He Yufan, Carass Aaron, Liu Yihao, Jedynak Bruno M, Solomon Sharon D, Saidha Shiv, Calabresi Peter A, Prince Jerry L
Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA.
Department of Electrical and Computer Engineering, The Johns Hopkins University, Baltimore, MD 21218, USA; Department of Computer Science, The Johns Hopkins University, Baltimore, MD 21218, USA.
Med Image Anal. 2021 Feb;68:101856. doi: 10.1016/j.media.2020.101856. Epub 2020 Oct 14.
Optical coherence tomography (OCT) is a noninvasive imaging modality with micrometer resolution which has been widely used for scanning the retina. Retinal layers are important biomarkers for many diseases. Accurate automated algorithms for segmenting smooth continuous layer surfaces with correct hierarchy (topology) are important for automated retinal thickness and surface shape analysis. State-of-the-art methods typically use a two step process. Firstly, a trained classifier is used to label each pixel into either background and layers or boundaries and non-boundaries. Secondly, the desired smooth surfaces with the correct topology are extracted by graph methods (e.g., graph cut). Data driven methods like deep networks have shown great ability for the pixel classification step, but to date have not been able to extract structured smooth continuous surfaces with topological constraints in the second step. In this paper, we combine these two steps into a unified deep learning framework by directly modeling the distribution of the surface positions. Smooth, continuous, and topologically correct surfaces are obtained in a single feed forward operation. The proposed method was evaluated on two publicly available data sets of healthy controls and subjects with either multiple sclerosis or diabetic macular edema, and is shown to achieve state-of-the art performance with sub-pixel accuracy.
光学相干断层扫描（OCT）是一种具有微米级分辨率的非侵入性成像方式，已被广泛用于扫描视网膜。视网膜层是许多疾病的重要生物标志物。用于分割具有正确层次结构（拓扑结构）的平滑连续层表面的精确自动算法，对于自动视网膜厚度和表面形状分析很重要。当前的先进方法通常采用两步法。首先，使用经过训练的分类器将每个像素标记为背景和层或边界和非边界。其次，通过图形方法（例如图割）提取具有正确拓扑结构的所需平滑表面。像深度网络这样的数据驱动方法在像素分类步骤中显示出强大的能力，但迄今为止，在第二步中还无法提取具有拓扑约束的结构化平滑连续表面。在本文中，我们通过直接对表面位置的分布进行建模，将这两个步骤合并为一个统一的深度学习框架。在单次前馈操作中即可获得平滑、连续且拓扑正确的表面。我们在两个公开可用的数据集上对所提出的方法进行了评估，这两个数据集分别来自健康对照者以及患有多发性硬化症或糖尿病性黄斑水肿的受试者，结果表明该方法以亚像素精度达到了当前的先进性能。
