Medical Imaging · fastMRI Challenge 2019
fastMRI: AI for faster MRI
Read the paperA research collaboration exploring how artificial intelligence can accelerate MRI scans and reconstruction.
The project
fastMRI was a collaboration between Facebook AI Research (FAIR) and NYU Langone to investigate using AI to make MRI scans faster. The 2019 fastMRI challenge invited research teams to reconstruct diagnostic-quality MRI images from undersampled data, helping advance more efficient imaging.
My contribution
During my postdoctoral research at Leiden University Medical Center (LUMC), I contributed to the Philips–LUMC team that won the most challenging part of the 2019 challenge. The team developed an algorithm to reconstruct near-intact knee MRI images using one-eighth of the usual data.