Poisson diffusion probabilistic model for low‐dose SPECT sinogram denoising

Abstract Background Low‐dose single photon emission computed tomography (SPECT) sinograms often suffer from noise due to photon attenuation during the imaging process. As a result, developing effective denoising methods for low‐dose SPECT images has become an essential research topic. Traditional image denoising methods struggle to balance noise reduction with the preservation of important image details, especially in medical applications where accurate image structures are critical. Purpose This paper proposes a diffusion probabilistic model based on Poisson noise, named the Poisson diffusion probabilistic model (PDPM), for denoising low‐dose SPECT sinograms. Considering the physical principles behind the formation of low‐dose SPECT sinograms, PDPM replaces the Gaussian noise traditionally used in diffusion models with Poisson noise, utilizing low‐dose and normal‐dose SPECT sinograms as the starting and ending points of the denoising process, respectively. Methods We present a preliminary framework for PDPM that encompasses both the forward and reverse processes. Subsequently, we refine this preliminary framework by implementing two improvements: discarding the forward process and generating the training dataset using a method based on the ideal reverse process, as well as introducing our proposed Temporal Prediction Aggregation Module (TPAM) into the reverse process to enhance the model's image denoising performance. Results Experiments conducted on the simulated SPECT dataset demonstrate that PDPM effectively improves the quality of sinogram images. Specifically, the peak signal‐to‐noise ratio (PSNR) and structural similarity (SSIM) of the sinograms increased from 19.3156 to 35.3446 () and from 0.7531 to 0.9791 (), respectively. For the reconstructed images from the sinograms, the PSNR and SSIM improved from 25.7511 to 35.1335 () and from 0.9286 to 0.9817 (), respectively. The experiments show that PDPM outperforms competitive methods in the task of low‐dose SPECT sinogram denoising, including one traditional denoising algorithm and four deep learning methods. Experiments on clinical SPECT datasets further indicate that our method effectively reduces the coefficient of variation (COV) in the regions of interest (ROI) of the reconstructed images, enhancing the quality of the reconstructed images by denoising the SPECT sinograms. Conclusions The proposed PDPM demonstrates promising performance in the denoising of low‐dose SPECT sinograms. We presented a preliminary framework for PDPM and refined it to create the final version of PDPM, which is designed for the task of low‐dose SPECT sinogram denoising. Our PDPM achieved favorable denoising results on both simulated and clinical datasets.