Noise2Context: Context-assisted Learning 3D Thin-layer Low Dose CT Without Clean Data

TL;DR

This paper introduces a novel unsupervised training method for 3D low-dose CT denoising that leverages adjacent slices as pseudo-supervision, eliminating the need for clean reference data and improving image quality in low-dose scenarios.

Contribution

It proposes a new unsupervised loss function utilizing adjacent slices in 3D thin-layer CT scans, enabling effective denoising without paired clean data.

Findings

Outperforms existing unsupervised methods on Mayo LDCT dataset

Achieves superior denoising quality in low-dose CT images

Validates effectiveness on realistic pig head scans

Abstract

Computed tomography (CT) has played a vital role in medical diagnosis, assessment, and therapy planning, etc. In clinical practice, concerns about the increase of X-ray radiation exposure attract more and more attention. To lower the X-ray radiation, low-dose CT is often used in certain scenarios, while it will induce the degradation of CT image quality. In this paper, we proposed a training method that trained denoising neural networks without any paired clean data. we trained the denoising neural network to map one noise LDCT image to its two adjacent LDCT images in a singe 3D thin-layer low-dose CT scanning, simultaneously In other words, with some latent assumptions, we proposed an unsupervised loss function with the integration of the similarity between adjacent CT slices in 3D thin-layer lowdose CT to train the denoising neural network in an unsupervised manner. For 3D thin-slice CT scanning, the proposed virtual supervised loss function was equivalent to a supervised loss function with paired noisy and clean samples when the noise in the different slices from a single scan was uncorrelated and zero-mean. Further experiments on Mayo LDCT dataset and a realistic pig head were carried out and demonstrated superior performance over existing unsupervised methods.