Unknown

Dataset Information

0

Fully automated, deep learning segmentation of oxygen-induced retinopathy images.


ABSTRACT: 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.

SUBMITTER: Xiao S 

PROVIDER: S-EPMC5752269 | biostudies-literature | 2017 Dec

REPOSITORIES: biostudies-literature

altmetric image

Publications

Fully automated, deep learning segmentation of oxygen-induced retinopathy images.

Xiao Sa S   Bucher Felicitas F   Wu Yue Y   Rokem Ariel A   Lee Cecilia S CS   Marra Kyle V KV   Fallon Regis R   Diaz-Aguilar Sophia S   Aguilar Edith E   Friedlander Martin M   Lee Aaron Y AY  

JCI insight 20171221 24


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 re  ...[more]

Similar Datasets

| S-EPMC10881508 | biostudies-literature
| S-EPMC7289260 | biostudies-literature
| S-EPMC8082409 | biostudies-literature
| S-EPMC7784718 | biostudies-literature
| S-EPMC10432383 | biostudies-literature
| S-EPMC9077502 | biostudies-literature
| S-EPMC7858625 | biostudies-literature
| S-EPMC11007525 | biostudies-literature
| S-EPMC8652855 | biostudies-literature
| S-EPMC6291436 | biostudies-literature