Short-axis PET Image Quality Improvement Based on a UEXPLORER Total-body PET System Through Deep Learning

Overview

Journal Eur J Nucl Med Mol Imaging

Specialties Biophysics
Nuclear Medicine
Radiology

Date 2023 Sep 6

PMID 37672046

Authors

Zhenxing Huang

Wenbo Li

Yaping Wu

Nannan Guo

Lin Yang

Na Zhang

Zhifeng Pang

Yongfeng Yang

Yun Zhou

Yue Shang

Hairong Zheng

Dong Liang

Meiyun Wang

Zhanli Hu

Affiliations

Soon will be listed here.

Abstract

Purpose: The axial field of view (AFOV) of a positron emission tomography (PET) scanner greatly affects the quality of PET images. Although a total-body PET scanner (uEXPLORER) with a large AFOV is more sensitive, it is more expensive and difficult to widely use. Therefore, we attempt to utilize high-quality images generated by uEXPLORER to optimize the quality of images from short-axis PET scanners through deep learning technology while controlling costs.

Methods: The experiments were conducted using PET images of three anatomical locations (brain, lung, and abdomen) from 335 patients. To simulate PET images from different axes, two protocols were used to obtain PET image pairs (each patient was scanned once). For low-quality PET (LQ-PET) images with a 320-mm AFOV, we applied a 300-mm FOV for brain reconstruction and a 500-mm FOV for lung and abdomen reconstruction. For high-quality PET (HQ-PET) images, we applied a 1940-mm AFOV during the reconstruction process. A 3D Unet was utilized to learn the mapping relationship between LQ-PET and HQ-PET images. In addition, the peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) were employed to evaluate the model performance. Furthermore, two nuclear medicine doctors evaluated the image quality based on clinical readings.

Results: The generated PET images of the brain, lung, and abdomen were quantitatively and qualitatively compatible with the HQ-PET images. In particular, our method achieved PSNR values of 35.41 ± 5.45 dB (p < 0.05), 33.77 ± 6.18 dB (p < 0.05), and 38.58 ± 7.28 dB (p < 0.05) for the three beds. The overall mean SSIM was greater than 0.94 for all patients who underwent testing. Moreover, the total subjective quality levels of the generated PET images for three beds were 3.74 ± 0.74, 3.69 ± 0.81, and 3.42 ± 0.99 (the highest possible score was 5, and the minimum score was 1) from two experienced nuclear medicine experts. Additionally, we evaluated the distribution of quantitative standard uptake values (SUV) in the region of interest (ROI). Both the SUV distribution and the peaks of the profile show that our results are consistent with the HQ-PET images, proving the superiority of our approach.

Conclusion: The findings demonstrate the potential of the proposed technique for improving the image quality of a PET scanner with a 320 mm or even shorter AFOV. Furthermore, this study explored the potential of utilizing uEXPLORER to achieve improved short-axis PET image quality at a limited economic cost, and computer-aided diagnosis systems that are related can help patients and radiologists.

Citing Articles

A generative whole-brain segmentation model for positron emission tomography images.

Li W, Huang Z, Tang H, Wu Y, Gao Y, Qin J EJNMMI Phys. 2025; 12(1):15.

PMID: 39920478 PMC: 11805735. DOI: 10.1186/s40658-025-00716-9.

Realization of high-end PET devices that assist conventional PET devices in improving image quality via diffusion modeling.

Zhang Q, Zhou C, Zhang X, Fan W, Zheng H, Liang D EJNMMI Phys. 2024; 11(1):103.

PMID: 39692956 PMC: 11656007. DOI: 10.1186/s40658-024-00706-3.

Assessment of image-derived input functions from small vessels for patlak parametric imaging using total-body PET/CT.

Tang H, Wu Y, Cheng Z, Song S, Dong Q, Zhou Y Eur J Nucl Med Mol Imaging. 2024; 52(2):648-659.

PMID: 39325156 PMC: 11732897. DOI: 10.1007/s00259-024-06926-0.

Fusion of shallow and deep features from F-FDG PET/CT for predicting EGFR-sensitizing mutations in non-small cell lung cancer.

Yao X, Zhu Y, Huang Z, Wang Y, Cong S, Wan L Quant Imaging Med Surg. 2024; 14(8):5460-5472.

PMID: 39144023 PMC: 11320501. DOI: 10.21037/qims-23-1028.

References

Etminani K, Soliman A, Davidsson A, Chang J, Martinez-Sanchis B, Byttner S . A 3D deep learning model to predict the diagnosis of dementia with Lewy bodies, Alzheimer's disease, and mild cognitive impairment using brain 18F-FDG PET. Eur J Nucl Med Mol Imaging. 2021; 49(2):563-584. PMC: 8803724. DOI: 10.1007/s00259-021-05483-0. View

Fletcher J, Djulbegovic B, Soares H, Siegel B, Lowe V, Lyman G . Recommendations on the use of 18F-FDG PET in oncology. J Nucl Med. 2008; 49(3):480-508. DOI: 10.2967/jnumed.107.047787. View

Rischpler C, Nekolla S, Dregely I, Schwaiger M . Hybrid PET/MR imaging of the heart: potential, initial experiences, and future prospects. J Nucl Med. 2013; 54(3):402-15. DOI: 10.2967/jnumed.112.105353. View

Zaidi H, Karakatsanis N . Towards enhanced PET quantification in clinical oncology. Br J Radiol. 2017; 91(1081):20170508. PMC: 6049841. DOI: 10.1259/bjr.20170508. View

Lammertsma A . Forward to the Past: The Case for Quantitative PET Imaging. J Nucl Med. 2017; 58(7):1019-1024. DOI: 10.2967/jnumed.116.188029. View

Boellaard R . Standards for PET image acquisition and quantitative data analysis. J Nucl Med. 2009; 50 Suppl 1:11S-20S. DOI: 10.2967/jnumed.108.057182. View

Badawi R, Shi H, Hu P, Chen S, Xu T, Price P . First Human Imaging Studies with the EXPLORER Total-Body PET Scanner. J Nucl Med. 2019; 60(3):299-303. PMC: 6424228. DOI: 10.2967/jnumed.119.226498. View

Jones T, Townsend D . History and future technical innovation in positron emission tomography. J Med Imaging (Bellingham). 2017; 4(1):011013. PMC: 5374360. DOI: 10.1117/1.JMI.4.1.011013. View

Cherry S, Jones T, Karp J, Qi J, Moses W, Badawi R . Total-Body PET: Maximizing Sensitivity to Create New Opportunities for Clinical Research and Patient Care. J Nucl Med. 2017; 59(1):3-12. PMC: 5750522. DOI: 10.2967/jnumed.116.184028. View

10.

Arabi H, Zaidi H . Applications of artificial intelligence and deep learning in molecular imaging and radiotherapy. Eur J Hybrid Imaging. 2021; 4(1):17. PMC: 8218135. DOI: 10.1186/s41824-020-00086-8. View

11.

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

12.

Liu X, Faes L, Kale A, Wagner S, Fu D, Bruynseels A . A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health. 2020; 1(6):e271-e297. DOI: 10.1016/S2589-7500(19)30123-2. View

13.

Huang Z, Li W, Wang Y, Liu Z, Zhang Q, Jin Y . MLNAN: Multi-level noise-aware network for low-dose CT imaging implemented with constrained cycle Wasserstein generative adversarial networks. Artif Intell Med. 2023; 143:102609. DOI: 10.1016/j.artmed.2023.102609. View

14.

Huang Z, Chen Z, Chen J, Lu P, Quan G, Du Y . DaNet: dose-aware network embedded with dose-level estimation for low-dose CT imaging. Phys Med Biol. 2020; 66(1):015005. DOI: 10.1088/1361-6560/abc5cc. View

15.

Dabov K, Foi A, Katkovnik V, Egiazarian K . Image denoising by sparse 3-D transform-domain collaborative filtering. IEEE Trans Image Process. 2007; 16(8):2080-95. DOI: 10.1109/tip.2007.901238. View

16.

Shi L, Onofrey J, Liu H, Liu Y, Liu C . Deep learning-based attenuation map generation for myocardial perfusion SPECT. Eur J Nucl Med Mol Imaging. 2020; 47(10):2383-2395. DOI: 10.1007/s00259-020-04746-6. View

17.

Wang H, Wu Y, Huang Z, Li Z, Zhang N, Fu F . Deep learning-based dynamic PET parametric K image generation from lung static PET. Eur Radiol. 2022; 33(4):2676-2685. DOI: 10.1007/s00330-022-09237-w. View

18.

Huang Z, Liu X, Wang R, Chen Z, Yang Y, Liu X . 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):3416-3427. DOI: 10.1109/JBHI.2021.3061758. View

19.

Liu G, Hu P, Yu H, Tan H, Zhang Y, Yin H . Ultra-low-activity total-body dynamic PET imaging allows equal performance to full-activity PET imaging for investigating kinetic metrics of F-FDG in healthy volunteers. Eur J Nucl Med Mol Imaging. 2021; 48(8):2373-2383. DOI: 10.1007/s00259-020-05173-3. View

20.

Zhang X, Cherry S, Xie Z, Shi H, Badawi R, Qi J . Subsecond total-body imaging using ultrasensitive positron emission tomography. Proc Natl Acad Sci U S A. 2020; 117(5):2265-2267. PMC: 7007535. DOI: 10.1073/pnas.1917379117. View