DINE is applied to two registration backbones, Robust-DefReg and DefTransNet, using a two-stage strategy: a first-stage model is trained with Chamfer distance, its predicted deformation fields are used to estimate a prior, and the model is then refined with a combined distance and negative log-prior objective.
Sara Monji-Azad, Rohit Beer, M. Kinz et al.· arXiv.org· 1 citation
It is concluded that a simple MLP can provide high-quality QTI parameter estimates from short tensor-valued diffusion acquisitions, which enables five-minute, high-resolution QTI and may encourage further clinical studies of markers such as microscopic fractional anisotropy.
Oliver Gödicke, Jin-Yang Yu, F. Laun et al.· Magnetic Resonance Imaging· 0 citations
Fast dMRI protocols for obtaining rotational invariants of the cumulant expansion were paired with constrained weighted linear least squares (CWLLS) to stabilize the more fragile WLLS fit, yielding high-quality parameter maps at an online-ready computational cost.
Jin-Yang Yu, Oliver Gödicke, F. Laun et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.