A Master Class on Reproducibility: A Student Hackathon on Advanced MRI Reconstruction Methods
This addresses reproducibility challenges for researchers and students in medical imaging, but it is incremental as it focuses on replicating existing methods rather than introducing new ones.
The paper tackled the problem of reproducibility in advanced MRI reconstruction methods by organizing a student hackathon to replicate results from three influential papers, resulting in documented outcomes and practices for building reproducible codebases.
We report the design, protocol, and outcomes of a student reproducibility hackathon focused on replicating the results of three influential MRI reconstruction papers: (a) MoDL, an unrolled model-based network with learned denoising; (b) HUMUS-Net, a hybrid unrolled multiscale CNN+Transformer architecture; and (c) an untrained, physics-regularized dynamic MRI method that uses a quantitative MR model for early stopping. We describe the setup of the hackathon and present reproduction outcomes alongside additional experiments, and we detail fundamental practices for building reproducible codebases.