University of Oulu

Riccardo Barbano et al 2022 Inverse Problems in press https://doi.org/10.1088/1361-6420/ac8a9

Unsupervised knowledge-transfer for learned image reconstruction

Saved in:
Author: Barbano, Riccardo1; Kereta, Zeljko2; Hauptmann, Andreas3;
Organizations: 1Department of Computer Science, University College London, 169 Euston Rd, London NW1 2AE, London, WC1E 6BT, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND
2Department of Computer Science, UCL, 169 Euston Rd, London NW1 2AE, London, WC1E 6BT, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND
3Department of Computer Science, University of Oulu, Research Unit of Mathematical Sciences, Pentti Kaiteran katu 1 Linnanmaa, Oulu, Pohjois-Pohjanmaa, 90014, FINLAND
4Department of Computer Science, University College London, Gower Street, LONDON, WC1E 6BT, London, London, WC1E 6BT, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND
5Department of Computer Science, University College London, 169 Euston Rd, London NW1 2AE, London, London, WC1E 6BT, UNITED KINGDOM OF GREAT BRITAIN AND NORTHERN IRELAND
Format: article
Version: accepted version
Access: open
Online Access: PDF Full Text (PDF, 3.9 MB)
Persistent link: http://urn.fi/urn:nbn:fi-fe2022083156855
Language: English
Published: IOP Publishing, 2022
Publish Date: 2022-08-31
Description:

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.

see all

Series: Inverse problems
ISSN: 0266-5611
ISSN-E: 1361-6420
ISSN-L: 0266-5611
Issue: Accepted manuscript
DOI: 10.1088/1361-6420/ac8a91
OADOI: https://oadoi.org/10.1088/1361-6420/ac8a91
Type of Publication: A1 Journal article – refereed
Field of Science: 111 Mathematics
112 Statistics and probability
113 Computer and information sciences
217 Medical engineering
Subjects:
Funding: Academy of Finland Projects 336796, 334817, 338408.
Academy of Finland Grant Number: 336796
334817
338408
Detailed Information: 336796 (Academy of Finland Funding decision)
334817 (Academy of Finland Funding decision)
338408 (Academy of Finland Funding decision)
Copyright information: © 2022 The Author(s). Published by IOP Publishing Ltd. As the Version of Record of this article is going to be/has been published on a gold open access basis under a CC BY 3.0 licence, this Accepted Manuscript is available for reuse under a CC BY 3.0 licence immediately. Although reasonable endeavours have been taken to obtain all necessary permissions from third parties to include their copyrighted content within this article, their full citation and copyright line may not be present in this Accepted Manuscript version. Before using any content from this article, please refer to the Version of Record on IOPscience once published for full citation and copyright details, as permission may be required. All third party content is fully copyright protected, and is not published on a gold open access basis under a CC BY licence, unless that is specifically stated in the figure caption in the Version of Record.
  https://creativecommons.org/licenses/by/3.0/