Comparative study of deep neural networks with unsupervised Noise2Noise strategy for noise reduction of optical coherence tomography images
Comparative study of deep neural networks with unsupervised Noise2Noise strategy for noise reduction of optical coherence tomography images
复制标题
深度神经网络与无监督Noise2Noise策略对光学相干断层扫描图像降噪的比较研究
DOI：
10.1002/jbio.202100151
复制
发表时间：
2021-08-20
影响因子：
2.8
通讯作者：
Lu, Yanye
中科院分区：
文献类型：
--
作者：
Qiu, Bin;Zeng, Shuang;Lu, Yanye
光学相干层析成像(OCT)作为一种强大的诊断工具，已被广泛应用于各种临床环境中。然而，由于低相干干涉成像过程，OCT图像容易受到固有的斑点噪声的影响，这些斑点噪声可能会污染细微的结构信息。许多基于监督学习的模型在抑制由大量噪声清洁的OCT图像训练的OCT图像的斑点噪声方面取得了令人印象深刻的性能，这在临床实践中并不常见。本文通过一种无监督Noise2Noise(N2N)策略，对OCT图像在不同深度神经网络上的去噪性能进行了比较研究，该策略只用有噪声的OCT样本进行训练。基于健康人眼OCT图像数据集，研究了U型模型、多信息流模型、直线型信息流模型和基于GaN的模型四种典型的网络结构。实验结果表明，四种非监督N2N模型均能得到与监督学习模型相当的去噪OCT图像，说明了非监督N2N模型对OCT图像去噪的有效性。此外，在无监督N2N环境下，U形模型和基于氮化镓网络的GaN模型是抑制OCT图像相干斑噪声和保留视网膜层精细结构信息的两种首选结构。
As a powerful diagnostic tool, optical coherence tomography (OCT) has been widely used in various clinical setting. However, OCT images are susceptible to inherent speckle noise that may contaminate subtle structure information, due to low-coherence interferometric imaging procedure. Many supervised learning-based models have achieved impressive performance in reducing speckle noise of OCT images trained with a large number of noisy-clean paired OCT images, which are not commonly feasible in clinical practice. In this article, we conducted a comparative study to investigate the denoising performance of OCT images over different deep neural networks through an unsupervised Noise2Noise (N2N) strategy, which only trained with noisy OCT samples. Four representative network architectures including U-shaped model, multi-information stream model, straight-information stream model and GAN-based model were investigated on an OCT image dataset acquired from healthy human eyes. The results demonstrated all four unsupervised N2N models offered denoised OCT images with a performance comparable with that of supervised learning models, illustrating the effectiveness of unsupervised N2N models in denoising OCT images. Furthermore, U-shaped models and GAN-based models using UNet network as generator are two preferred and suitable architectures for reducing speckle noise of OCT images and preserving fine structure information of retinal layers under unsupervised N2N circumstances.