Noise as Domain Shift: Denoising Medical Images by Unpaired Image Translation

Abstract

We cast the problem of image denoising as a domain translation problem between high and low noise domains. By modifying the cycleGAN model, we are able to learn a mapping between these domains on unpaired retinal optical coherence tomography images. In quantitative measurements and a qualitative evaluation by ophthalmologists, we show how this approach outperforms other established methods. The results indicate that the network differentiates subtle changes in the level of noise in the image. Further investigation of the model's feature maps reveals that it has learned to distinguish retinal layers and other distinct regions of the images.

Cited by in corpus (5)

• Domain Adaptation for Medical Image Analysis: A Survey
• Enhancing and Adapting in the Clinic: Source-free Unsupervised Domain Adaptation for Medical Image Enhancement
• Noise transfer for unsupervised domain adaptation of retinal OCT images
• Toward ground-truth optical coherence tomography via three-dimensional unsupervised deep learning processing and data
• Deep learning-based bias transfer for overcoming laboratory differences of microscopic images