Share Email Print

Proceedings Paper

Multi-channel MRI segmentation with graph cuts using spectral gradient and multidimensional Gaussian mixture model
Author(s): Jérémy Lecoeur; Jean-Christophe Ferré; D. Louis Collins; Sean P. Morrisey; Christian Barillot
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A new segmentation framework is presented taking advantage of multimodal image signature of the different brain tissues (healthy and/or pathological). This is achieved by merging three different modalities of gray-level MRI sequences into a single RGB-like MRI, hence creating a unique 3-dimensional signature for each tissue by utilising the complementary information of each MRI sequence. Using the scale-space spectral gradient operator, we can obtain a spatial gradient robust to intensity inhomogeneity. Even though it is based on psycho-visual color theory, it can be very efficiently applied to the RGB colored images. More over, it is not influenced by the channel assigment of each MRI. Its optimisation by the graph cuts paradigm provides a powerful and accurate tool to segment either healthy or pathological tissues in a short time (average time about ninety seconds for a brain-tissues classification). As it is a semi-automatic method, we run experiments to quantify the amount of seeds needed to perform a correct segmentation (dice similarity score above 0.85). Depending on the different sets of MRI sequences used, this amount of seeds (expressed as a relative number in pourcentage of the number of voxels of the ground truth) is between 6 to 16%. We tested this algorithm on brainweb for validation purpose (healthy tissue classification and MS lesions segmentation) and also on clinical data for tumours and MS lesions dectection and tissues classification.

Paper Details

Date Published: 27 March 2009
PDF: 11 pages
Proc. SPIE 7259, Medical Imaging 2009: Image Processing, 72593X (27 March 2009); doi: 10.1117/12.811108
Show Author Affiliations
Jérémy Lecoeur, INRIA, IRISA (France)
Univ. of Rennes I, CNRS IRISA (France)
Jean-Christophe Ferré, Pontchaillou Univ. Hospital (France)
Univ. of Rennes 1, CNRS IRISA (France)
D. Louis Collins, Montreal Neurological Insitute, McGill Univ. (Canada)
Sean P. Morrisey, Pontchaillou Univ. Hospital (France)
Univ. of Rennes I, CNRS IRISA (France)
Christian Barillot, INRIA, IRISA (France)
Univ. of Rennes I, CNRS IRISA (France)

Published in SPIE Proceedings Vol. 7259:
Medical Imaging 2009: Image Processing
Josien P. W. Pluim; Benoit M. Dawant, Editor(s)

© SPIE. Terms of Use
Back to Top