%0 Conference Proceedings
%T Conjugate Gradient Method for Brain Magnetic Resonance Images Segmentation
%+ Laboratoire de Méthodes de Conception de Systèmes (LMCS)
%+ Laboratoire d'Electronique, d'Informatique et d'Image [EA 7508] (Le2i)
%A Guerrout, El-Hachemi
%A Ait-Aoudia, Samy
%A Michelucci, Dominique
%A Mahiou, Ramdane
%Z Part 8: Pattern Recognition and Image Processing
%< avec comité de lecture
%( IFIP Advances in Information and Communication Technology
%B 6th IFIP International Conference on Computational Intelligence and Its Applications (CIIA)
%C Oran, Algeria
%Y Abdelmalek Amine
%Y Malek Mouhoub
%Y Otmane Ait Mohamed
%Y Bachir Djebbar
%I Springer International Publishing
%3 Computational Intelligence and Its Applications
%V AICT-522
%P 561-572
%8 2018-05-08
%D 2018
%R 10.1007/978-3-319-89743-1_48
%K Brain image segmentation
%K Hidden Markov Random Field
%K The Conjugate Gradient algorithm
%K Dice Coefficient metric
%Z Computer Science [cs]Conference papers
%X Image segmentation is the process of partitioning the image into regions of interest in order to provide a meaningful representation of information. Nowadays, segmentation has become a necessity in many practical medical imaging methods as locating tumors and diseases. Hidden Markov Random Field model is one of several techniques used in image segmentation. It provides an elegant way to model the segmentation process. This modeling leads to the minimization of an objective function. Conjugate Gradient algorithm (CG) is one of the best known optimization techniques. This paper proposes the use of the nonlinear Conjugate Gradient algorithm (CG) for image segmentation, in combination with the Hidden Markov Random Field modelization. Since derivatives are not available for this expression, finite differences are used in the CG algorithm to approximate the first derivative. The approach is evaluated using a number of publicly available images, where ground truth is known. The Dice Coefficient is used as an objective criterion to measure the quality of segmentation. The results show that the proposed CG approach compares favorably with other variants of Hidden Markov Random Field segmentation algorithms.
%G English
%Z TC 5
%2 https://inria.hal.science/hal-01913885/document
%2 https://inria.hal.science/hal-01913885/file/467079_1_En_48_Chapter.pdf
%L hal-01913885
%U https://inria.hal.science/hal-01913885
%~ UNIV-BOURGOGNE
%~ CNRS
%~ UNIV-BM
%~ ENSAM
%~ LE2I
%~ UNIV-BM-THESE
%~ IFIP-LNCS
%~ IFIP
%~ IFIP-AICT
%~ IFIP-TC
%~ IFIP-TC5
%~ IFIP-CIIA
%~ IFIP-AICT-522
%~ LIB_UB
%~ LIB_MODGEOM
%~ HESAM
%~ HESAM-ENSAM
%~ IRENAV
%~ LAMPA
%~ LCPI
%~ LABOMAP
%~ LISPEN
%~ MSMP