Toggle Main Menu Toggle Search

Open Access padlockePrints

Evaluating a radiotherapy deep learning synthetic CT algorithm for PET-MR attenuation correction in the pelvis

Lookup NU author(s): JJ Wyatt, Dr Rachel Pearson, Dr George Petrides, Dr Hazel McCallum, Dr Ross Maxwell

Downloads


Licence

This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).


Abstract

© 2024, The Author(s). Background: Positron emission tomography–magnetic resonance (PET-MR) attenuation correction is challenging because the MR signal does not represent tissue density and conventional MR sequences cannot image bone. A novel zero echo time (ZTE) MR sequence has been previously developed which generates signal from cortical bone with images acquired in 65 s. This has been combined with a deep learning model to generate a synthetic computed tomography (sCT) for MR-only radiotherapy. This study aimed to evaluate this algorithm for PET-MR attenuation correction in the pelvis. Methods: Ten patients being treated with ano-rectal radiotherapy received a 18 F-FDG-PET-MR in the radiotherapy position. Attenuation maps were generated from ZTE-based sCT (sCTAC) and the standard vendor-supplied MRAC. The radiotherapy planning CT scan was rigidly registered and cropped to generate a gold standard attenuation map (CTAC). PET images were reconstructed using each attenuation map and compared for standard uptake value (SUV) measurement, automatic thresholded gross tumour volume (GTV) delineation and GTV metabolic parameter measurement. The last was assessed for clinical equivalence to CTAC using two one-sided paired t tests with a significance level corrected for multiple testing of p≤ 0.05 / 7 = 0.007 . Equivalence margins of ± 3.5 % were used. Results: Mean whole-image SUV differences were −0.02% (sCTAC) compared to −3.0% (MRAC), with larger differences in the bone regions (−0.5% to −16.3%). There was no difference in thresholded GTVs, with Dice similarity coefficients ≥ 0.987 . However, there were larger differences in GTV metabolic parameters. Mean differences to CTAC in SUV max were 1.0 ± 0.8 % (± standard error, sCTAC) and - 4.6 ± 0.9 % (MRAC), and 1.0 ± 0.7 % (sCTAC) and - 4.3 ± 0.8 % (MRAC) in SUV mean . The sCTAC was statistically equivalent to CTAC within a ± 3.5 % equivalence margin for SUV max and SUV mean (p= 0.007 and p= 0.002), whereas the MRAC was not (p= 0.88 and p= 0.83). Conclusion: Attenuation correction using this radiotherapy ZTE-based sCT algorithm was substantially more accurate than current MRAC methods with only a 40 s increase in MR acquisition time. This did not impact tumour delineation but did significantly improve the accuracy of whole-image and tumour SUV measurements, which were clinically equivalent to CTAC. This suggests PET images reconstructed with sCTAC would enable accurate quantitative PET images to be acquired on a PET-MR scanner.


Publication metadata

Author(s): Wyatt JJ, Kaushik S, Cozzini C, Pearson RA, Petrides G, Wiesinger F, McCallum HM, Maxwell RJ

Publication type: Article

Publication status: Published

Journal: EJNMMI Physics

Year: 2024

Volume: 11

Online publication date: 29/01/2024

Acceptance date: 15/01/2024

Date deposited: 07/02/2024

ISSN (electronic): 2197-7364

Publisher: Springer Nature

URL: https://doi.org/10.1186/s40658-024-00617-3

DOI: 10.1186/s40658-024-00617-3

Data Access Statement: The datasets used and/or analysed during the current study are available from the corresponding author on reasonable request.


Altmetrics

Altmetrics provided by Altmetric


Funding

Funder referenceFunder name
210995
19037EIT Health e.V.
20648
United Kingdom Research and Innovation council

Share