Low dose SPECT image denoising using a generative adversarial network

TL;DR

This paper demonstrates that a generative adversarial network can effectively denoise low-dose SPECT images, potentially allowing for reduced radiation exposure or shorter scan times without compromising image quality.

Contribution

The study introduces a GAN-based method for denoising SPECT images, showing its effectiveness in reducing noise at low doses with promising clinical implications.

Findings

Significant noise reduction in high noise SPECT images after GAN processing

Potential to lower radiation dose or scan time while maintaining image quality

Validated on simulated patient data with different noise levels

Abstract

The image noise level and resolution of SPECT images are relatively poor attributed to the limited number of detected counts and various physical degradation factors during acquisitions. This study aims to apply and evaluate the use of generative adversarial network (GAN) method in static SPECT image denoising. A population of 4D extended cardiac-torso (XCAT) phantoms were used to simulate 10 male and female patients with different organ sizes and activity uptakes. An analytical projector was applied to simulate 120 projections from right anterior oblique to left posterior oblique positions with two noise levels. The first noise level was based on a standard clinical count rate of 987 MBq injection and 16 min acquisition (low noise) while the other was 1/8 of the previous count rate (high noise). The high noise and low noise SPECT reconstructed images of 9 patients, i.e., 1026 images (9*114 axial slices) respectively, were paired for training. High noise SPECT images of 1 patient were tested using the trained GAN. The noise level is substantially reduced in high noise SPECT reconstructed images after using the GAN. Our method has the potential to decrease the noise level of SPECT images, which could be traded for a reduced injection dose or acquisition time while still maintaining the similar image quality as compared to the original low noise images for clinical diagnosis.