Automated segmentation of geographic atrophy of the retinal epithelium via random forests in AREDS color fundus images.
Automated segmentation of geographic atrophy of the retinal epithelium via random forests in AREDS color fundus images.
复制标题
DOI：
10.1016/j.compbiomed.2015.06.018
复制
发表时间：
2015-10-01
影响因子：
7.7
通讯作者：
Burlina P
中科院分区：
文献类型：
--
作者：
Feeny AK;Tadarati M;Freund DE;Bressler NM;Burlina P
未经治疗的老年性黄斑变性(AMD)是55岁以上人群视力丧失的主要原因。严重的中枢性视力丧失发生在疾病的晚期，其特征是脉络膜新生血管(CNV)生长缓慢，称为“湿性”形式，或视网膜色素上皮(RPE)的地理萎缩，累及黄斑中心，称为“干性”形式。跟踪GA面积随时间的变化很重要，因为它允许表征GA治疗的有效性。追踪GA的演变可以通过医生在视网膜眼底图像上手动描绘GA区域来实现。然而，手动GA描述是耗时的，并且受到观察者之间和观察者内部变异性的影响。我们开发了一种在彩色眼底图像中使用监督机器学习方法的全自动GA分割算法，该方法采用随机森林分类器。该算法是使用NIH赞助的年龄相关眼病研究(AREDS)的图像数据集开发和测试的。将GA分割输出与视网膜专家的手动描绘进行比较。使用55个不同患者眼的143幅彩色眼底图像，我们的算法获得了0.82±0.19的PPV和0：95±0.07的NPV。据我们所知，这是第一次将机器学习方法应用于彩色眼底图像的GA分割，并使用AREDS图像进行测试。这些初步结果表明，机器学习方法可能在从彩色眼底图像中自动表征GA方面具有实用价值。
Age-related macular degeneration (AMD), left untreated, is the leading cause of vision loss in people older than 55. Severe central vision loss occurs in the advanced stage of the disease, characterized by either the in growth of choroidal neovascularization (CNV), termed the “wet” form, or by geographic atrophy (GA) of the retinal pigment epithelium (RPE) involving the center of the macula, termed the “dry” form. Tracking the change in GA area over time is important since it allows for the characterization of the effectiveness of GA treatments. Tracking GA evolution can be achieved by physicians performing manual delineation of GA area on retinal fundus images. However, manual GA delineation is time-consuming and subject to inter-and intra-observer variability. We have developed a fully automated GA segmentation algorithm in color fundus images that uses a supervised machine learning approach employing a random forest classifier. This algorithm is developed and tested using a dataset of images from the NIH-sponsored Age Related Eye Disease Study (AREDS). GA segmentation output was compared against a manual delineation by a retina specialist. Using 143 color fundus images from 55 different patient eyes, our algorithm achieved PPV of 0.82±0.19, and NPV of 0:95±0.07. This is the first study, to our knowledge, applying machine learning methods to GA segmentation on color fundus images and using AREDS imagery for testing. These preliminary results show promising evidence that machine learning methods may have utility in automated characterization of GA from color fundus images.