Low-dose CT reconstruction by self-supervised learning in the projection domain

Abstract

In the intention of minimizing excessive X-ray radiation administration to patients, low-dose computed tomography (LDCT) has become a distinct trend in radiology. However, while lowering the radiation dose reduces the risk to the patient, it also increases noise and artifacts, compromising image quality and clinical diagnosis. In most supervised learning methods, paired CT images are required, but such images are unlikely to be available in the clinic. We present a self-supervised learning model (Noise2Projection) that fully exploits the raw projection images to reduce noise and improve the quality of reconstructed LDCT images. Unlike existing self-supervised algorithms, the proposed method only requires noisy CT projection images and reduces noise by exploiting the correlation between nearby projection images. We trained and tested the model using clinical data and the quantitative and qualitative results suggest that our model can effectively reduce LDCT image noise while also drastically removing artifacts in LDCT images.

Irregular Feature Enhancer for Low-dose CT Denoising

“…To make the reconstructed images beneficial to the visualization and diagnosis of patients' medical conditions, LDCT image reconstruction methods can be divided into three categories: denoising based on sinogram filtration [2], iterative reconstruction denoising [3], and denoising based on image post-processing. However, the first and second category methods are required to access the sinogram data inside CT scanners, which limits their development and application.…”