MRI Recovery with Self-Calibrated Denoisers without Fully-Sampled Data

In many MRI applications, acquiring fully sampled training data is challenging. We present a self-supervised image reconstruction method, termed ReSiDe, capable of recovering images solely from undersampled data. ReSiDe is inspired by plug-and-play (PnP) methods and employs a denoiser as a regularizer. However, unlike traditional PnP approaches that utilize generic denoisers or train application-specific denoisers using high-quality images or image patches, ReSiDe directly trains the denoiser on the image or images that are being reconstructed from the undersampled data. We introduce two variations of our method: ReSiDe-S and ReSiDe-M. ReSiDe-S is scan-specific and works with a single set of undersampled measurements, while ReSiDe-M operates on multiple sets of undersampled measurements. More importantly, the denoisers trained in ReSiDe-M are stored for faster PnP-based inference without further training. To improve robustness, the denoising strength in ReSiDe is auto-tuned using the discrepancy principle. Studies I, II, and III compare ReSiDe-S and ReSiDe-M against other self-supervised or unsupervised methods using data from T1- and T2-weighted brain MRI, MRXCAT digital perfusion phantom, and first-pass cardiac perfusion, respectively. ReSiDe-S and ReSiDe-M outperform other methods in terms of reconstruction signal-to-noise ratio and structural similarity index measure for Studies I and II, and in terms of expert scoring for Study III. In summary, we present a self-supervised image reconstruction method and validate it in both static and dynamic MRI applications. These developments can benefit MRI applications where the availability of fully sampled training data is limited.