SMURF for 2D Phase-Contrast MRI

Summary

Segmentation and velocity reconstruction from 2D phase-contrast MRI using a measurement-coupled model.

SMURF for 2D Phase-Contrast MRI
SMURF: Simultaneous Automatic Segmentation, Unwrapping and Flow Reconstruction Framework for 2D PC MRI

Overview

This project adapts the SMURF measurement-model approach to 2D phase-contrast MRI. The goal is to infer a geometry representation and a velocity field on 2D slices while accounting for phase artifacts and noise.

Work includes defining the measurement likelihood for magnitude and phase-derived velocities in 2D, implementing inference with subsampling, and producing outputs that can be used for downstream analysis. Extensions include multi-slice aggregation and consistency checks on reconstructed flow fields.

Publications

Manuscript in preparation — link forthcoming

Collaborators

External Collaborators:
  • Pavlos Vlachos

PSL Partners

Eli Lilly

Scientific Machine Learning & AI for Engineering

Join Prof. Bilionis’ Substack community for deep dives into uncertainty quantification, AI-driven simulations, and the latest laboratory updates.

Ilias Bilionis