Shanghai Institute of Technology, Shanghai, 201418, People's Republic of China.
Phys Med Biol. 2022 Jul 8;67(14). doi: 10.1088/1361-6560/ac799a.
The shape and structure of retinal layers are basic characteristics for the diagnosis of many ophthalmological diseases. Based on B-Scans of optical coherence tomography, most of retinal layer segmentation methods are composed of two-steps: classifying pixels and extracting retinal layers, in which the optimization of two independent steps decreases the accuracy. Although the methods based on deep learning are highly accurate, they require a large amount of labeled data. This paper proposes a single-step method based on transformer for retinal layer segmentation, which is trained by axial data (A-Scans), to obtain the boundary of each layer. The proposed method was evaluated on two public data sets. The first one contains eight retinal layer boundaries for diabetic macular edema, and the second one contains nine retinal layer boundaries for healthy controls and subjects with multiple sclerosis. Its absolute average distance errors are 0.99 pixels and 3.67 pixels, respectively, for the two sets, and its root mean square error is 1.29 pixels for the latter set. In addition, its accuracy is acceptable even if the training data is reduced to 0.3. The proposed method achieves state-of-the-art performance while maintaining the correct topology and requires less labeled data.
视网膜层的形状和结构是许多眼科疾病诊断的基本特征。基于光学相干断层扫描的 B 扫描，大多数视网膜层分割方法由两步组成：像素分类和提取视网膜层，其中两个独立步骤的优化降低了准确性。虽然基于深度学习的方法非常准确，但它们需要大量标记数据。本文提出了一种基于转换器的用于视网膜层分割的单步方法，该方法通过轴向数据 (A 扫描) 进行训练，以获得各层的边界。该方法在两个公共数据集上进行了评估。第一个数据集包含 8 个糖尿病性黄斑水肿的视网膜层边界，第二个数据集包含 9 个健康对照者和多发性硬化症患者的视网膜层边界。对于这两个数据集，其绝对平均距离误差分别为 0.99 像素和 3.67 像素，而对于后一个数据集，其均方根误差为 1.29 像素。此外，即使训练数据减少到 0.3，该方法的准确性也可以接受。该方法在保持正确拓扑结构的同时实现了最先进的性能，并且需要更少的标记数据。
