Unsupervised Denoising of Optical Coherence Tomography Images with Dual_Merged CycleWGAN

TL;DR

This paper introduces Dual-Merged CycleWGAN, an unsupervised neural network model that effectively denoises OCT images with less labeled data, leveraging dual Cycle-GANs and image merging for improved detail preservation.

Contribution

The paper presents a novel unsupervised Cycle-WGAN architecture with image merging, reducing the need for labeled data and enhancing denoising performance for OCT images.

Findings

Outperforms existing methods in visual quality and objective metrics

Requires fewer labeled training samples

Demonstrates robustness through ablation and comparative experiments

Abstract

Nosie is an important cause of low quality Optical coherence tomography (OCT) image. The neural network model based on Convolutional neural networks(CNNs) has demonstrated its excellent performance in image denoising. However, OCT image denoising still faces great challenges because many previous neural network algorithms required a large number of labeled data, which might cost much time or is expensive. Besides, these CNN-based algorithms need numerous parameters and good tuning techniques, which is hardware resources consuming. To solved above problems, We proposed a new Cycle-Consistent Generative Adversarial Nets called Dual-Merged Cycle-WGAN for retinal OCT image denoiseing, which has remarkable performance with less unlabeled traning data. Our model consists of two Cycle-GAN networks with imporved generator, descriminator and wasserstein loss to achieve good training stability and better performance. Using image merge technique between two Cycle-GAN networks, our model could obtain more detailed information and hence better training effect. The effectiveness and generality of our proposed network has been proved via ablation experiments and comparative experiments. Compared with other state-of-the-art methods, our unsupervised method obtains best subjective visual effect and higher evaluation objective indicators.