Fully automated, deep learning segmentation of oxygen-induced retinopathy images
Fully automated, deep learning segmentation of oxygen-induced retinopathy images
复制标题
DOI：
10.1172/jci.insight.97585
复制
发表时间：
2017-12-21
期刊：
影响因子：
8
通讯作者：
Lee, Aaron Y.
中科院分区：
文献类型：
--
作者：
Xiao, Sa;Bucher, Felicitas;Lee, Aaron Y.
氧诱导的视网膜病变（OIR）是一种广泛使用的模型，用于研究视网膜中缺血驱动的新生血管形成（NV），并用于评价用于眼部以及非眼部疾病的抗血管生成药物的概念验证研究。在该小鼠模型中分析的主要参数包括具有血管闭塞（VO）和NV面积的视网膜的百分比。然而，由于人类专家需要阅读图像，这两个关键变量的量化带来了巨大的挑战。人类读者是昂贵的，耗时的，并受到偏见。利用机器学习和计算机视觉的最新进展，我们使用超过一千个分割来训练深度学习神经网络，以完全自动化OIR图像的分割。在确定VO的百分比面积时，我们的算法实现了与专家人间相关系数相似的相关系数范围。此外，我们的算法实现了更高范围的相关系数相比，专家间的相关系数定量的百分比面积的新生血管簇。总之，我们已经创建了一个开源的、全自动的管道，用于使用深度学习神经网络量化OIR图像的关键值。
Oxygen-induced retinopathy (OIR) is a widely used model to study ischemia-driven neovascularization (NV) in the retina and to serve in proof-of-concept studies in evaluating antiangiogenic drugs for ocular, as well as nonocular, diseases. The primary parameters that are analyzed in this mouse model include the percentage of retina with vaso-obliteration (VO) and NV areas. However, quantification of these two key variables comes with a great challenge due to the requirement of human experts to read the images. Human readers are costly, time-consuming, and subject to bias. Using recent advances in machine learning and computer vision, we trained deep learning neural networks using over a thousand segmentations to fully automate segmentation in OIR images. While determining the percentage area of VO, our algorithm achieved a similar range of correlation coefficients to that of expert inter-human correlation coefficients. In addition, our algorithm achieved a higher range of correlation coefficients compared with inter-expert correlation coefficients for quantification of the percentage area of neovascular tufts. In summary, we have created an open-source, fully automated pipeline for the quantification of key values of OIR images using deep learning neural networks.