Multi-Subject Image Synthesis as a Generative Prior for Single-Subject PET Image Reconstruction
December 05, 2024 Β· Declared Dead Β· π 2024 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector Conference (RTSD)
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
George Webber, Yuya Mizuno, Oliver D. Howes, Alexander Hammers, Andrew P. King, Andrew J. Reader
arXiv ID
2412.04324
Category
physics.med-ph
Cross-listed
cs.CV
Citations
1
Venue
2024 IEEE Nuclear Science Symposium (NSS), Medical Imaging Conference (MIC) and Room Temperature Semiconductor Detector Conference (RTSD)
Last Checked
3 months ago
Abstract
Large high-quality medical image datasets are difficult to acquire but necessary for many deep learning applications. For positron emission tomography (PET), reconstructed image quality is limited by inherent Poisson noise. We propose a novel method for synthesising diverse and realistic pseudo-PET images with improved signal-to-noise ratio. We also show how our pseudo-PET images may be exploited as a generative prior for single-subject PET image reconstruction. Firstly, we perform deep-learned deformable registration of multi-subject magnetic resonance (MR) images paired to multi-subject PET images. We then use the anatomically-learned deformation fields to transform multiple PET images to the same reference space, before averaging random subsets of the transformed multi-subject data to form a large number of varying pseudo-PET images. We observe that using MR information for registration imbues the resulting pseudo-PET images with improved anatomical detail compared to the originals. We consider applications to PET image reconstruction, by generating pseudo-PET images in the same space as the intended single-subject reconstruction and using them as training data for a diffusion model-based reconstruction method. We show visual improvement and reduced background noise in our 2D reconstructions as compared to OSEM, MAP-EM and an existing state-of-the-art diffusion model-based approach. Our method shows the potential for utilising highly subject-specific prior information within a generative reconstruction framework. Future work may compare the benefits of our approach to explicitly MR-guided reconstruction methodologies.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β physics.med-ph
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Gibbs-Ringing Artifact Removal Based on Local Subvoxel-shifts
R.I.P.
π»
Ghosted
Deep Learning-enabled Virtual Histological Staining of Biological Samples
R.I.P.
π»
Ghosted
Eigenspectra optoacoustic tomography achieves quantitative blood oxygenation imaging deep in tissues
π
π
The Cartographer
Deep learning for biomedical photoacoustic imaging: A review
R.I.P.
π»
Ghosted
The reliability of a deep learning model in clinical out-of-distribution MRI data: a multicohort study
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Neural Architecture Search with Reinforcement Learning
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted