Scan-specific Self-supervised Bayesian Deep Non-linear Inversion for Undersampled MRI Reconstruction
arXiv:2203.00361 · doi:10.1109/TMI.2024.3364911
Abstract
Magnetic resonance imaging is subject to slow acquisition times due to the inherent limitations in data sampling. Recently, supervised deep learning has emerged as a promising technique for reconstructing sub-sampled MRI. However, supervised deep learning requires a large dataset of fully-sampled data. Although unsupervised or self-supervised deep learning methods have emerged to address the limitations of supervised deep learning approaches, they still require a database of images. In contrast, scan-specific deep learning methods learn and reconstruct using only the sub-sampled data from a single scan. Here, we introduce Scan-Specific Self-Supervised Bayesian Deep Non-Linear Inversion (DNLINV) that does not require an auto calibration scan region. DNLINV utilizes a deep image prior-type generative modeling approach and relies on approximate Bayesian inference to regularize the deep convolutional neural network. We demonstrate our approach on several anatomies, contrasts, and sampling patterns and show improved performance over existing approaches in scan-specific calibrationless parallel imaging and compressed sensing.
References in corpus (18)
- Adam: A Method for Stochastic Optimization
- Decoupled Weight Decay Regularization
- Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
- Deep Image Prior
- fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
- Self-Supervised Learning of Physics-Guided Reconstruction Neural Networks without Fully-Sampled Reference Data
- RARE: Image Reconstruction using Deep Priors Learned without Ground Truth
- Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Models
- Linear Predictability in MRI Reconstruction: Leveraging Shift-Invariant Fourier Structure for Faster and Better Imaging
- MRI Reconstruction Using Deep Bayesian Estimation
- LORAKI: Autocalibrated Recurrent Neural Networks for Autoregressive MRI Reconstruction in k-Space
- Accelerated Coronary MRI with sRAKI: A Database-Free Self-Consistent Neural Network k-space Reconstruction for Arbitrary Undersampling
- Scan Specific Artifact Reduction in K-space (SPARK) Neural Networks Synergize with Physics-based Reconstruction to Accelerate MRI
- Zero-Shot Self-Supervised Learning for MRI Reconstruction
- ENLIVE: An Efficient Nonlinear Method for Calibrationless and Robust Parallel Imaging
- Unsupervised Deep Basis Pursuit: Learning inverse problems without ground-truth data
- Scan-specific Self-supervised Bayesian Deep Non-linear Inversion for Undersampled MRI Reconstruction
- Memory Efficient Model Based Deep Learning Reconstructions for High Spatial Resolution 3D Non-Cartesian Acquisitions