Deep kernel representations of latent space features for low-dose PET-MR imaging robust to variable dose reduction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Pain, Cameron Dennis, George, Yasmeen, Fornito, Alex, Egan, Gary, Chen, Zhaolin
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910597426184192
author Pain, Cameron Dennis
George, Yasmeen
Fornito, Alex
Egan, Gary
Chen, Zhaolin
author_facet Pain, Cameron Dennis
George, Yasmeen
Fornito, Alex
Egan, Gary
Chen, Zhaolin
contents Low-dose positron emission tomography (PET) image reconstruction methods have potential to significantly improve PET as an imaging modality. Deep learning provides a promising means of incorporating prior information into the image reconstruction problem to produce quantitatively accurate images from compromised signal. Deep learning-based methods for low-dose PET are generally poorly conditioned and perform unreliably on images with features not present in the training distribution. We present a method which explicitly models deep latent space features using a robust kernel representation, providing robust performance on previously unseen dose reduction factors. Additional constraints on the information content of deep latent features allow for tuning in-distribution accuracy and generalisability. Tests with out-of-distribution dose reduction factors ranging from $\times 10$ to $\times 1000$ and with both paired and unpaired MR, demonstrate significantly improved performance relative to conventional deep-learning methods trained using the same data. Code:https://github.com/cameronPain
format Preprint
id arxiv_https___arxiv_org_abs_2409_06198
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep kernel representations of latent space features for low-dose PET-MR imaging robust to variable dose reduction
Pain, Cameron Dennis
George, Yasmeen
Fornito, Alex
Egan, Gary
Chen, Zhaolin
Computer Vision and Pattern Recognition
Low-dose positron emission tomography (PET) image reconstruction methods have potential to significantly improve PET as an imaging modality. Deep learning provides a promising means of incorporating prior information into the image reconstruction problem to produce quantitatively accurate images from compromised signal. Deep learning-based methods for low-dose PET are generally poorly conditioned and perform unreliably on images with features not present in the training distribution. We present a method which explicitly models deep latent space features using a robust kernel representation, providing robust performance on previously unseen dose reduction factors. Additional constraints on the information content of deep latent features allow for tuning in-distribution accuracy and generalisability. Tests with out-of-distribution dose reduction factors ranging from $\times 10$ to $\times 1000$ and with both paired and unpaired MR, demonstrate significantly improved performance relative to conventional deep-learning methods trained using the same data. Code:https://github.com/cameronPain
title Deep kernel representations of latent space features for low-dose PET-MR imaging robust to variable dose reduction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.06198