Cardiac MRI Reconstruction Challenge

Cardiac magnetic resonance imaging (CMR) has become an important imaging modality for diagnosing cardiac disease due to its superior soft tissue contrast and non-invasiveness. However, an inherent drawback of MRI is that the imaging speed is particularly slow, which will cause discomfort to patients and introduce motion artifacts into images. CMR image reconstruction from highly under-sampled k-space (raw data) has become a hot research topic. Recently, a large number of AI-based image reconstruction algorithms have shown the potential to improve imaging performance through highly under-sampling data. However, the field of CMR reconstruction still lacks public, standardized, and high-quality datasets. To date, NYU Langone Health has released 'fastMRI' dataset, containing multi-channel knee and brain MRI raw data. However, these images are inadequate for 3D+1D (time domain) applications in cardiac imaging. The goal of establishing 'CMRxRecon' dataset is to provide a benchmark dataset that enables the broad research community to participate in this important work of accelerated CMR imaging. Thus, we design two tasks for the ‘CMRxRecon’ challenge: 1) accelerated cine reconstruction task and 2) accelerated T1&T2 mapping task. The challenge will consist of both single-coil and multi-coil MRI raw data. For the training dataset, fully sampled k-space data will be acquired and provided to the participant groups. For the validation and test datasets, paired fully sampled k-space data and corresponding prospectively under-sampled data (with acceleration factors from 4x, 8x, 10x) will be obtained from healthy volunteers and released