• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Scientific reports. >A Deep Learning Approach to Denoise Optical Coherence Tomography Images of the Optic Nerve Head
【24h】

A Deep Learning Approach to Denoise Optical Coherence Tomography Images of the Optic Nerve Head

机译：光神经顶头去噪光学相干断层扫描图像的深度学习方法

获取原文
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Optical coherence tomography (OCT) has become an established clinical routine for the in vivo imaging of the optic nerve head (ONH) tissues, that is crucial in the diagnosis and management of various ocular and neuro-ocular pathologies. However, the presence of speckle noise affects the quality of OCT images and its interpretation. Although recent frame-averaging techniques have shown to enhance OCT image quality, they require longer scanning durations, resulting in patient discomfort. Using a custom deep learning network trained with 2,328 'clean B-scans' (multi-frame B-scans; signal averaged), and their corresponding 'noisy B-scans' (clean B-scans?+?Gaussian noise), we were able to successfully denoise 1,552 unseen single-frame (without signal averaging) B-scans. The denoised B-scans were qualitatively similar to their corresponding multi-frame B-scans, with enhanced visibility of the ONH tissues. The mean signal to noise ratio (SNR) increased from 4.02?±?0.68?dB (single-frame) to 8.14?±?1.03?dB (denoised). For all the ONH tissues, the mean contrast to noise ratio (CNR) increased from 3.50?±?0.56 (single-frame) to 7.63?±?1.81 (denoised). The mean structural similarity index (MSSIM) increased from 0.13?±?0.02 (single frame) to 0.65?±?0.03 (denoised) when compared with the corresponding multi-frame B-scans. Our deep learning algorithm can denoise a single-frame OCT B-scan of the ONH in under 20?ms, thus offering a framework to obtain superior quality OCT B-scans with reduced scanning times and minimal patient discomfort.
机译：光学相干断层扫描（OCT）已成为视神经头部（ONH）组织的体内成像的既定临床常规，这在各种眼部和神经眼病理学的诊断和管理中至关重要。然而，斑点噪声的存在会影响OCT图像的质量及其解释。尽管最近的帧平均技术已经显示为增强OCT图像质量，但它们需要更长的扫描持续时间，导致患者不适。使用带有2,328“清洁B-SCANS的自定义深度学习网络（多帧B-SCANS;信号平均），以及它们相应的”嘈杂的B-SCANS“（清洁B-SCANS？+？高斯噪音），我们是能够成功去噪1,552个看不见的单帧（没有信号平均）B扫描。去氧化B扫描与其相应的多帧B扫描定性类似，具有增强的ONH组织的可见性。噪声比（SNR）的平均信号从4.02°（SNR）增加到0.68Ω·dB（单帧）至8.14？±1.03？DB（去噪）。对于所有ONH组织，与噪声比（CNR）的平均对比度从3.50°（CNR）增加到3.50？±0.56（单帧）至7.63？±1.81（去噪）。与相应的多帧B扫描相比，平均结构相似指数（MSSIM）从0.13Ω·Δ0（单帧）增加到0.65°（单帧）至0.65？0.03（去噪）。我们的深度学习算法可以在20岁以下的20岁以下的ONH的单帧OCT B-SCAN扫描，从而提供框架，以获得扫描时间和最小患者的患者不适来获得优质的OCT B扫描。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号