High-quality PET image synthesis from ultra-low-dose PET/MRI using bi-task deep learning

Hanyu Sun; Yongluo Jiang; Jianmin Yuan; Haining Wang; Dong Liang; Wei Fan; Zhanli Hu; Na Zhang

doi:10.21037/qims-22-116

High-quality PET image synthesis from ultra-low-dose PET/MRI using bi-task deep learning

Quant Imaging Med Surg. 2022 Dec;12(12):5326-5342. doi: 10.21037/qims-22-116.

Authors

Hanyu Sun^#¹, Yongluo Jiang^#², Jianmin Yuan³, Haining Wang⁴, Dong Liang¹, Wei Fan², Zhanli Hu^{1

4}, Na Zhang^{1

4}

Affiliations

¹ Lauterbur Research Center for Biomedical Imaging, Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
² Department of Nuclear Medicine, Sun Yat-sen University Cancer Center, Guangzhou, China.
³ Central Research Institute, Shanghai United Imaging Healthcare, Shanghai, China.
⁴ United Imaging Research Institute of Innovative Medical Equipment, Shenzhen, China.

^# Contributed equally.

Abstract

Background: Lowering the dose for positron emission tomography (PET) imaging reduces patients' radiation burden but decreases the image quality by increasing noise and reducing imaging detail and quantifications. This paper introduces a method for acquiring high-quality PET images from an ultra-low-dose state to achieve both high-quality images and a low radiation burden.

Methods: We developed a two-task-based end-to-end generative adversarial network, named bi-c-GAN, that incorporated the advantages of PET and magnetic resonance imaging (MRI) modalities to synthesize high-quality PET images from an ultra-low-dose input. Moreover, a combined loss, including the mean absolute error, structural loss, and bias loss, was created to improve the trained model's performance. Real integrated PET/MRI data from 67 patients' axial heads (each with 161 slices) were used for training and validation purposes. Synthesized images were quantified by the peak signal-to-noise ratio (PSNR), normalized mean square error (NMSE), structural similarity (SSIM), and contrast noise ratio (CNR). The improvement ratios of these four selected quantitative metrics were used to compare the images produced by bi-c-GAN with other methods.

Results: In the four-fold cross-validation, the proposed bi-c-GAN outperformed the other three selected methods (U-net, c-GAN, and multiple input c-GAN). With the bi-c-GAN, in a 5% low-dose PET, the image quality was higher than that of the other three methods by at least 6.7% in the PSNR, 0.6% in the SSIM, 1.3% in the NMSE, and 8% in the CNR. In the hold-out validation, bi-c-GAN improved the image quality compared to U-net and c-GAN in both 2.5% and 10% low-dose PET. For example, the PSNR using bi-C-GAN was at least 4.46% in the 2.5% low-dose PET and at most 14.88% in the 10% low-dose PET. Visual examples also showed a higher quality of images generated from the proposed method, demonstrating the denoising and improving ability of bi-c-GAN.

Conclusions: By taking advantage of integrated PET/MR images and multitask deep learning (MDL), the proposed bi-c-GAN can efficiently improve the image quality of ultra-low-dose PET and reduce radiation exposure.

Keywords: Integrated PET/MRI; bias loss; multitask deep learning (MDL); ultra-low-dose positron emission tomography (PET).