Inference Stage Denoising for Undersampled MRI Reconstruction (2402.08692v1)
Abstract: Reconstruction of magnetic resonance imaging (MRI) data has been positively affected by deep learning. A key challenge remains: to improve generalisation to distribution shifts between the training and testing data. Most approaches aim to address this via inductive design or data augmentation. However, they can be affected by misleading data, e.g. random noise, and cases where the inference stage data do not match assumptions in the modelled shifts. In this work, by employing a conditional hyperparameter network, we eliminate the need of augmentation, yet maintain robust performance under various levels of Gaussian noise. We demonstrate that our model withstands various input noise levels while producing high-definition reconstructions during the test stage. Moreover, we present a hyperparameter sampling strategy that accelerates the convergence of training. Our proposed method achieves the highest accuracy and image quality in all settings compared to baseline methods.
- Arghya Pal et al., “A review and experimental evaluation of deep learning methods for mri reconstruction,” Machine Learning for Biomedical Imaging, vol. 1, no. March 2022 issue, pp. 1–50, 2022.
- Arturo Cárdenas-Blanco et al., “Noise in magnitude magnetic resonance images,” Concepts in Magnetic Resonance Part A: An Educational Journal, vol. 32, no. 6, pp. 409–416, 2008.
- Jinhong Huang et al., “Evaluation on the generalization of a learned convolutional neural network for mri reconstruction,” Magnetic resonance imaging, vol. 87, pp. 38–46, 2022.
- Zalan Fabian et al., “Data augmentation for deep learning based accelerated mri reconstruction with limited data,” in International Conference on Machine Learning. PMLR, 2021, pp. 3057–3067.
- Arjun D Desai et al., “Vortex: Physics-driven data augmentations using consistency training for robust accelerated mri reconstruction,” in International Conference on Medical Imaging with Deep Learning. PMLR, 2022, pp. 325–352.
- Neha Koonjoo et al., “Boosting the signal-to-noise of low-field mri with deep learning image reconstruction,” Scientific reports, vol. 11, no. 1, pp. 8248, 2021.
- Kerstin Hammernik et al., “Machine learning for mri reconstruction,” in Advances in Magnetic Resonance Technology and Applications, vol. 7, pp. 281–323. Elsevier, 2022.
- Jo Schlemper et al., “A deep cascade of convolutional neural networks for mr image reconstruction,” in Information Processing in Medical Imaging: 25th International Conference, IPMI 2017, 2017, Proceedings 25. Springer, 2017, pp. 647–658.
- Hemant K Aggarwal et al., “Modl: Model-based deep learning architecture for inverse problems,” IEEE transactions on medical imaging, vol. 38, no. 2, pp. 394–405, 2018.
- Marc Claesen et al., “Hyperparameter search in machine learning,” arXiv preprint arXiv:1502.02127, 2015.
- David Ha et al., “Hypernetworks,” arXiv preprint arXiv:1609.09106, 2016.
- Alan Q Wang et al., “Hyperrecon: Regularization-agnostic cs-mri reconstruction with hypernetworks,” in MLMIR 2021: 4th International Workshop, 2021, Proceedings 4. Springer, 2021, pp. 3–13.
- Tony CW Mok et al., “Conditional deformable image registration with convolutional neural network,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2021, 2021, Proceedings, Part IV 24. Springer, 2021, pp. 35–45.
- Yinsong Wang et al., “Conditional deformable image registration with spatially-variant and adaptive regularization,” arXiv preprint arXiv:2303.10700, 2023.
- Xun Huang et al., “Arbitrary style transfer in real-time with adaptive instance normalization,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 1501–1510.
- Andrew Hoopes et al., “Hypermorph: Amortized hyperparameter learning for image registration,” in Information Processing in Medical Imaging: 27th International Conference, IPMI 2021, 2021, Proceedings 27. Springer, 2021, pp. 3–17.
- Florian Knoll et al., “fastmri: A publicly available raw k-space and dicom dataset of knee images for accelerated mr image reconstruction using machine learning,” Radiology: Artificial Intelligence, vol. 2, no. 1, pp. e190007, 2020.
- Patricia M Johnson et al., “Evaluation of the robustness of learned mr image reconstruction to systematic deviations between training and test data for the models from the fastmri challenge,” in MLMIR 2021: 4th International Workshop, 2021, Proceedings 4. Springer, 2021, pp. 25–34.
- Jure Zbontar et al., “fastmri: An open dataset and benchmarks for accelerated mri,” arXiv preprint arXiv:1811.08839, 2018.
- Kerstin Hammernik et al., “Systematic evaluation of iterative deep neural networks for fast parallel mri reconstruction with sensitivity-weighted coil combination,” Magnetic Resonance in Medicine, vol. 86, no. 4, pp. 1859–1872, 2021.