CT Image Denoising with Perceptive Deep Neural Networks

TL;DR

This paper introduces a perceptual deep learning approach for CT image denoising that preserves structural details better than traditional MSE-based methods, improving diagnostic confidence in low-dose CT scans.

Contribution

It proposes a novel perceptual similarity-based loss function for deep neural networks to enhance CT image denoising while maintaining structural integrity.

Findings

Effective noise reduction in CT images

Preservation of critical structural details

Improved visual quality over MSE-based methods

Abstract

Increasing use of CT in modern medical practice has raised concerns over associated radiation dose. Reduction of radiation dose associated with CT can increase noise and artifacts, which can adversely affect diagnostic confidence. Denoising of low-dose CT images on the other hand can help improve diagnostic confidence, which however is a challenging problem due to its ill-posed nature, since one noisy image patch may correspond to many different output patches. In the past decade, machine learning based approaches have made quite impressive progress in this direction. However, most of those methods, including the recently popularized deep learning techniques, aim for minimizing mean-squared-error (MSE) between a denoised CT image and the ground truth, which results in losing important structural details due to over-smoothing, although the PSNR based performance measure looks great. In this work, we introduce a new perceptual similarity measure as the objective function for a deep convolutional neural network to facilitate CT image denoising. Instead of directly computing MSE for pixel-to-pixel intensity loss, we compare the perceptual features of a denoised output against those of the ground truth in a feature space. Therefore, our proposed method is capable of not only reducing the image noise levels, but also keeping the critical structural information at the same time. Promising results have been obtained in our experiments with a large number of CT images.