An interesting challenge in e-Health is to develop tools and software in order to benefit the healthcare services. Our applicative context is Magnetic Resonance Imaging (MRI). The main purpose of this paper is to propose a regularization framework for solving an inverse reconstruction problem in MRI. We focus on the Split Bregman method, which is a well known effcient tool for solving a wide variety of opti- mization problems e.g. total variation minimization prob- lems arising from image denoising. The proposed denoising approach, based on the TV/ROF model, involves a second- order derivative penalty term and, accordingly, introduces some modifications to the Split Bregman scheme. Our iterative regularization strategy has interesting features in highlighting the image contrasts and in the noise removal. Numerical experiments prove the goodness of the proposed approach.
A novel split bregman algorithm for MRI denoising task in an e-Health system / Cuomo, Salvatore; Campagna, Rosanna; DE MICHELE, Pasquale; Murano, Aniello; Crisci, S.; Galletti, A.; Marcellino, L.. - 29-:(2016), pp. 1-2. (Intervento presentato al convegno 9th ACM International Conference on Pervasive Technologies Related to Assistive Environments, PETRA 2016 tenutosi a grc nel 2016) [10.1145/2910674.2910692].
A novel split bregman algorithm for MRI denoising task in an e-Health system
CUOMO, SALVATORE;CAMPAGNA, ROSANNA;DE MICHELE, PASQUALE;MURANO, ANIELLO;
2016
Abstract
An interesting challenge in e-Health is to develop tools and software in order to benefit the healthcare services. Our applicative context is Magnetic Resonance Imaging (MRI). The main purpose of this paper is to propose a regularization framework for solving an inverse reconstruction problem in MRI. We focus on the Split Bregman method, which is a well known effcient tool for solving a wide variety of opti- mization problems e.g. total variation minimization prob- lems arising from image denoising. The proposed denoising approach, based on the TV/ROF model, involves a second- order derivative penalty term and, accordingly, introduces some modifications to the Split Bregman scheme. Our iterative regularization strategy has interesting features in highlighting the image contrasts and in the noise removal. Numerical experiments prove the goodness of the proposed approach.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.