Noise-aware dynamic image denoising and positron range correction for Rubidium-82 cardiac PET imaging via self-supervision

Huidong Xie; Liang Guo; Alexandre Velo; Zhao Liu; Qiong Liu; Xueqi Guo; Bo Zhou; Xiongchao Chen; Yu-Jung Tsai; Tianshun Miao; Menghua Xia; Yi-Hwa Liu; Ian S Armstrong; Ge Wang; Richard E Carson; Albert J Sinusas; Chi Liu

doi:10.1016/j.media.2024.103391

Noise-aware dynamic image denoising and positron range correction for Rubidium-82 cardiac PET imaging via self-supervision

Med Image Anal. 2024 Nov 20:100:103391. doi: 10.1016/j.media.2024.103391. Online ahead of print.

Authors

Huidong Xie¹, Liang Guo², Alexandre Velo³, Zhao Liu³, Qiong Liu², Xueqi Guo², Bo Zhou², Xiongchao Chen², Yu-Jung Tsai³, Tianshun Miao³, Menghua Xia³, Yi-Hwa Liu⁴, Ian S Armstrong⁵, Ge Wang⁶, Richard E Carson⁷, Albert J Sinusas⁸, Chi Liu⁹

Affiliations

¹ Department of Biomedical Engineering, Yale University, USA. Electronic address: huidong.xie@yale.edu.
² Department of Biomedical Engineering, Yale University, USA.
³ Department of Radiology and Biomedical Imaging, Yale University, USA.
⁴ Department of Internal Medicine (Cardiology), Yale University, USA.
⁵ Department of Nuclear Medicine, University of Manchester, UK.
⁶ Department of Biomedical Engineering, Rensselaer Polytechnic Institute, USA.
⁷ Department of Biomedical Engineering, Yale University, USA; Department of Radiology and Biomedical Imaging, Yale University, USA.
⁸ Department of Biomedical Engineering, Yale University, USA; Department of Radiology and Biomedical Imaging, Yale University, USA; Department of Internal Medicine (Cardiology), Yale University, USA.
⁹ Department of Biomedical Engineering, Yale University, USA; Department of Radiology and Biomedical Imaging, Yale University, USA. Electronic address: chi.liu@yale.edu.

PMID: 39579623
DOI: 10.1016/j.media.2024.103391

Abstract

Rubidium-82 (⁸²Rb) is a radioactive isotope widely used for cardiac PET imaging. Despite numerous benefits of ⁸²Rb, there are several factors that limits its image quality and quantitative accuracy. First, the short half-life of ⁸²Rb results in noisy dynamic frames. Low signal-to-noise ratio would result in inaccurate and biased image quantification. Noisy dynamic frames also lead to highly noisy parametric images. The noise levels also vary substantially in different dynamic frames due to radiotracer decay and short half-life. Existing denoising methods are not applicable for this task due to the lack of paired training inputs/labels and inability to generalize across varying noise levels. Second, ⁸²Rb emits high-energy positrons. Compared with other tracers such as ¹⁸F, ⁸²Rb travels a longer distance before annihilation, which negatively affect image spatial resolution. Here, the goal of this study is to propose a self-supervised method for simultaneous (1) noise-aware dynamic image denoising and (2) positron range correction for ⁸²Rb cardiac PET imaging. Tested on a series of PET scans from a cohort of normal volunteers, the proposed method produced images with superior visual quality. To demonstrate the improvement in image quantification, we compared image-derived input functions (IDIFs) with arterial input functions (AIFs) from continuous arterial blood samples. The IDIF derived from the proposed method led to lower AUC differences, decreasing from 11.09% to 7.58% on average, compared to the original dynamic frames. The proposed method also improved the quantification of myocardium blood flow (MBF), as validated against ¹⁵O-water scans, with mean MBF differences decreased from 0.43 to 0.09, compared to the original dynamic frames. We also conducted a generalizability experiment on 37 patient scans obtained from a different country using a different scanner. The presented method enhanced defect contrast and resulted in lower regional MBF in areas with perfusion defects. Lastly, comparison with other related methods is included to show the effectiveness of the proposed method.

Keywords: Deep learning; Medical image denoising; Positron range correction; Rubidium-82 cardiac PET imaging; Self-supervised learning.