A deep learning method for the recovery of standard-dose imaging quality from ultra-low-dose PET on wavelet domain

Song Xue; Fanxuan Liu; Hanzhong Wang; Hong Zhu; Hasan Sari; Marco Viscione; Raphael Sznitman; Axel Rominger; Rui Guo; Biao Li; Kuangyu Shi

doi:10.1007/s00259-024-06994-2

A deep learning method for the recovery of standard-dose imaging quality from ultra-low-dose PET on wavelet domain

Eur J Nucl Med Mol Imaging. 2024 Nov 25. doi: 10.1007/s00259-024-06994-2. Online ahead of print.

Authors

Song Xue^{1

2}, Fanxuan Liu¹, Hanzhong Wang^{3

4

5

6}, Hong Zhu⁷, Hasan Sari^{1

8}, Marco Viscione¹, Raphael Sznitman², Axel Rominger¹, Rui Guo^{9

10

11

12}, Biao Li^{13

14

15

16}, Kuangyu Shi^{1

7

2}

Affiliations

¹ Department of Nuclear Medicine, Bern University Hospital, Inselspital, University of Bern, Bern, Switzerland.
² ARTORG Center, University of Bern, Bern, Switzerland.
³ Department of Nuclear Medicine, School of Medicine, Ruijin Hospital, Shanghai Jiao Tong University, Shanghai, China.
⁴ College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
⁵ Collaborative Innovation Center for Molecular Imaging of Precision Medicine, Ruijin Center, Shanghai, China.
⁶ Institute for Medical Imaging Technology, Ruijin Hospital, Shanghai Jiao Tong University, Shanghai, China.
⁷ Department of Informatics, Technical University of Munich, Munich, Germany.
⁸ Advanced Clinical Imaging Technology, Siemens Healthcare AG, Lausanne, Switzerland.
⁹ Department of Nuclear Medicine, School of Medicine, Ruijin Hospital, Shanghai Jiao Tong University, Shanghai, China. gr11734@rjh.com.cn.
¹⁰ College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China. gr11734@rjh.com.cn.
¹¹ Collaborative Innovation Center for Molecular Imaging of Precision Medicine, Ruijin Center, Shanghai, China. gr11734@rjh.com.cn.
¹² Institute for Medical Imaging Technology, Ruijin Hospital, Shanghai Jiao Tong University, Shanghai, China. gr11734@rjh.com.cn.
¹³ Department of Nuclear Medicine, School of Medicine, Ruijin Hospital, Shanghai Jiao Tong University, Shanghai, China. lb10363@rjh.com.cn.
¹⁴ College of Health Science and Technology, Shanghai Jiao Tong University School of Medicine, Shanghai, China. lb10363@rjh.com.cn.
¹⁵ Collaborative Innovation Center for Molecular Imaging of Precision Medicine, Ruijin Center, Shanghai, China. lb10363@rjh.com.cn.
¹⁶ Institute for Medical Imaging Technology, Ruijin Hospital, Shanghai Jiao Tong University, Shanghai, China. lb10363@rjh.com.cn.

PMID: 39585354
DOI: 10.1007/s00259-024-06994-2

Abstract

Purpose: Recent development in positron emission tomography (PET) dramatically increased the effective sensitivity by increasing the geometric coverage leading to total-body PET imaging. This encouraging breakthrough brings the hope of ultra-low dose PET imaging equivalent to transatlantic flight with the assistance of deep learning (DL)-based methods. However, conventional DL approaches face limitations in addressing the heterogeneous domain of PET imaging. This study aims to develop a wavelet-based DL method capable of restoring high-quality imaging from ultra-low-dose PET scans.

Materials and methods: In contrast to conventional DL techniques that denoise images in the spatial domain, we introduce WaveNet, a novel approach that inputs wavelet-decomposed frequency components of PET imaging to perform denoising in the frequency domain. A dataset comprising total-body ¹⁸F -FDG PET images of 1447, acquired using total-body PET scanners including Biograph Vision Quadra (Siemens Healthineers) and uEXPLORER (United Imaging) in Bern and Shanghai, was utilized for developing and testing the proposed method. The quality of enhanced images was assessed using a customized scoring system, which incorporated weighted global physical metrics and local indices.

Results: Our proposed WaveNet consistently outperforms the baseline UNet model across all levels of dose reduction factors (DRF), with greater improvements observed as image quality decreases. Statistical analysis (p < 0.05) and visual inspection validated the superiority of WaveNet. Moreover, WaveNet demonstrated superior generalizability when applied to two cross-scanner datasets (p < 0.05).

Conclusion: WaveNet developed with total-body PET scanners may offer a computational-friendly and robust approach to recover image quality from ultra-low-dose PET imaging. Its adoption may enhance the reliability and clinical acceptance of DL-based dose reduction techniques.

Keywords: Deep learning; PET; Ultra-low-dose; Wavelet.

Abstract

Grants and funding