nach oben

European Journal of Nuclear Medicine and Molecular Imaging

Erschienen in:

21.03.2022 | Original Article

Parametric image generation with the uEXPLORER total-body PET/CT system through deep learning

verfasst von: Zhenxing Huang, Yaping Wu, Fangfang Fu, Nan Meng, Fengyun Gu, Qi Wu, Yun Zhou, Yongfeng Yang, Xin Liu, Hairong Zheng, Dong Liang, Meiyun Wang, Zhanli Hu

Erschienen in: European Journal of Nuclear Medicine and Molecular Imaging | Ausgabe 8/2022

Einloggen, um Zugang zu erhalten

Abstract

Purpose

Total-body dynamic positron emission tomography/computed tomography (PET/CT) provides much sensitivity for clinical imaging and research, bringing new opportunities and challenges regarding the generation of total-body parametric images. This study investigated parametric \(K_i\) images directly generated from static PET images without an image-derived input function on a 2-m total-body PET/CT scanner (uEXPLORER) using a deep learning model to significantly reduce the dynamic scanning time and improve patient comfort.

Methods

\(^{18}\)F-Fluorodeoxyglucose (\(^{18}\)F-FDG) 2-m total-body PET/CT image pairs were acquired for 200 patients (scanned once) with two protocols: one parametric PET image (60 min, 0\(\sim\)60 min) and one static PET image (10 min, range of 50\(\sim\)60 min). A deep learning model was implemented to predict parametric \(K_i\) images from the static PET images. Evaluation metrics, including the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM), and normalized mean square error (NMSE), were calculated for a 10-fold cross-validation assessment. Moreover, image quality was assessed by two nuclear medicine physicians in terms of clinical readings.

Results

The synthetic parametric PET images were qualitatively and quantitatively consistent with the reference images. In particular, the global mean SSIM between the synthetic and reference parametric \(K_i\) images exceeded 0.9 across all test patients. On the other hand, the overall subjective quality of the synthetic parametric PET images was 4.00 ± 0.45 (the highest possible rating is 5) according to the two expert nuclear medicine physicians.

Conclusion

The findings illustrated the feasibility of the proposed technique and its potential to reduce the required scanning duration for 2-m total-body dynamic PET/CT systems. Moreover, this study explored the potential of direct parametric image generation with uEXPLORER. Deep learning technologies may output high-quality synthetic parametric images, and the validation of clinical applications and the interpretability of network models still need further research in future works.

Lammertsma AA. Forward to the past: the case for quantitative pet imaging. J Nucl Med. 2017;58(7):1019–24.

Tomasi G, Turkheimer F, Aboagye E. Importance of quantification for the analysis of pet data in oncology: review of current methods and trends for the future. Mol Imaging Biol. 2012;14(2):131–46.

Wang Y, Li E, Cherry SR, Wang G. Total-body pet kinetic modeling and potential opportunities using deep learning. PET Clin. 2021;16(4):613–25.

Collij LE, Konijnenberg E, Reimand J, Ten Kate M, Den Braber A, Alves IL, Zwan M, Yaqub M, van Assema DM, Wink AM, et al. Assessing amyloid pathology in cognitively normal subjects using 18f-flutemetamol pet: comparing visual reads and quantitative methods. J Nucl Med. 2019;60(4):541–7.

Peretti DE, Vállez García D, Reesink FE, van der Goot T, De Deyn PP, de Jong BM, Dierckx RA, Boellaard R. Relative cerebral flow from dynamic pib scans as an alternative for fdg scans in alzheimer’s disease pet studies. PloS ONE. 2019;14(1):e0211000.

Leahy R, Boellaard R, Zaidi H. Whole-body parametric pet imaging will replace conventional image-derived pet metrics in clinical oncology. Med Phys. 2018;45(12):5355–8.

Zhuang M, Karakatsanis NA, Dierckx RA, Zaidi H. Quantitative analysis of heterogeneous [18 f] fdg static (suv) vs. patlak (ki) whole-body pet imaging using different segmentation methods: a simulation study. Mol Imaging Biol. 2019;21(2):317–27.

Fahrni G, Karakatsanis NA, Di Domenicantonio G, Garibotto V, Zaidi H. Does whole-body patlak 18 f-fdg pet imaging improve lesion detectability in clinical oncology? Eur Radiol. 2019;29(9):4812–21.

Chen Y, Li L, Yu X, Wang J, Wang Y, Huang G, Liu J. Is dynamic total-body pet imaging feasible in the clinical daily practice? 2021.

10.

Zaker N, Kotasidis F, Garibotto V, Zaidi H. Assessment of lesion detectability in dynamic whole-body pet imaging using compartmental and patlak parametric mapping. Clin Nucl Med. 2020;45(5):e221–31.

11.

Zhang X, Xie Z, Berg E, Judenhofer MS, Liu W, Xu T, Ding Y, Lv Y, Dong Y, Deng Z, et al. Total-body dynamic reconstruction and parametric imaging on the uEXPLORER. J Nucl Med. 2020;61(2):285–91.

12.

Liu G, Xu H, Hu P, Tan H, Zhang Y, Yu H, Li X, Shi H. Kinetic metrics of 18 f-fdg in normal human organs identified by systematic dynamic total-body positron emission tomography. Eur J Nucl Med Mol Imaging. 2021;1–10.

13.

Lan X, Fan K, Li K, Cai W. Dynamic pet imaging with ultra-low-activity of 18 f-fdg: unleashing the potential of total-body pet. 2021.

14.

Zhang X, Cherry SR, Xie Z, Shi H, Badawi RD, Qi J. Subsecond total-body imaging using ultrasensitive positron emission tomography. Proc Natl Acad Sci. 2020;117(5):2265–7.

15.

Tan H, Sui X, Yin H, Yu H, Gu Y, Chen S, Hu P, Mao W, Shi H. Total-body pet/ct using half-dose fdg and compared with conventional pet/ct using full-dose fdg in lung cancer. Eur J Nucl Med Mol Imaging. 2021;48(6):1966–75.

16.

Hu J, Panin V, Smith AM, Spottiswoode B, Shah V, von Gall CC, Baker M, Howe W, Kehren F, Casey M, et al. Design and implementation of automated clinical whole body parametric pet with continuous bed motion. IEEE Trans Radiat Plasma Med Sci. 2020;4(6):696–707.

17.

Wu J, Liu H, Ye Q, Gallezot J-D, Naganawa M, Miao T, Lu Y, Chen M-K, Esserman DA, Kyriakides TC, et al. Generation of parametric ki images for fdg pet using two 5-min scans. Med Phys. 2021.

18.

Feng T, Wu Y, Zhao Y, Xu T, Fu F, Huang Z, Meng N, Li H, Shao F, Wang M. Whole-body parametric imaging of fdg pet using uexplorer with reduced scan time. J Nucl Med. 2021.

19.

Schaefferkoetter J, Yan J, Moon S, Chan R, Ortega C, Metser U, Berlin A, Veit-Haibach P. Deep learning for whole-body medical image generation. Eur J Nucl Med Mol Imaging. 2021;1–10.

20.

Chen KT, Schürer M, Ouyang J, Koran MEI, Davidzon G, Mormino E, Tiepolt S, Hoffmann K-T, Sabri O, Zaharchuk G, et al. Generalization of deep learning models for ultra-low-count amyloid pet/mri using transfer learning. Eur J Nucl Med Mol Imaging. 2020;47(13):2998–3007.

21.

Cui J, Gong K, Guo N, Wu C, Meng X, Kim K, Zheng K, Wu Z, Fu L, Xu B, et al. Pet image denoising using unsupervised deep learning. Eur J Nucl Med Mol Imaging. 2019;46(13):2780–9.

22.

Huang Z, Liu X, Wang R, Chen Z, Yang Y, Liu X, Zheng H, Liang D, Hu Z. Learning a deep cnn denoising approach using anatomical prior information implemented with attention mechanism for low-dose ct imaging on clinical patient data from multiple anatomical sites. IEEE J Biomed Health Inform. 2021;25(9):3416–27.

23.

Chen KT, Toueg TN, Koran MEI, Davidzon G, Zeineh M, Holley D, Gandhi H, Halbert K, Boumis A, Kennedy G, et al. True ultra-low-dose amyloid pet/mri enhanced with deep learning for clinical interpretation. Eur J Nucl Med Mol Imaging. 2021;1–10.

24.

Sanaat A, Shiri I, Arabi H, Mainta I, Nkoulou R, Zaidi H. Deep learning-assisted ultra-fast/low-dose whole-body pet/ct imaging. Eur J Nucl Med Mol Imaging. 2021;1–11.

25.

Huang Z, Liu X, Wang R, Chen J, Lu P, Zhang Q, Jiang C, Yang Y, Liu X, Zheng H, et al. Considering anatomical prior information for low-dose ct image enhancement using attribute-augmented wasserstein generative adversarial networks. Neurocomputing. 2021;428:104–15.

26.

Gong K, Catana C, Qi J, Li Q. Pet image reconstruction using deep image prior. IEEE Trans Med Imaging. 2018;38(7):1655–65.

27.

Gong K, Guan J, Kim K, Zhang X, Yang J, Seo Y, El Fakhri G, Qi J, Li Q. Iterative pet image reconstruction using convolutional neural network representation. IEEE Trans Med Imaging. 2018;38(3):675–85.

28.

Reader AJ, Corda G, Mehranian A, da Costa-Luis C, Ellis S, Schnabel JA. Deep learning for pet image reconstruction. IEEE Trans Radiat Plasma Med Sci. 2020;5(1):1–25.

29.

Gong K, Han PK, Johnson KA, El Fakhri G, Ma C, Li Q. Attenuation correction using deep learning and integrated ute/multi-echo dixon sequence: evaluation in amyloid and tau pet imaging. Eur J Nucl Med Mol Imaging. 2021;48(5):1351–61.

30.

Shi L, Onofrey JA, Liu H, Liu Y-H, Liu C. Deep learning-based attenuation map generation for myocardial perfusion spect. Eur J Nucl Med Mol Imaging. 2020;47(10).

31.

Huang Z, Chen Z, Chen J, Lu P, Quan G, Du Y, Li C, Gu Z, Yang Y, Liu X, et al. Danet: dose-aware network embedded with dose-level estimation for low-dose ct imaging. Phys Med Biol. 2021;66(1):015005.

32.

Zhang Y, Hu D, Zhao Q, Quan G, Liu J, Liu Q, Zhang Y, Coatrieux G, Chen Y, Yu H. Clear: comprehensive learning enabled adversarial reconstruction for subtle structure enhanced low-dose ct imaging. IEEE Trans Med Imaging. 2021;40(11):3089–101.

33.

Jiang C, Zhang X, Zhang N, Zhang Q, Zhou C, Yuan J, He Q, Yang Y, Liu X, Zheng H, et al. Synthesizing pet/mr (t1-weighted) images from non-attenuation-corrected pet images. Phys Med Biol. 2021.

34.

Yang H, Sun J, Carass A, Zhao C, Lee J, Prince JL, Xu Z. Unsupervised mr-to-ct synthesis using structure-constrained cyclegan. IEEE Trans Med Imaging. 2020;39(12):4249–61.

35.

Yang H, Lu X, Wang S-H, Lu Z, Yao J, Jiang Y, Qian P. Synthesizing multi-contrast mr images via novel 3d conditional variational auto-encoding gan. Mob Netw Appl. 2021;26(1):415–24.

36.

Hu S, Shen Y, Wang S, Lei B. Brain mr to pet synthesis via bidirectional generative adversarial network. In: International conference on medical image computing and computer-assisted intervention. Springer; 2020. pp 698–707

37.

Karakatsanis NA, Zhou Y, Lodge MA, Casey ME, Wahl RL, Zaidi H, Rahmim A. Generalized whole-body patlak parametric imaging for enhanced quantification in clinical pet. Phys Med Biol. 2015;60(22):8643.

38.

Karakatsanis NA, Casey ME, Lodge MA, Rahmim A, Zaidi H. Whole-body direct 4d parametric pet imaging employing nested generalized patlak expectation-maximization reconstruction. Phys Med Biol. 2016;61(15):5456.

39.

Yin X, Zhao Q, Liu J, Yang W, Yang J, Quan G, Chen Y, Shu H, Luo L, Coatrieux J-L. Domain progressive 3d residual convolution network to improve low-dose ct imaging. IEEE Trans Med Imaging. 2019;38(12):2903–13.

Titel: Parametric image generation with the uEXPLORER total-body PET/CT system through deep learning
verfasst von: Zhenxing Huang
Yaping Wu
Fangfang Fu
Nan Meng
Fengyun Gu
Qi Wu
Yun Zhou
Yongfeng Yang
Xin Liu
Hairong Zheng
Dong Liang
Meiyun Wang
Zhanli Hu
Publikationsdatum: 21.03.2022
Verlag: Springer Berlin Heidelberg
Erschienen in: European Journal of Nuclear Medicine and Molecular Imaging / Ausgabe 8/2022
Print ISSN: 1619-7070
Elektronische ISSN: 1619-7089
DOI: https://doi.org/10.1007/s00259-022-05731-x

Springer Medizin

Abstract

Purpose

Methods

Results

Conclusion

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Weitere Artikel der Ausgabe 8/2022

Size-changeable nanoprobes for the combined radiotherapy and photodynamic therapy of tumor

Galectin expression detected by 68Ga-galectracer PET as a predictive biomarker of radiotherapy resistance

GPC3-targeted immunoPET imaging of hepatocellular carcinomas

18F- or 177Lu-labeled bivalent ligand of fibroblast activation protein with high tumor uptake and retention

Decoding the dopamine transporter imaging for the differential diagnosis of parkinsonism using deep learning

Current status and future perspective of radiopharmaceuticals in China