosity analysis both by microsatellite marker and SNP profiling demonstrated a 1.5 Mb deletion beyond the telomeric end of the typical WSCR. No mutations were identified in the X-linked filamin-A gene (the most common cause of PNH). These findings suggest another dominant PNH disorder along chromosome 7q11.23.

Cerebral Ventricles↗