Inferring Oocyte Cytoplasmic Material Properties from Cytoplasmic Streaming Movies Using Physics-Informed Neural Networks

Alokendra Ghosh, Tetsuya Hiraiwa, Xing Duan, Rong Li

Submission Type: I want my submission to be considered for both oral and poster presentation.

Keywords: Physics-informed neural networks (PINNs), oocyte quality, cytoplasmic streaming, inverse problems, viscosity inference, incompressible fluid dynamics, optical flow, microrheology validation, assisted reproductive technology

TL;DR: A physics-informed neural network infers cytoplasmic viscosity from oocyte streaming movies, yielding estimates consistent with bead-based microrheology and reliably capturing sample-to-sample variation across multiple oocytes and initializations.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 414