Denoising method for dynamic contrast-enhanced CT perfusion studies using three-dimensional deep image prior as a simultaneous spatial and temporal regularizer

TL;DR

This paper introduces a novel 3D deep image prior-based denoising method for DCE-CT perfusion studies that outperforms traditional TV-based methods, especially at low exposure levels, improving image quality and CBF estimation accuracy.

Contribution

The study proposes a 3D deep image prior approach as a simultaneous spatial and temporal regularizer for DCE-CT denoising, demonstrating superior performance over TV methods in simulation studies.

Findings

DIP method maintains PSNR and SSIM across exposure levels.

DIP yields higher SSIM than TV methods at all exposures.

CBF linearity is better preserved with DIP.

Abstract

This study aimed to propose a denoising method for dynamic contrast-enhanced computed tomography (DCE-CT) perfusion studies using a three-dimensional deep image prior (DIP), and to investigate its usefulness in comparison with total variation (TV)-based methods with different regularization parameter (alpha) values through simulation studies. In the proposed DIP method, the DIP was incorporated into the constrained optimization problem for image denoising as a simultaneous spatial and temporal regularizer, which was solved using the alternating direction method of multipliers. In the simulation studies, DCE-CT images were generated using a digital brain phantom and their noise level was varied using the X-ray exposure noise model with different exposures (15, 30, 50, 75, and 100 mAs). Cerebral blood flow (CBF) images were generated from the original contrast enhancement (CE) images and those obtained by the DIP and TV methods using block-circulant singular value decomposition. The quality of the CE images was evaluated using the peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM). To compare the CBF images obtained by the different methods and those generated from the ground truth images, linear regression analysis was performed. When using the DIP method, the PSNR and SSIM were not significantly dependent on the exposure, and the SSIM was the highest for all exposures. When using the TV methods, they were significantly dependent on the exposure and alpha values. The results of the linear regression analysis suggested that the linearity of the CBF images obtained by the DIP method was superior to those obtained from the original CE images and by the TV methods. Our preliminary results suggest that the DIP method is useful for denoising DCE-CT images at ultra-low to low exposures and for improving the accuracy of the CBF images generated from them.