Clinical and Phantom Validation of a Deep Learning Based Denoising Algorithm for F-18-FDG PET Images from Lower Detection Counting in Comparison with the Standard Acquisition

Overview

Journal EJNMMI Phys

Specialty Radiology

Date 2022 May 11

PMID 35543894

Authors

Gerald Bonardel

Axel Dupont

Pierre Decazes

Mathieu Queneau

Romain Modzelewski

Jeremy Coulot

Nicolas Le Calvez

Sebastien Hapdey

Affiliations

Soon will be listed here.

Abstract

Background: PET/CT image quality is directly influenced by the F-18-FDG injected activity. The higher the injected activity, the less noise in the reconstructed images but the more radioactive staff exposition. A new FDA cleared software has been introduced to obtain clinical PET images, acquired at 25% of the count statistics considering US practices. Our aim is to determine the limits of a deep learning based denoising algorithm (SubtlePET) applied to statistically reduced PET raw data from 3 different last generation PET scanners in comparison to the regular acquisition in phantom and patients, considering the European guidelines for radiotracer injection activities. Images of low and high contrasted (SBR = 2 and 5) spheres of the IEC phantom and high contrast (SBR = 5) of micro-spheres of Jaszczak phantom were acquired on 3 different PET devices. 110 patients with different pathologies were included. The data was acquired in list-mode and retrospectively reconstructed with the regular acquisition count statistic (PET100), 50% reduction in counts (PET50) and 66% reduction in counts (PET33). These count reduced images were post-processed with SubtlePET to obtain PET50 + SP and PET33 + SP images. Patient image quality was scored by 2 senior nuclear physicians. Peak-signal-to-Noise and Structural similarity metrics were computed to compare the low count images to regular acquisition (PET100).

Results: SubtlePET reliably denoised the images and maintained the SUV values in PET50 + SP. SubtlePET enhanced images (PET33 + SP) had slightly increased noise compared to PET100 and could lead to a potential loss of information in terms of lesion detectability. Regarding the patient datasets, the PET100 and PET50 + SP were qualitatively comparable. The SubtlePET algorithm was able to correctly recover the SUV values of the lesions and maintain a noise level equivalent to full-time images.

Conclusion: Based on our results, SubtlePET is adapted in clinical practice for half-time or half-dose acquisitions based on European recommended injected dose of 3 MBq/kg without diagnostic confidence loss.

Citing Articles

Dohmen M, Klemens M, Baltruschat I, Truong T, Lenga M Sci Rep. 2025; 15(1):3853.

PMID: 39890963 PMC: 11785996. DOI: 10.1038/s41598-025-87358-0.

Whole-body PET image denoising for reduced acquisition time.

Kruzhilov I, Kudin S, Vetoshkin L, Sokolova E, Kokh V Front Med (Lausanne). 2024; 11:1415058.

PMID: 39403284 PMC: 11471667. DOI: 10.3389/fmed.2024.1415058.

The impact of introducing deep learning based [F]FDG PET denoising on EORTC and PERCIST therapeutic response assessments in digital PET/CT.

Weyts K, Lequesne J, Johnson A, Curcio H, Parzy A, Coquan E EJNMMI Res. 2024; 14(1):72.

PMID: 39126532 PMC: 11316728. DOI: 10.1186/s13550-024-01128-z.

Deep learning generation of preclinical positron emission tomography (PET) images from low-count PET with task-based performance assessment.

Dutta K, Laforest R, Luo J, Jha A, Shoghi K Med Phys. 2024; 51(6):4324-4339.

PMID: 38710222 PMC: 11423763. DOI: 10.1002/mp.17105.

Feasibility of a deep learning algorithm to achieve the low-dose Ga-FAPI/the fast-scan PET images: a multicenter study.

Liu L, Chen X, Wan L, Zhang N, Hu R, Li W Br J Radiol. 2023; 96(1149):20230038.

PMID: 37393527 PMC: 10461288. DOI: 10.1259/bjr.20230038.

References

Nuyts J, Fessler J . A penalized-likelihood image reconstruction method for emission tomography, compared to postsmoothed maximum-likelihood with matched spatial resolution. IEEE Trans Med Imaging. 2003; 22(9):1042-52. DOI: 10.1109/TMI.2003.816960. View

Gatidis S, Wurslin C, Seith F, Schafer J, Fougere C, Nikolaou K . Towards tracer dose reduction in PET studies: Simulation of dose reduction by retrospective randomized undersampling of list-mode data. Hell J Nucl Med. 2016; 19(1):15-8. DOI: 10.1967/s002449910333. View

Wang Y, Ma G, An L, Shi F, Zhang P, Lalush D . Semisupervised Tripled Dictionary Learning for Standard-Dose PET Image Prediction Using Low-Dose PET and Multimodal MRI. IEEE Trans Biomed Eng. 2016; 64(3):569-579. PMC: 5383421. DOI: 10.1109/TBME.2016.2564440. View

Turkheimer F, Boussion N, Anderson A, Pavese N, Piccini P, Visvikis D . PET image denoising using a synergistic multiresolution analysis of structural (MRI/CT) and functional datasets. J Nucl Med. 2008; 49(4):657-66. DOI: 10.2967/jnumed.107.041871. View

Lu W, Onofrey J, Lu Y, Shi L, Ma T, Liu Y . An investigation of quantitative accuracy for deep learning based denoising in oncological PET. Phys Med Biol. 2019; 64(16):165019. DOI: 10.1088/1361-6560/ab3242. View

Le Pogam A, Hanzouli H, Hatt M, Cheze Le Rest C, Visvikis D . Denoising of PET images by combining wavelets and curvelets for improved preservation of resolution and quantitation. Med Image Anal. 2013; 17(8):877-91. DOI: 10.1016/j.media.2013.05.005. View

Kaalep A, Burggraaff C, Pieplenbosch S, Verwer E, Sera T, Zijlstra J . Quantitative implications of the updated EARL 2019 PET-CT performance standards. EJNMMI Phys. 2019; 6(1):28. PMC: 6933045. DOI: 10.1186/s40658-019-0257-8. View

Texte E, Gouel P, Thureau S, Lequesne J, Barres B, Edet-Sanson A . Impact of the Bayesian penalized likelihood algorithm (Q.Clear®) in comparison with the OSEM reconstruction on low contrast PET hypoxic images. EJNMMI Phys. 2020; 7(1):28. PMC: 7218037. DOI: 10.1186/s40658-020-00300-3. View

Chan C, Fulton R, Barnett R, Feng D, Meikle S . Postreconstruction nonlocal means filtering of whole-body PET with an anatomical prior. IEEE Trans Med Imaging. 2014; 33(3):636-50. DOI: 10.1109/TMI.2013.2292881. View

10.

Dutta J, Leahy R, Li Q . Non-local means denoising of dynamic PET images. PLoS One. 2013; 8(12):e81390. PMC: 3855264. DOI: 10.1371/journal.pone.0081390. View

11.

Haggstrom I, Schmidtlein C, Campanella G, Fuchs T . DeepPET: A deep encoder-decoder network for directly solving the PET image reconstruction inverse problem. Med Image Anal. 2019; 54:253-262. PMC: 6537887. DOI: 10.1016/j.media.2019.03.013. View

12.

Gong K, Guan J, Liu C, Qi J . PET Image Denoising Using a Deep Neural Network Through Fine Tuning. IEEE Trans Radiat Plasma Med Sci. 2020; 3(2):153-161. PMC: 7402614. DOI: 10.1109/TRPMS.2018.2877644. View

13.

Gong K, Guan J, Kim K, Zhang X, Yang J, Seo Y . Iterative PET Image Reconstruction Using Convolutional Neural Network Representation. IEEE Trans Med Imaging. 2018; 38(3):675-685. PMC: 6472985. DOI: 10.1109/TMI.2018.2869871. View

14.

Schaefferkoetter J, Yan J, Ortega C, Sertic A, Lechtman E, Eshet Y . Convolutional neural networks for improving image quality with noisy PET data. EJNMMI Res. 2020; 10(1):105. PMC: 7505915. DOI: 10.1186/s13550-020-00695-1. View

15.

Teoh E, McGowan D, Macpherson R, Bradley K, Gleeson F . Phantom and Clinical Evaluation of the Bayesian Penalized Likelihood Reconstruction Algorithm Q.Clear on an LYSO PET/CT System. J Nucl Med. 2015; 56(9):1447-52. PMC: 4558942. DOI: 10.2967/jnumed.115.159301. View

16.

Spuhler K, Serrano-Sosa M, Cattell R, DeLorenzo C, Huang C . Full-count PET recovery from low-count image using a dilated convolutional neural network. Med Phys. 2020; 47(10):4928-4938. DOI: 10.1002/mp.14402. View

17.

Wang Y, Zhang P, An L, Ma G, Kang J, Shi F . Predicting standard-dose PET image from low-dose PET and multimodal MR images using mapping-based sparse representation. Phys Med Biol. 2016; 61(2):791-812. DOI: 10.1088/0031-9155/61/2/791. View

18.

Katsari K, Penna D, Arena V, Polverari G, Ianniello A, Italiano D . Artificial intelligence for reduced dose 18F-FDG PET examinations: a real-world deployment through a standardized framework and business case assessment. EJNMMI Phys. 2021; 8(1):25. PMC: 7943690. DOI: 10.1186/s40658-021-00374-7. View

19.

Duffy I, Boyle A, Vasdev N . Improving PET Imaging Acquisition and Analysis With Machine Learning: A Narrative Review With Focus on Alzheimer's Disease and Oncology. Mol Imaging. 2019; 18:1536012119869070. PMC: 6702769. DOI: 10.1177/1536012119869070. View