School of Engineering, University of Edinburgh, United Kingdom.
J Biomed Opt. 2012 Oct;17(10):106010. doi: 10.1117/1.JBO.17.10.106010.
We describe a computer-aided measuring tool, named parapapillary atrophy and optic disc region assessment (PANDORA), for automated detection and quantification of both the parapapillary atrophy (PPA) and the optic disc (OD) regions in two-dimensional color retinal fundus images. The OD region is segmented using a combination of edge detection and ellipse fitting methods. The PPA region is identified by the presence of bright pixels in the temporal zone of the OD, and it is segmented using a sequence of techniques, including a modified Chan-Vese approach, thresholding, scanning filter, and multiseed region growing. PANDORA has been tested with 133 color retinal images (82 with PPA; 51 without PPA) drawn randomly from the Lothian Birth Cohort (LBC) database, together with a "ground truth" estimate from an ophthalmologist. The PPA detection rate is 89.47% with a sensitivity of 0.83 and a specificity of 1. The mean accuracy in defining the OD region is 81.31% (SD=10.45) when PPA is present and 95.32% (SD=4.36) when PPA is absent. The mean accuracy in defining the PPA region is 73.57% (SD=11.62). PANDORA demonstrates for the first time how to quantify the OD and PPA regions using two-dimensional fundus images, enabling ophthalmologists to study ocular diseases related to PPA using a standard fundus camera.
我们描述了一种名为视盘旁萎缩和视盘区域评估（PANDORA）的计算机辅助测量工具，用于在二维彩色眼底图像中自动检测和量化视盘旁萎缩（PPA）和视盘（OD）区域。OD 区域使用边缘检测和椭圆拟合方法的组合进行分割。PPA 区域通过 OD 颞区的亮像素来识别，并使用一系列技术进行分割，包括修改后的 Chan-Vese 方法、阈值处理、扫描滤波器和多种子区域生长。PANDORA 已经在 Lothian 出生队列（LBC）数据库中随机抽取的 133 张彩色眼底图像（82 张有 PPA；51 张没有 PPA）以及一位眼科医生的“真实”估计进行了测试。当 PPA 存在时，PPA 的检测率为 89.47%，灵敏度为 0.83，特异性为 1。当 PPA 不存在时，OD 区域定义的平均准确度为 81.31%（SD=10.45）。PPA 区域定义的平均准确度为 73.57%（SD=11.62）。PANDORA 首次展示了如何使用二维眼底图像量化 OD 和 PPA 区域，使眼科医生能够使用标准眼底相机研究与 PPA 相关的眼部疾病。
