A Deep Learning Approach for F-FDG PET Attenuation Correction

Overview

Journal EJNMMI Phys

Specialty Radiology

Date 2018 Nov 13

PMID 30417316

Citations 45

Authors

Fang Liu

Hyungseok Jang

Richard Kijowski

Gengyan Zhao

Tyler Bradshaw

Alan B McMillan

Affiliations

Soon will be listed here.

Abstract

Background: To develop and evaluate the feasibility of a data-driven deep learning approach (deepAC) for positron-emission tomography (PET) image attenuation correction without anatomical imaging. A PET attenuation correction pipeline was developed utilizing deep learning to generate continuously valued pseudo-computed tomography (CT) images from uncorrected F-fluorodeoxyglucose (F-FDG) PET images. A deep convolutional encoder-decoder network was trained to identify tissue contrast in volumetric uncorrected PET images co-registered to CT data. A set of 100 retrospective 3D FDG PET head images was used to train the model. The model was evaluated in another 28 patients by comparing the generated pseudo-CT to the acquired CT using Dice coefficient and mean absolute error (MAE) and finally by comparing reconstructed PET images using the pseudo-CT and acquired CT for attenuation correction. Paired-sample t tests were used for statistical analysis to compare PET reconstruction error using deepAC with CT-based attenuation correction.

Results: deepAC produced pseudo-CTs with Dice coefficients of 0.80 ± 0.02 for air, 0.94 ± 0.01 for soft tissue, and 0.75 ± 0.03 for bone and MAE of 111 ± 16 HU relative to the PET/CT dataset. deepAC provides quantitatively accurate F-FDG PET results with average errors of less than 1% in most brain regions.

Conclusions: We have developed an automated approach (deepAC) that allows generation of a continuously valued pseudo-CT from a single F-FDG non-attenuation-corrected (NAC) PET image and evaluated it in PET/CT brain imaging.

Citing Articles

AI-enhanced PET/CT image synthesis using CycleGAN for improved ovarian cancer imaging.

Farshchitabrizi A, Sadeghi M, Sina S, Alavi M, Feshani Z, Omidi H Pol J Radiol. 2025; 90:e26-e35.

PMID: 40070416 PMC: 11891552. DOI: 10.5114/pjr/196804.

CT-Free Attenuation Correction in Paediatric Long Axial Field-of-View Positron Emission Tomography Using Synthetic CT from Emission Data.

Montgomery M, Andersen F, Mathiasen R, Borgwardt L, Andersen K, Ladefoged C Diagnostics (Basel). 2025; 14(24.

PMID: 39767149 PMC: 11727418. DOI: 10.3390/diagnostics14242788.

Improving F-FDG PET Quantification Through a Spatial Normalization Method.

Kim D, Kang S, Shin S, Choi H, Lee J J Nucl Med. 2024; 65(10):1645-1651.

PMID: 39209545 PMC: 11448607. DOI: 10.2967/jnumed.123.267360.

Deep learning applications for quantitative and qualitative PET in PET/MR: technical and clinical unmet needs.

Yang J, Afaq A, Sibley R, McMilan A, Pirasteh A MAGMA. 2024; 37(4):749-763.

PMID: 39167304 DOI: 10.1007/s10334-024-01199-y.

Artificial intelligence-based joint attenuation and scatter correction strategies for multi-tracer total-body PET.

Sun H, Huang Y, Hu D, Hong X, Salimi Y, Lv W EJNMMI Phys. 2024; 11(1):66.

PMID: 39028439 PMC: 11264498. DOI: 10.1186/s40658-024-00666-8.

References

Huang B, Law M, Khong P . Whole-body PET/CT scanning: estimation of radiation dose and cancer risk. Radiology. 2009; 251(1):166-74. DOI: 10.1148/radiol.2511081300. View

Kazerooni A, Ay M, Arfaie S, Khateri P, Saligheh Rad H . Single STE-MR Acquisition in MR-Based Attenuation Correction of Brain PET Imaging Employing a Fully Automated and Reproducible Level-Set Segmentation Approach. Mol Imaging Biol. 2016; 19(1):143-152. DOI: 10.1007/s11307-016-0990-5. View

Burger C, Goerres G, Schoenes S, Buck A, Lonn A, von Schulthess G . PET attenuation coefficients from CT images: experimental evaluation of the transformation of CT into PET 511-keV attenuation coefficients. Eur J Nucl Med Mol Imaging. 2002; 29(7):922-7. DOI: 10.1007/s00259-002-0796-3. View

Mehranian A, Arabi H, Zaidi H . Vision 20/20: Magnetic resonance imaging-guided attenuation correction in PET/MRI: Challenges, solutions, and opportunities. Med Phys. 2016; 43(3):1130-55. DOI: 10.1118/1.4941014. View

Zhou Z, Zhao G, Kijowski R, Liu F . Deep convolutional neural network for segmentation of knee joint anatomy. Magn Reson Med. 2018; 80(6):2759-2770. PMC: 6342268. DOI: 10.1002/mrm.27229. View

Benoit D, Ladefoged C, Rezaei A, Keller S, Andersen F, Hojgaard L . Optimized MLAA for quantitative non-TOF PET/MR of the brain. Phys Med Biol. 2016; 61(24):8854-8874. DOI: 10.1088/1361-6560/61/24/8854. View

Liu F, Jang H, Kijowski R, Bradshaw T, McMillan A . Deep Learning MR Imaging-based Attenuation Correction for PET/MR Imaging. Radiology. 2017; 286(2):676-684. PMC: 5790303. DOI: 10.1148/radiol.2017170700. View

Leynes A, Yang J, Wiesinger F, Kaushik S, Shanbhag D, Seo Y . Zero-Echo-Time and Dixon Deep Pseudo-CT (ZeDD CT): Direct Generation of Pseudo-CT Images for Pelvic PET/MRI Attenuation Correction Using Deep Convolutional Neural Networks with Multiparametric MRI. J Nucl Med. 2017; 59(5):852-858. PMC: 5932530. DOI: 10.2967/jnumed.117.198051. View

Jang H, Liu F, Zhao G, Bradshaw T, McMillan A . Technical Note: Deep learning based MRAC using rapid ultrashort echo time imaging. Med Phys. 2018; . PMC: 6443501. DOI: 10.1002/mp.12964. View

10.

Jang H, Liu F, Bradshaw T, McMillan A . Rapid dual-echo ramped hybrid encoding MR-based attenuation correction (dRHE-MRAC) for PET/MR. Magn Reson Med. 2017; 79(6):2912-2922. PMC: 5843521. DOI: 10.1002/mrm.26953. View

11.

Leynes A, Yang J, Shanbhag D, Kaushik S, Seo Y, Hope T . Hybrid ZTE/Dixon MR-based attenuation correction for quantitative uptake estimation of pelvic lesions in PET/MRI. Med Phys. 2017; 44(3):902-913. PMC: 5877454. DOI: 10.1002/mp.12122. View

12.

Xiang L, Wang Q, Nie D, Zhang L, Jin X, Qiao Y . Deep embedding convolutional neural network for synthesizing CT image from T1-Weighted MR image. Med Image Anal. 2018; 47:31-44. PMC: 6410565. DOI: 10.1016/j.media.2018.03.011. View

13.

Liu F, Zhou Z, Jang H, Samsonov A, Zhao G, Kijowski R . Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging. Magn Reson Med. 2017; 79(4):2379-2391. PMC: 6271435. DOI: 10.1002/mrm.26841. View

14.

Ladefoged C, Law I, Anazodo U, St Lawrence K, Izquierdo-Garcia D, Catana C . A multi-centre evaluation of eleven clinically feasible brain PET/MRI attenuation correction techniques using a large cohort of patients. Neuroimage. 2016; 147:346-359. PMC: 6818242. DOI: 10.1016/j.neuroimage.2016.12.010. View

15.

Litjens G, Kooi T, Bejnordi B, Setio A, Ciompi F, Ghafoorian M . A survey on deep learning in medical image analysis. Med Image Anal. 2017; 42:60-88. DOI: 10.1016/j.media.2017.07.005. View

16.

Mehranian A, Zaidi H . Joint Estimation of Activity and Attenuation in Whole-Body TOF PET/MRI Using Constrained Gaussian Mixture Models. IEEE Trans Med Imaging. 2015; 34(9):1808-21. DOI: 10.1109/TMI.2015.2409157. View

17.

LeCun Y, Bengio Y, Hinton G . Deep learning. Nature. 2015; 521(7553):436-44. DOI: 10.1038/nature14539. View

18.

Wiesinger F, Bylund M, Yang J, Kaushik S, Shanbhag D, Ahn S . Zero TE-based pseudo-CT image conversion in the head and its application in PET/MR attenuation correction and MR-guided radiation therapy planning. Magn Reson Med. 2018; 80(4):1440-1451. DOI: 10.1002/mrm.27134. View