Application-Driven MRI: Joint Reconstruction and Segmentation from Undersampled MRI Data
Medical image segmentation has traditionally been regarded as a separate process from image acquisition and reconstruction, even though its performance directly depends on the quality and characteristics of these first stages of the imaging pipeline. Adopting an integrated acquisition-reconstruction-segmentation process can provide a more efficient and accurate solution. In this paper we propose a joint segmentation and reconstruction algorithm for undersampled magnetic resonance data. Merging a reconstructive patch-based sparse modelling and a discriminative Gaussian mixture modelling can produce images with enhanced edge information ultimately improving their segmentation.
KeywordsDiscrete Cosine Transform Gaussian Mixture Model Compress Sense Sparse Code Magnetic Resonance Imaging Data
- 1.Bishop, C.M.: Pattern recognition and machine learning. Springer, New York (2006)Google Scholar
- 8.Hsiao, I.T., Rangarajan, A., Gindi, G.: Joint-MAP reconstruction/segmentation for transmission tomography using mixture-models as priors. IEEE Nucl. Sci. Symp. Conf. Rec. 3, 1689–1693 (1998)Google Scholar
- 12.de Sompel, D.V., Brady, M.: Simultaneous reconstruction and segmentation algorithm for positron emission tomography and transmission tomography. In: ISBI 2008, pp. 1035–1038. IEEE (2008)Google Scholar
- 14.Virtue, P., Uecker, M., Elad, M., Lustig, M.: Predicting image quality of under-sampled data reconstruction in the presence of noise. In: Proc. 21st Annual Meeting ISMRM, Salt Lake City, Utah, USA, p. 2668 (2013)Google Scholar