Deep learning-based multi-frequency denoising for myocardial perfusion SPECT

Yu Du; Jingzhang Sun; Chien-Ying Li; Bang-Hung Yang; Tung-Hsin Wu; Greta S P Mok

doi:10.1186/s40658-024-00680-w

Deep learning-based multi-frequency denoising for myocardial perfusion SPECT

EJNMMI Phys. 2024 Oct 2;11(1):80. doi: 10.1186/s40658-024-00680-w.

Authors

Yu Du^{1

2}, Jingzhang Sun^{1

3}, Chien-Ying Li^{4

5}, Bang-Hung Yang^{4

5}, Tung-Hsin Wu⁴, Greta S P Mok^{6

7}

Affiliations

¹ Biomedical Imaging Laboratory (BIG), Department of Electrical and Computer Engineering, Faculty of Science and Technology, University of Macau, Taipa, Macau SAR, China.
² Center for Cognitive and Brain Sciences, Institute of Collaborative Innovation, University of Macau, Taipa, Macau SAR, China.
³ School of Cyberspace Security, Hainan University, Haikou, Hainan, China.
⁴ Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan.
⁵ Department of Nuclear Medicine, Taipei Veterans General Hospital, Taipei, Taiwan.
⁶ Biomedical Imaging Laboratory (BIG), Department of Electrical and Computer Engineering, Faculty of Science and Technology, University of Macau, Taipa, Macau SAR, China. [email protected].
⁷ Center for Cognitive and Brain Sciences, Institute of Collaborative Innovation, University of Macau, Taipa, Macau SAR, China. [email protected].

Abstract

Background: Deep learning (DL)-based denoising has been proven to improve image quality and quantitation accuracy of low dose (LD) SPECT. However, conventional DL-based methods used SPECT images with mixed frequency components. This work aims to develop an integrated multi-frequency denoising network to further enhance LD myocardial perfusion (MP) SPECT denoising.

Methods: Fifty anonymized patients who underwent routine ^99mTc-sestamibi stress SPECT/CT scans were retrospectively recruited. Three LD datasets were obtained by reducing the 10 s acquisition time of full dose (FD) SPECT to be 5, 2 and 1 s per projection based on the list mode data for a total of 60 projections. FD and LD projections were Fourier transformed to magnitude and phase images, which were then separated into two or three frequency bands. Each frequency band was then inversed Fourier transformed back to the image domain. We proposed a 3D integrated attention-guided multi-frequency conditional generative adversarial network (AttMFGAN) and compared with AttGAN, and separate AttGAN for multi-frequency bands denoising (AttGAN-MF).The multi-frequency FD and LD projections of 35, 5 and 10 patients were paired for training, validation and testing. The LD projections to be tested were separated to multi-frequency components and input to corresponding networks to get the denoised components, which were summed to get the final denoised projections. Voxel-based error indices were measured on the cardiac region on the reconstructed images. The perfusion defect size (PDS) was also analyzed.

Results: AttGAN-MF and AttMFGAN have superior performance on all physical and clinical indices as compared to conventional AttGAN. The integrated AttMFGAN is better than AttGAN-MF. Multi-frequency denoising with two frequency bands have generally better results than corresponding three-frequency bands methods.

Conclusions: AttGAN-MF and AttMFGAN are promising to further improve LD MP SPECT denoising.

Keywords: Deep learning; Denoising; Generative adversarial network; Myocardial perfusion SPECT.

Abstract

Grants and funding