aLow-dose CT via convolutional neural network

TLDR

Low‑dose CT is increasingly pursued to reduce radiation risk, but simply lowering the dose markedly degrades image quality. The study proposes a deep‑learning noise‑reduction method for low‑dose CT that does not require original projection data. A deep convolutional neural network maps low‑dose CT patches to normal‑dose counterparts in a patch‑by‑patch fashion. Qualitative and quantitative evaluations demonstrate that the method markedly improves PSNR, RMSE, and SSIM, preserves artifacts and structure, and runs an order of magnitude faster than iterative reconstruction and patch‑based denoising.

Abstract

In order to reduce the potential radiation risk, low-dose CT has attracted an increasing attention. However, simply lowering the radiation dose will significantly degrade the image quality. In this paper, we propose a new noise reduction method for low-dose CT via deep learning without accessing original projection data. A deep convolutional neural network is here used to map low-dose CT images towards its corresponding normal-dose counterparts in a patch-by-patch fashion. Qualitative results demonstrate a great potential of the proposed method on artifact reduction and structure preservation. In terms of the quantitative metrics, the proposed method has showed a substantial improvement on PSNR, RMSE and SSIM than the competing state-of-art methods. Furthermore, the speed of our method is one order of magnitude faster than the iterative reconstruction and patch-based image denoising methods.