Medical image denoising using convolutional denoising autoencoders
This addresses the problem of high computational costs and large data requirements for medical image analysis, though it is incremental as it builds on existing deep learning methods.
The paper tackled medical image denoising by using convolutional denoising autoencoders with small sample sizes, achieving efficient denoising even at high corruption levels where noise and signal are indistinguishable to the human eye.
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.