基于稀疏表示的频域OCT图像降噪技术研究

在压缩感知理论的基础上提出了一种非规则采样层析数据的重建方法, 主要研究了频域光学相关层析(SDOCT)数据的降噪问题。采用传统的B-scans扫描模式得到一系列具有高SNR的图像, 对每一幅高SNR图像训练得到一个稀疏表示字典, 然后由所得到的稀疏表示字典对低SNR的B-scans图像进行降噪, 称这种方法为多层稀疏层析降噪算法(MSBTD)。其基本原理是在通常的SDOCT数据中, 相邻的B-scans数据具有相同的结构和噪声类型。其优点在于其不需要在大多数方位向获取超过一个B-scans数据, 因此会明显降低扫描时间。尽管稀疏表示方法在图像处理领域得到了广泛的应用, 但是MSBTD算法的最大创新点在于其结合了一种常用的扫描算法, 使其适用于医学上的SDOCT处理。仿真表明MSBTD算法能够取得优于传统降噪方法的结果。

Spectral domain OCT image denoising based on sparse representation

This paper made contact with the field of compressive sensing and presented a development and generalization of tools and results for reconstructing irregularly sampled tomographic data. In particular, it focused on denoising spectral-domain optical coherence tomography(SDOCT) volumetric data. It took advantage of customized scanning patterns, in which, a selected number of B-scans were imaged at higher signal-to-noise ratio(SNR). It learnt a sparse representation dictionary for each of these high-SNR images, and utilized such dictionaries to denoise the low-SNR B-scans. This paper named this method multiscale sparsity based tomographic denoising(MSBTD). It shows the qualitative and quantitative superiority of the MSBTD algorithm compared to popular denoising algorithms on images from normal and age-related macular degeneration eyes of a multi-center clinical trial.