Soochow University, School of Electronics and Information Engineering, Suzhou, China.
Shantou University and the Chinese University of Hong Kong, Joint Shantou International Eye Center, Shantou, ChinacThe Chinese University of Hong Kong, Department of Ophthalmology and Visual Sciences, Hong Kong, China.
J Biomed Opt. 2017 Jul 1;22(7):76014. doi: 10.1117/1.JBO.22.7.076014.
Cystoid macular edema (CME) and macular hole (MH) are the leading causes for visual loss in retinal diseases. The volume of the CMEs can be an accurate predictor for visual prognosis. This paper presents an automatic method to segment the CMEs from the abnormal retina with coexistence of MH in three-dimensional-optical coherence tomography images. The proposed framework consists of preprocessing and CMEs segmentation. The preprocessing part includes denoising, intraretinal layers segmentation and flattening, and MH and vessel silhouettes exclusion. In the CMEs segmentation, a three-step strategy is applied. First, an AdaBoost classifier trained with 57 features is employed to generate the initialization results. Second, an automated shape-constrained graph cut algorithm is applied to obtain the refined results. Finally, cyst area information is used to remove false positives (FPs). The method was evaluated on 19 eyes with coexistence of CMEs and MH from 18 subjects. The true positive volume fraction, FP volume fraction, dice similarity coefficient, and accuracy rate for CMEs segmentation were 81.0%±7.8%, 0.80%±0.63%, 80.9%±5.7%, and 99.7%±0.1%, respectively.
囊样黄斑水肿 (CME) 和黄斑裂孔 (MH) 是视网膜疾病导致视力丧失的主要原因。CME 的体积可以作为预测视力预后的准确指标。本文提出了一种自动方法，用于从三维光学相干断层扫描图像中存在 MH 的异常视网膜中分割 CME。所提出的框架包括预处理和 CME 分割。预处理部分包括去噪、内视网膜层分割和平整化，以及 MH 和血管轮廓的排除。在 CME 分割中，应用了三步策略。首先，使用 57 个特征训练 AdaBoost 分类器来生成初始化结果。其次，应用自动形状约束图割算法来获得细化结果。最后，利用囊区信息去除假阳性 (FP)。该方法在 18 名受试者的 19 只存在 CME 和 MH 的眼中进行了评估。CME 分割的真阳性体积分数、FP 体积分数、骰子相似系数和准确率分别为 81.0%±7.8%、0.80%±0.63%、80.9%±5.7%和 99.7%±0.1%。
