Optimal Transport driven Cycle-consistent Generative Adversarial Network (OT-CycleGAN) for an accurate MR water-fat separation
Juan Pablo Meneses1,2,3, Cristobal Arrieta1,2, Gabriel della Maggiora1,2, Pablo Irarrazaval1,2,3,4, Cristian Tejos1,2,3, Marcelo Andia1,2,5, Sergio Uribe1,2,5, and Carlos Sing Long1,2,4,6,7
1Biomedical Imaging Center, Pontificia Universidad Católica de Chile, Santiago, Chile, 2ANID – Millennium Science Initiative Program – Millennium Nucleus for Cardiovascular Magnetic Resonance, Santiago, Chile, 3Electrical Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile, 4Institute for Biological and Medical Engineering, Pontificia Universidad Catolica de Chile, Santiago, Chile, 5Radiology Department, School of Medicine, Pontificia Universidad Catolica de Chile, Santiago, Chile, 6Institute for Mathematical & Computational Engineering, Pontificia Universidad Catolica de Chile, Santiago, Chile, 7ANID – Millennium Science Initiative Program – Millennium Nucleus for Discovery of Structure in Complex Data, Santiago, Chile
MRI water-fat separation is an ill-posed inverse problem usually addressed using complex numerical methods. This problem is related to an MR signal physical model that includes the effects of R2* signal decay ratio and main magnetic field inhomogeneities (Δf), which induce non-linearities that are related to the ill-posedness of the inverse problem. In this work, we propose an Optimal Transport driven Cycle-consistent Generative Adversarial Networks (OT-CycleGAN) framework, which is physics-based, and could use partially labeled training data to estimate the non-linear components (R2* and Δf), and posteriorly compute the water-fat images through a conventional least-squares approach.
This abstract and the presentation materials are available to members only;
a login is required.