Optimization of IVIM-DKI MR Imaging model using Automatic Differentiation Methods: Enhancing the Computation Efficacy by 100 Fold

Motivation: Spatially constrained IDTV method have shown improved IVIM-DKI parameter estimation, although suffers from high time complexity preventing it to be used in clinical setup in real-time. Goal(s): This study aims to improve the computational time and efficiency of IVIM-DKI model optimization and proposes a novel spatially constrained IDIV-AD method using automatic differentiation framework. Approach: The proposed novel IDTV-AD method demonstrated at least 100 times faster computation time than the IDTV method maintaining the robustness and quality of parameter estimation. Results: Proposed novel IDTV-AD method demonstrated a time-efficient implementation and robust parameters estimation of IVIM-DKI parameters in pancreatic tumors and healthy pancreatic tissue. Impact: Novel spatially constrained IDTV-AD method using automatic differentiation demonstrated significantly fast (at least 100 times faster than the state-of-the-art method) and accurate IVIM-DKI parameter estimation, tested in clinical dataset of pancreatic cancer cohort.