Limited-angle SPECT image reconstruction using deep image prior.
Authors
Affiliations (4)
Affiliations (4)
- Department of Radiologital Technology, Juntendo University, 1-5-32, Yushima, Bunkyo-ku, Tokyo 113-0034, Japan, Bunkyo, 113-8421, JAPAN.
- University of Florida, Gainesville, 32611, FL, USA, Gainesville, 32611-7011, UNITED STATES.
- Department of Radiologital Technology, Juntendo University, 1-5-32, Yushima, Bunkyo-ku, Tokyo, 113-0034, Japan, Bunkyo, 113-8421, JAPAN.
- Medical Radiological Technology, Kyorin University Faculty of Health Sciences Graduate School of Health Sciences, Shimorenjaku 5-4-1, Mitaka, Tokyo, 181-8612, JAPAN.
Abstract
[Objective] In single-photon emission computed tomography (SPECT) image reconstruction, limited-angle 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 limited-angle conditions, the image quality is still unsuitable for clinical use. We propose a limited-angle SPECT image reconstruction method that uses an end-to-end deep image prior (DIP) framework to improve reconstructed image quality.
[Approach] The proposed limited-angle 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.
[Main results] 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 peak signal-to-noise ratio and structural similarity index measure. 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.
[Significance] The proposed end-to-end DIP-based reconstruction method restores lost frequency components and mitigates image distortion under limited-angle conditions by incorporating a binary mask into the loss function.