用深度图像先验修复有限角度SPECT图像失真

In SPECT image reconstruction, limited-angle (LA) conditions lead to a loss of frequency components, which distort the reconstructed tomographic image along directions corresponding to the non-collected projection angle range. Although conventional iterative image reconstruction methods have been used to improve the reconstructed images in LA conditions, the image quality is still unsuitable for clinical use. We propose a LA SPECT image reconstruction method that uses an end-to-end deep image prior (DIP) framework to improve reconstructed image quality. The proposed LA SPECT image reconstruction is an end-to-end DIP framework which incorporates a forward projection model into the loss function to optimise the neural network. By also incorporating a binary mask that indicates whether each data point in the measured projection data has been collected, the proposed method restores the non-collected projection data and reconstructs a less distorted image. The proposed method was evaluated using 20 numerical phantoms and clinical patient data. In numerical simulations, the proposed method outperformed existing back-projection-based methods in terms of PSNR and SSIM. We analysed the reconstructed tomographic images in the frequency domain using an object-specific modulation transfer function, in simulations and on clinical patient data, to evaluate the response of the reconstruction method to different frequencies of the object. The proposed method significantly improved the response to almost all spatial frequencies, even in the non-collected projection angle range. The results demonstrate that the proposed method reconstructs a less distorted tomographic image. The proposed end-to-end DIP-based reconstruction method restores lost frequency components and mitigates image distortion under LA conditions by incorporating a binary mask into the loss function.