CoilDrop-MRI: Self-supervised physics-guided MRI reconstruction with coil dropout
Researchers have developed CoilDrop-MRI, a novel self-supervised deep learning method for accelerating MRI reconstruction. This technique applies coil-wise dropout to acquired data, using the dropped portions as training targets. CoilDrop-MRI has been validated across various datasets and imaging conditions, demonstrating superior performance compared to existing self-supervised methods and achieving quality comparable to supervised approaches without needing fully sampled reference data. AI