Medical image denoising using convolutional denoising autoencoders

TL;DR

This paper demonstrates that convolutional denoising autoencoders can effectively denoise medical images even with small datasets, and combining heterogeneous images enhances performance, offering an efficient alternative to traditional deep learning methods.

Contribution

The study introduces a convolutional autoencoder approach that performs well with limited data and leverages heterogeneous images to improve denoising in medical imaging.

Findings

Effective denoising with small sample sizes

Heterogeneous images boost denoising performance

Simple networks can handle high noise levels

Abstract

Image denoising is an important pre-processing step in medical image analysis. Different algorithms have been proposed in past three decades with varying denoising performances. More recently, having outperformed all conventional methods, deep learning based models have shown a great promise. These methods are however limited for requirement of large training sample size and high computational costs. In this paper we show that using small sample size, denoising autoencoders constructed using convolutional layers can be used for efficient denoising of medical images. Heterogeneous images can be combined to boost sample size for increased denoising performance. Simplest of networks can reconstruct images with corruption levels so high that noise and signal are not differentiable to human eye.