期刊
INVERSE PROBLEMS
卷 38, 期 10, 页码 -出版社
IOP Publishing Ltd
DOI: 10.1088/1361-6420/ac8a91
关键词
unsupervised learning; pretraining; image reconstruction; Bayesian deep learning; computed tomography
资金
- i4health PhD studentship (UK EPSRC) [EP/S021930/1]
- Alan Turing Institute (UK EPSRC) [EP/N510129/1]
- UK EPSRC [EP/V026259/1]
- Academy of Finland [336796, 334817, 338408]
- Academy of Finland (AKA) [336796, 334817, 334817] Funding Source: Academy of Finland (AKA)
This research proposes a novel unsupervised knowledge-transfer paradigm for learned reconstruction in medical imaging within a Bayesian framework. The approach learns a reconstruction network in two phases and is capable of delivering predictive uncertainty information over the reconstructed image. Experimental results demonstrate the competitiveness of the approach in low-dose and sparse-view computed tomography, with significant improvements in reconstruction quality both visually and quantitatively.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据