Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learning

no code implementations • 29 Feb 2024 • Keying Kuang, Frances Dean, Jack B. Jedlicki, David Ouyang, Anthony Philippakis, David Sontag, Ahmed M. Alaa

We approach the digital twin modeling as a composite inverse problem, and observe that its structure resembles pretraining and finetuning in self-supervised learning (SSL).

counterfactual Self-Supervised Learning