6533b821fe1ef96bd127b69a
RESEARCH PRODUCT
Hidden Markov Random Field model and BFGS algorithm for Brain Image Segmentation
Dominique MichelucciEl-hachemi GuerroutRamdane MahiouSamy Ait-aoudiasubject
business.industrySegmentation-based object categorizationComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONScale-space segmentationPattern recognitionImage segmentationMachine learningcomputer.software_genreSørensen–Dice coefficientBroyden–Fletcher–Goldfarb–Shanno algorithmSegmentationArtificial intelligenceHidden Markov random fieldbusinessHidden Markov modelcomputerMathematicsdescription
Brain MR images segmentation has attracted a particular focus in medical imaging. The automatic image analysis and interpretation became a necessity. Segmentation is one of the key operations to provide a crucial decision support to physicians. Its goal is to simplify the representation of an image into items meaningful and easier to analyze. Hidden Markov Random Fields (HMRF) provide an elegant way to model the segmentation problem. This model leads to the minimization problem of a function. BFGS (Broyden-Fletcher-Goldfarb-Shanno algorithm) is one of the most powerful methods to solve unconstrained optimization problem. This paper presents how we combine HMRF and BFGS to achieve a good segmentation. Brain image segmentation results are evaluated on ground-truth images, using the Dice coefficient.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2016-11-22 | Proceedings of the Mediterranean Conference on Pattern Recognition and Artificial Intelligence |