PET++: Improving Localisation, Diagnosis and Quantification in Clinical and Medical PET Imaging with Randomised Optimisation
Project News Publications Team Contact Hackathons Software

Project

Positron Emission Tomography (PET) is a pillar of modern diagnostic imaging, allowing non-invasive, sensitive and specific detection of functional changes in several disease types. In endocrinology, the precise localisation of small functioning tumours of the pituitary or adrenal glands is crucial for planning curative surgery or radiotherapy. While PET imaging shows good promise for this task, initial studies suggest significant room for improvement, with improved PET imaging and subsequent more accurate localisation opening up the possibility for more adapted therapies. In dementia, the accurate quantification of PET images is key for the early detection of disease. Improved PET imaging may allow for earlier detection of dementia while asymptomatic and increased sensitivity to assess and monitor treatment once appropriate drugs have been found.

In this project mathematicians team up with researchers and clinicians from Addenbrooke's Hospital Cambridge, Dementias Platform UK (DPUK), GE Healthcare and University College London (UCL) for improved diagnosis and localization for tumours in endocrinology and earlier diagnosis of dementia with improved PET imaging. In particular, we investigate modern PET reconstruction approaches based on advanced mathematical methods to increase the PET image resolution and contrast, while keeping computational complexity low, thereby directly benefiting clinical workflow.

News

03/2023Priscilla Canizares joins our project at the Cambridge end. She replaces Billy who takes up an assitant professorship in Birmingham. Congratulations to Billy and welcome Priscilla!
01/2023New preprint: Stochastic Primal Dual Hybrid Gradient Algorithm with Adaptive Step-Sizes, Joint work with Antonin Chambolle (Paris-Dauphine, France), Claire Delplancke (Bath, UK), Carola-Bibiane Schönlieb and Junqi Tang (both Cambridge, UK).
10/2022Pawel Markiewicz joins our team in Bath. He replaces Claire who joined EDF as a research engineer over the summer. All the best to Claire and welcome Pawel!
07/2022New preprint out On the convergence and sampling of randomized primal-dual algorithms and their application to parallel MRI reconstruction. This is joint work with Eric B. Gutierrez (Bath, UK) and Claire Delplancke (Bath, UK).
05/2022Huge congratulations to Claire Deplancke who won the 2022 CoSeC Impact Award!
04/2022We're happy to announce the second hackathon dedicated to benchmarking algorithms for tomography image reconstruction, which we organize with CCP SyneRBI and CCPi. Get in touch if you'd like to join us!
11/2021We look forward the hackathon dedicated to benchmarking algorithms for tomography image reconstruction which we co-organize with CCP SyneRBI and CCPi.
09/2021We are excited for Billy Junqi Tang joining our team in Cambridge in September 2021. He will replace Jonas who joins Heriot-Watt as an assistant professor. Congratulations to Jonas and welcome Billy!
07/2021Our paper on Motion estimation and correction for simultaneous PET/MR using SIRF and CIL got published in the Philosophical Transactions A of the Royal Society. This is joint work with many people from CCP SyneRBI, in particular Richard Brown (KCL, UK) and Kris Thielemans (UCL, UK).
05/2021New book chapter out on Multi-modality Imaging with Structure-Promoting Regularizers as part of the Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging. This is a good starting point if you are interested in multi-modality imaging and guided image reconstruction.
05/2021Need an introduction to synergistic image reconstruction for multi-modality imaging? Check out our recent review paper on (An overview of) Synergistic reconstruction for multimodality/multichannel imaging methods. This is joint work with Simon Arridge and Kris Thielemans (both UCL, UK).
05/2021New paper out on Convergence Properties of a Randomized Primal-Dual Algorithm with Applications to Parallel MRI. This is joint work with Eric B. Gutierrez (Bath, UK). It will be presented by Eric at Scale Space and Variational Methods in Computer Vision.
05/2021 New paper published on the analysis of stochastic gradient descent in continuous time. Have a look!
12/2020Our paper Robust Image Reconstruction with Misaligned Structural Information got published by IEEE Access. This is joint work with Leon Bungert (Erlangen, Germany).
11/2020Presentation at the IEEE Medical Imaging Conference, on [Improving a stochastic algorithm for regularized PET image reconstruction] (poster, 1.2MB).
10/2020Presentation at the bi-weekly meetings of Institute of Nuclear Medicine, UCL [Regularized PET reconstruction with a stochastic algorithm] (slides, 1MB).
09/2020Our paper on Accelerating Variance-Reduced Stochastic Gradient Methods got accepted by Mathematical Programming.
07/2020New review paper out on Multi-modality imaging with structure-promoting regularisers. If you are new to image reconstruction from multi-modality imaging data, this is the best place to start!
06/2020Team member C. Delplancke participated to CCPi/SyneRBI vHackathon algorithm, during which Stochastic Primal-Dual Hybrid Gradient algorithm was implemented in CCPi Core Imaging Library (CIL), and to SyneRBI/STIR vHackathon PET scanner support.
04/2020New paper out on an Analysis of Stochastic Gradient Descent in Continuous Time.
04/2020New paper out on making structure-promoting regularizers robust to misalignment: Robust Image Reconstruction with Misaligned Structural Information.
04/2020Our paper on SIRF: Synergistic Image Reconstruction Framework got published in Computer Physics Communication. SIRF is a powerful software toolbox for PET-MR reconstruction.
03/2020The "collaborative computational project" (CCP) on Synergistic Reconstruction for Biomedical Imaging was funded by EPSRC. Its aim is to further develop a software framework called SIRF which we use for PET-MR image reconstruction.
10/2019New paper out on Accelerating Variance-Reduced Stochastic Gradient Methods.
10/2019Great news! Claire Delplancke will be joining our team in Bath in January 2020.
08/2019We are hosting a CCP PET-MR hackathon in Bath on September 23-24, 2019. For more infos see link.
08/2019Our paper on Faster PET reconstruction with non-smooth priors by randomization and preconditioning just got accepted in Physics in Medicine & Biology.
08/2019We are excited for Jonas Latz joining our team in Cambridge in January 2020.
03/2019EPSRC announced the funding of our project EP/S026045/1 on Improving Localisation, Diagnosis and Quantification in Clinical and Medical PET Imaging with Randomised Optimisation to start September 2019.

Publications

19.H. Y. Tan, S. Mukherjee, J. Tang, C.-B. Schönlieb, Data-Driven Mirror Descent with Input-Convex Neural Networks, to appear in SIAM Journal on Mathematics of Data Science, 2023 [preprint]
18.H. Y. Tan, S. Mukherjee, J. Tang, A. Hauptmann, C.-B. Schönlieb, Robust Data-Driven Accelerated Mirror Descent, to appear in International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023 [preprint]
17.S. R. Arridge, M. J. Ehrhardt, K. Thielemans, (An overview of) Synergistic reconstruction for multimodality/multichannel imaging methods, Philosophical Transactions of the Royal Society A 379, 20200205, 2021 [print]
16.E. B. Gutierrez, C. Delplancke, M. J. Ehrhardt, Convergence Properties of a Randomized Primal-Dual Algorithm with Applications to Parallel MRI, Elmoataz A., Fadili J., Quéau Y., Rabin J., Simon L. (eds) Scale Space and Variational Methods in Computer Vision. SSVM 2021. Lecture Notes in Computer Science, vol 12679. Springer, 2021 [print] [preprint]
15.M. J. Ehrhardt, Multi-modality imaging with structure-promoting regularisers, Springer Handbook of Mathematical Models and Algorithms in Computer Vision and Imaging, 2021 [print] [preprint] [software@github]
14.R. Brown, C. Kolbitsch, C. Delplancke, E. Papoutsellis, J. Mayer, E. Ovtchinnikov, E. Pasca, R. Neji, C. da Costa-Luis, A. G. Gillman, M. J. Ehrhardt, J. R. McClelland, B. Eiben and K. Thielemans, Motion estimation and correction for simultaneous PET/MR using SIRF and CIL, Philosophical Transactions of the Royal Society A 379, 20200208, 2021 [print]
13.E. Papoutsellis, E. Ametova, C. Delplancke, G. Fardell, J. S. Jørgensen, E. Pasca, M. Turner, R. Warr, W. R. B. Lionheart and P. J. Withers, Core Imaging Library – Part II: Multichannel reconstruction for dynamic and spectral tomography, Philosophical Transactions of the Royal Society A 379, 2021 [print]
12.J. Latz, Analysis of stochastic gradient descent in continuous time, Statistics and Computing 31(39), 2021 [arXiv] [print]
11.J. Budd, Y. van Gennip, J. Latz, Classification and image processing with a semi-discrete scheme for fidelity forced Allen–Cahn on graphs, GAMM Mitteilungen 44(1), e202100004, 2021 [arXiv] [print]
10.C. Delplancke, M. J. Ehrhardt and K. Thielemans, Accelerated Convergent Motion Compensated Image Reconstruction, IEEE Medical Imaging Conference, 2021
9.E. Ovtchinnikov, R. Brown, C. Kolbitsch, E. Pasca, C. da Costa-Luis, A. G. Gillman, B. A. Thomas, N. Efthimiou, J. Mayer, P. Wadhwa, M. J. Ehrhardt, S. Ellis, J. S. Jørgensen, J. Matthews, C. Prieto, A. J. Reader, C. Tsoumpas, M. Turner, D. Atkinson, K. Thielemans, SIRF: Synergistic Image Reconstruction Framework, Computer Physics Communication 249, 107087, 2020 [print]
8.C. Delplancke, M. Gurnell, J. Latz, P. J. Markiewicz, C.-B. Schönlieb and M. J. Ehrhardt, Improving a Stochastic Algorithm for Regularized PET Image Reconstruction, IEEE Medical Imaging Conference, 2020 [print]
7.D. Driggs, M. J. Ehrhardt, C.-B. Schönlieb, Accelerating Variance-Reduced Stochastic Gradient Methods, Mathematical Programming, 2020 [print] [preprint]
6.L. Bungert, M. J. Ehrhardt, Robust Image Reconstruction with Misaligned Structural Information, IEEE Access 8, 222944-222955, 2020 [preprint] [print] [software@github]
5.M. J. Ehrhardt, P. J. Markiewicz, C.-B. Schönlieb, Faster PET Reconstruction with Non-Smooth Priors by Randomization and Preconditioning, Physics in Medicine & Biology 64(22), 225019, 2019 [preprint] [IOP] [slides (<1MB)]
4.D. Kazantsev, E. Pasca, M. Basham, M. Turner, M. J. Ehrhardt, K. Thielemans, B. A. Thomas, E. Ovtchinnikov, P. J. Withers, A. W. Ashton, Versatile regularisation toolkit for iterative image reconstruction with proximal splitting algorithms, Proceedings of SPIE 11072 Fully 3D, 2019 [print]
3.A. Chambolle, M. J. Ehrhardt, P. Richtárik, C.-B. Schönlieb, Stochastic Primal-Dual Hybrid Gradient Algorithm with Arbitrary Sampling and Imaging Applications, SIAM Journal on Optimization 28(4), 2783-2808, 2018 [print] [preprint] [slides (<1MB)] [poster (2 MB)] [software@github] [software@ODL]
2.P. J. Markiewicz, M. J. Ehrhardt, K. Erlandsson, P. J. Noonan, A. Barnes, J. M Schott, D. Atkinson, S. R. Arridge, B. F. Hutton, S. Ourselin, NiftyPET: A high-throughput software platform for high quantitative accuracy and precision PET imaging and analysis, Neuroinformatics 16(1), 95–115, 2018 [print] [software]
1.M. J. Ehrhardt, P. Markiewicz, A. Chambolle, P. Richtárik, J. Schott, C.-B. Schönlieb, Faster PET Reconstruction with a Stochastic Primal-Dual Hybrid Gradient Method, Proceedings of SPIE, 2017 [SPIE library] [preprint (2 MB)] [poster (2 MB)]

Preprints

-Hong Ye Tan, Subhadip Mukherjee, Junqi Tang, Carola-Bibiane Schönlieb, Provably Convergent Plug-and-Play Quasi-Newton Methods, 2023 [preprint]
-A. Chambolle, C. Delplancke, M. J. Ehrhardt, C.-B. Schönlieb, J. Tang, Stochastic Primal Dual Hybrid Gradient Algorithm with Adaptive Step-Sizes, 2023 [preprint]
-J. Tang, S. Mukherjee, C.-B. Schönlieb, Accelerating Deep Unrolling Networks via Dimensionality Reduction, 2022 [preprint]
-E. B. Gutierrez, C. Delplancke, M. J. Ehrhardt, On the convergence and sampling of randomized primal-dual algorithms and their application to parallel MRI reconstruction, 2022 [preprint]
-J. Tang, M. J. Ehrhardt, C.-B. Schönlieb, Stochastic Primal-Dual Three Operator Splitting with Arbitrary Sampling and Preconditioning, 2022 [preprint]
-J. Tang, Data-Consistent Local Superresolution for Medical Imaging, 2022 [preprint]

Presentations

12. Advanced Image Reconstruction Methods, UCL, UK, 2022. Randomized Image Reconstruction, 2022 [video]
11. Mathematics of Data Science Seminar, University of Graz, Austria (virtual). A Randomized Algorithm for Convex Optimization and Medical Imaging Applications, 2022
10. SIAM Conference on Data Science (virtual). Adaptive Primal-Dual Stochastic Algorithm for Inverse Problems, 2022 [slides (1MB)]
9. SIAM Imaging Science (virtual). Robust Image Reconstruction with Misaligned Structural Information, 2022
8. SIAM Imaging Science (virtual). A fast stochastic algorithm and application to Tomographic Imaging, 2022
7. SIMAI 2020+2021 conference, Parma. A Fast Stochastic Algorithm for Regularized PET Reconstruction, 2021
6. SIAM Conference on Optimization (virtual). A Fast Stochastic Algorithm for Regularized PET Reconstruction, 2021
5. IEEE Medical Imaging Conference (virtual). Accelerated Convergent Motion Compensated Image Reconstruction, 2021 [slides (7MB)]
4. Synergistic Reconstruction Symposium, Chester, UK. Faster PET Reconstruction with Non-Smooth Anatomical Priors by Randomization and Preconditioning, 2019 [slides (2MB)]
3. Applied Mathematics Seminar, University of Leicester, UK. A Randomized Algorithm for Non-Smooth Optimization and Medical Imaging Applications, 2019 [slides (1MB)]
2. Quantitative Imaging of Electrochemical Interfaces Workshop, Diamond Light Source, Harwell Campus, UK. 1 + 1 > 2? Getting More Out of Multi-Modality Imaging, 2019 [slides (8MB)]
1. 2nd IMA Conference On Inverse Problems From Theory To Application, London, UK. Faster PET Reconstruction with Non-Smooth Priors by Randomization, 2019 [slides (7MB)] [paper, IOP] [preprint]

Team

Project Leads

Medical and Clinical Project Team

Researchers

PhD Students

Project Collaborators

Advisory Board

Contact

Carola-Bibiane Schönlieb
cbs31@cam.ac.uk
University of Cambridge, UK

Useful Links

Hackathons

PET++, CCP SyneRBI and CCPi jointly organize two hackathons on algorithms benchmark for medical imaging reconstruction. The first one will take place on November 2021 and the second one in January 2022. The goal of the hackathons is to establish a benchmark between the numerous iterative algorithms for CT and PET reconstructions which have been proposed in the recent years, with a focus on randomized algorithms.

Hackathon 2021 November 23-26

The goal of the hackathon is to implement selected randomized algorithms in CIL (eg SAGA, SVRG) and test them on a toy dataset jointly with already implemented algorithms (eg SPDHG). There will also be a group working on subset data structures in STIR to enable efficient computation on subsets. More details here.

Hackathon 2022 April 4-7

The goal of this hackathon is to establish the practical framework for benchmarking the several state-of-the-art iterative algorithms for PET and/or CT reconstruction which have been implemented in the first hackathon. More details here.
© 2019-23 PET++ team - last updated: March 2023