Department of Ophthalmology, University of Washington, Seattle, Washington, USA.
Department of Molecular Medicine, The Scripps Research Institute, La Jolla, California, USA.
JCI Insight. 2017 Dec 21;2(24):97585. doi: 10.1172/jci.insight.97585.
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.
氧诱导视网膜病变（OIR）是一种广泛用于研究视网膜缺血驱动的新生血管化（NV）的模型，也可用于评估眼部和非眼部疾病的抗血管生成药物的概念验证研究。该小鼠模型中分析的主要参数包括视网膜血管闭塞（VO）和 NV 区域的百分比。然而，由于需要人类专家来阅读图像，因此对这两个关键变量进行定量分析具有很大的挑战性。人类读者成本高、耗时且容易产生偏差。利用机器学习和计算机视觉的最新进展，我们使用一千多个分割对深度学习神经网络进行了训练，以实现 OIR 图像的完全自动化分割。在确定 VO 面积百分比时，我们的算法与专家之间的人类相关性系数的相关性范围相似。此外，与专家之间的相关性系数相比，我们的算法在量化新生血管丛的百分比面积方面具有更高的相关性范围。总之，我们使用深度学习神经网络创建了一个开源的、完全自动化的 OIR 图像关键值定量分析流水线。
