Diffeomorphic Surface Modeling for MRI-Based Characterization of Gastric Anatomy and Motility

Abstract

Objective: Gastrointestinal magnetic resonance imaging (MRI) provides rich spatiotemporal data about the movement of the food inside the stomach, but does not directly report muscular activity on the stomach wall. Here we describe a novel approach to characterize the motility of the stomach wall that drives the volumetric changes of the ingesta. Methods: A neural ordinary differential equation was optimized to model a diffeomorphic flow that ascribed the deformation of the stomach wall to a continuous biomechanical process. Driven by this diffeomorphic flow, the surface of the stomach progressively changes its shape over time, while preserving its topology and manifoldness. Results: We teste..