The matching algorithms

J.-F. Mangin, J. Régis, I. Bloch,
V. Frouin, Y. Samson, and J. Lopez-Krahe
A Markovian random field based random graph
modelling the human cortical topography
In First Int. Conf. on Computer Vision, Virtual Reality and Robotics in Medicine, Nice, France,
pages 177--183,
LNCS 905, Springer Verlag,
1995

This paper presents a project aiming at the automatic detection and recognition of the human cortical sulci in a 3D magnetic resonance image. The two first steps of this project (automatic extraction of an attributed relational graph (ARG) representing the individual cortical topography, constitution of a database of labelled ARGs) are briefly described. Then, a probabilistic structural model of the cortical topography is inferred from the database. This model, which is a structural prototype whose nodes can split into pieces according to syntactic constraints, relies on several original interpretations of the inter-individual structural variability of the cortical topography. This prototype is endowed with a random graph structure taking into account this anatomical variability. The recognition process is formalized as a labelling problem whose solution, defined as the maximum a posteriori estimate of a Markovian random field (MRF), is obtained using simulated annealing.

D. Rivière, J.-F. Mangin, D. Papadopoulos-Orfanos,
J.-M. Martinez, V. Frouin, and J. Régis
Automatic recognition of cortical sulci of the Human Brain
using a congregation of neural networks
Medical Image Analysis,
6(2):77--92,
2002

This paper describes a complete system allowing automatic recognition of the main sulci of the human cortex. This system relies on a preprocessing of magnetic resonance images leading to abstract structural representations of the cortical folding patterns. The representation nodes are cortical folds, which are given a sulcus name by a contextual pattern recognition method. This method can be interpreted as a graph matching approach, which is driven by the minimization of a global function made up of local potentials. Each potential is a measure of the likelihood of the labelling of a restricted area. This potential is given by a multi-layer perceptron trained on a learning database. A base of 26 brains manually labelled by a neuroanatomist is used to validate our approach. The whole system developed for the right hemisphere is made up of 265 neural networks. The mean recognition rate is 86% for the learning base and 76% for a generalization base, which is very satisfying considering the current weak understanding of the variability of the cortical folding patterns.
BrainVISA doc

A. Cachia, J.-F. Mangin,
D. Rivière, D. Papadopoulos-Orfanos,
F. Kherif, I. Bloch, and J. Régis
A generic framework
for parcellation of the cortical surface into gyri
using geodesic Voronoï diagrams
Medical Image Analysis,
in press, 2003

In this paper, we propose a generic automatic approach for the parcellation of the cortical surface into labelled gyri. These gyri are defined from a set of pairs of sulci selected by the user. The selected sulci are first automatically identified in the data, then projected onto the cortical surface. The parcellation stems from two nested Voronoï diagrams computed geodesically to the cortical surface. The first diagram provides the zones of influence of the sulci. The boundary between the two zones of influence of each selected pair of sulcus stands for a gyrus seed. A second diagram yields the gyrus parcellation. The distance underlying the Voronoï diagram allows the method to extrapolate the gyrus limits where the sulci are interrupted. The method is applied on twelve different hemispheres.