Centre for Visual Information Technology, International Institute of Information Technology, Hyderabad 500032, India.
Comput Methods Programs Biomed. 2018 Oct;165:235-250. doi: 10.1016/j.cmpb.2018.09.004. Epub 2018 Sep 5.
Accurate segmentation of the intra-retinal tissue layers in Optical Coherence Tomography (OCT) images plays an important role in the diagnosis and treatment of ocular diseases such as Age-Related Macular Degeneration (AMD) and Diabetic Macular Edema (DME). The existing energy minimization based methods employ multiple, manually handcrafted cost terms and often fail in the presence of pathologies. In this work, we eliminate the need to handcraft the energy by learning it from training images in an end-to-end manner. Our method can be easily adapted to pathologies by re-training it on an appropriate dataset.
We propose a Conditional Random Field (CRF) framework for the joint multi-layer segmentation of OCT B-scans. The appearance of each retinal layer and boundary is modeled by two convolutional filter banks and the shape priors are modeled using Gaussian distributions. The total CRF energy is linearly parameterized to allow a joint, end-to-end training by employing the Structured Support Vector Machine formulation.
The proposed method outperformed three benchmark algorithms on four public datasets. The NORMAL-1 and NORMAL-2 datasets contain healthy OCT B-scans while the AMD-1 and DME-1 dataset contain B-scans of AMD and DME cases respectively. The proposed method achieved an average unsigned boundary localization error (U-BLE) of 1.52 pixels on NORMAL-1, 1.11 pixels on NORMAL-2 and 2.04 pixels on the combined NORMAL-1 and DME-1 dataset across the eight layer boundaries, outperforming the three benchmark methods in each case. The Dice coefficient was 0.87 on NORMAL-1, 0.89 on NORMAL-2 and 0.84 on the combined NORMAL-1 and DME-1 dataset across the seven retinal layers. On the combined NORMAL-1 and AMD-1 dataset, we achieved an average U-BLE of 1.86 pixels on the ILM, inner and outer RPE boundaries and a Dice of 0.98 for the ILM-RPE region and 0.81 for the RPE layer.
We have proposed a supervised CRF based method to jointly segment multiple tissue layers in OCT images. It can aid the ophthalmologists in the quantitative analysis of structural changes in the retinal tissue layers for clinical practice and large-scale clinical studies.
在光学相干断层扫描（OCT）图像中准确分割视网膜内组织层在诊断和治疗年龄相关性黄斑变性（AMD）和糖尿病性黄斑水肿（DME）等眼部疾病中起着重要作用。现有的基于能量最小化的方法使用多个手动制作的成本项，并且在存在病变的情况下常常失败。在这项工作中，我们通过以端到端的方式从训练图像中学习来消除对手工制作能量的需求。我们的方法可以通过在适当的数据集上重新训练来轻松适应病变。
我们提出了一种用于 OCT B 扫描的联合多层分割的条件随机场（CRF）框架。每个视网膜层和边界的外观由两个卷积滤波器组建模，形状先验使用高斯分布建模。通过使用结构化支持向量机公式，线性参数化总 CRF 能量以允许联合，端到端训练。
该方法在四个公共数据集上优于三种基准算法。NORMAL-1 和 NORMAL-2 数据集包含健康的 OCT B 扫描，而 AMD-1 和 DME-1 数据集分别包含 AMD 和 DME 病例的 B 扫描。该方法在 NORMAL-1 上的平均无符号边界定位误差（U-BLE）为 1.52 像素，在 NORMAL-2 上为 1.11 像素，在合并的 NORMAL-1 和 DME-1 数据集上为 2.04 像素，在每种情况下均优于三种基准方法。在 NORMAL-1 上的 Dice 系数为 0.87，在 NORMAL-2 上为 0.89，在合并的 NORMAL-1 和 DME-1 数据集上为 0.84，跨越七个视网膜层。在合并的 NORMAL-1 和 AMD-1 数据集上，我们在内界膜（ILM），内和外视网膜色素上皮（RPE）边界上获得了平均 U-BLE 为 1.86 像素，在 ILM-RPE 区域的 Dice 为 0.98，在 RPE 层的 Dice 为 0.81。
我们提出了一种基于监督 CRF 的方法来联合分割 OCT 图像中的多个组织层。它可以帮助眼科医生进行视网膜组织层结构变化的定量分析，用于临床实践和大规模临床研究。
