Unsupervised Knowledge-Transfer for Learned Image Reconstruction

Abstract

Deep learning-based image reconstruction approaches have demonstrated impressive empirical performance in many imaging modalities. These approaches usually require a large amount of high-quality paired training data, which is often not available in medical imaging. To circumvent this issue we develop a novel unsupervised knowledge-transfer paradigm for learned reconstruction within a Bayesian framework. The proposed approach learns a reconstruction network in two phases. The first phase trains a reconstruction network with a set of ordered pairs comprising of ground truth images of ellipses and the corresponding simulated measurement data. The second phase fine-tunes the pretrained network to more realistic measurement data without supervision. By construction, the framework is capable of delivering predictive uncertainty information over the reconstructed image. We present extensive experimental results on low-dose and sparse-view computed tomography showing that the approach is competitive with several state-of-the-art supervised and unsupervised reconstruction techniques. Moreover, for test data distributed differently from the training data, the proposed framework can significantly improve reconstruction quality not only visually, but also quantitatively in terms of PSNR and SSIM, when compared with learned methods trained on the synthetic dataset only.

References in corpus (19)

• Auto-Encoding Variational Bayes
• What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?
• Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
• Deep Convolutional Neural Network for Inverse Problems in Imaging
• Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)
• Weight Uncertainty in Neural Networks
• On instabilities of deep learning in image reconstruction - Does AI come at a cost?
• Learned Primal-dual Reconstruction
• Solving ill-posed inverse problems using iterative deep neural networks
• Test-Time Adaptable Neural Networks for Robust Medical Image Segmentation
• Computed Tomography Reconstruction Using Deep Image Prior and Learned Reconstruction Methods
• Practical Deep Learning with Bayesian Principles
• The LoDoPaB-CT Dataset: A Benchmark Dataset for Low-Dose CT Reconstruction Methods
• Regularization by architecture: A deep prior approach for inverse problems
• Unsupervised Deep Learning Methods for Biological Image Reconstruction and Enhancement
• Combining Weighted Total Variation and Deep Image Prior for natural and medical image restoration via ADMM
• Higher-order total variation approaches and generalisations
• A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning
• Quantifying Sources of Uncertainty in Deep Learning-Based Image Reconstruction

Cited by in corpus (1)

• An Educated Warm Start For Deep Image Prior-Based Micro CT Reconstruction