A sparse Bayesian representation for super-resolution of cardiac MR images |
| |
| Institution: | 1. Computer Imaging and Medical Applications Laboratory – CIM@LAB, Universidad Nacional de Colombia, Bogotá, Colombia;2. Universidad Militar Nueva Granada, Bogotá, Colombia;3. Departamento de Ingeniería de Sistemas, Pontificia Universidad Javeriana, Bogotá, Colombia;4. Departamento de Física Matemática y de Fluidos, Universidad Nacional de Educación a Distancia, Madrid, Spain;1. Department of Radiology, Memorial Sloan Kettering Cancer Center;2. Department of Medical Physics, Memorial Sloan Kettering Cancer Center;3. Department of Epidemiology & Biostatistics, Memorial Sloan Kettering Cancer Center;4. Brain Tumor Center, Memorial Sloan Kettering Cancer Center;5. Department of Diagnostics, Imaging and Biomedical Technologies, GE Global Research;1. Central European Institute of Technology, Masaryk University, Brno, Czech Republic;2. Institute of Scientific Instruments, Academy of Sciences of the Czech Republic, Brno, Czech Republic;3. Biological Resources Imaging Laboratory, Mark Wainwright Analytical Centre, Level 4, Lowy Cancer Research Centre, UNSW Australia, Sydney, NSW 2052, Australia;4. McGill Scoliosis and Spine Centre, McGill University Health Centre, Montreal General Hospital site, A5-169, 1650 Cedar Avenue, Montreal, Quebec, H3G 1A4, Canada;5. University of Alberta, Department of Oncology, Division of Medical Physics, 8303 - 112 Street NW, Edmonton, AB, T6G 2T4, Canada;1. Department of Electric, Electronic and Computer Engineering, University of Catania, Viale Andrea Doria 6, 95125 Catania, Italy;2. Department of Biomedical Sciences, Dental and of Morphological and Functional Images, University of Messina, Via Consolare Valeria 1, 98125 Messina, Italy;3. Department of Mathematical and Computer Sciences, Physical Sciences and Earth Sciences, University of Messina, Viale F. D''alcontres 31, 98166 Messina, Italy;1. Beijing City Key Lab for Medical Physics and Engineering, Institute of Heavy Ion Physics, School of Physics, Peking University, Beijing, China;2. Center for MRI Research, Academy for Advanced Interdisciplinary Studies, Peking University, Beijing, China;3. GE Healthcare MR Research China, Beijing, China;4. McGovern Institute for Brain Research, Peking University, Beijing, China |
| |
| Abstract: | High-quality cardiac magnetic resonance (CMR) images can be hardly obtained when intrinsic noise sources are present, namely heart and breathing movements. Yet heart images may be acquired in real time, the image quality is really limited and most sequences use ECG gating to capture images at each stage of the cardiac cycle during several heart beats. This paper presents a novel super-resolution algorithm that improves the cardiac image quality using a sparse Bayesian approach. The high-resolution version of the cardiac image is constructed by combining the information of the low-resolution series –observations from different non-orthogonal series composed of anisotropic voxels – with a prior distribution of the high-resolution local coefficients that enforces sparsity. In addition, a global prior, extracted from the observed data, regularizes the solution. Quantitative and qualitative validations were performed in synthetic and real images w.r.t to a baseline, showing an average increment between 2.8 and 3.2 dB in the Peak Signal-to-Noise Ratio (PSNR), between 1.8% and 2.6% in the Structural Similarity Index (SSIM) and 2.% to 4% in quality assessment (IL-NIQE). The obtained results demonstrated that the proposed method is able to accurately reconstruct a cardiac image, recovering the original shape with less artifacts and low noise. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
