2018 · 37 citations · 18 references
ComputingComputer ScienceOphthalmologyComputer VisionMachine LearningMachine VisionDeep LearningGlaucomaMedical Image AnalysisPattern RecognitionRepresentation LearningTransfer LearningAccuracyBenchmark DatasetsClinical Test AccuracyDeep Learning DiagnosticsDeep Learning-based ClassificationIndependent Dataset ValidationOptic Nerve Head EvaluationSmall Sample Overfitting
We developed a deep learning algorithm for identifying glaucoma on optic nerve head (ONH) photographs. We applied transfer learning to overcome overfitting on the small training sample size that we employed. The transfer learning framework that was previously trained on large datasets such as ImageNet, uses the initial parameters and makes the approach applicable to small sample sizes. We then classified the input ONH photographs as “normal” or “glaucoma”. The proposed approach achieved a validation accuracy of 92.3% on a dataset of 277 ONH photographs from normal eyes and 170 ONH photographs from eyes with glaucoma. In order to re-test the accuracy and generalizability of the proposed approach, we re-tested the algorithm using an independent dataset of 30 ONH photographs. The re-test accuracy was 80.0% on average.
18
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke et al. · 2017 · 12.6K citations · Full text
Robust Vessel Segmentation in Fundus Images
Attila Budai, Rüdiger Bock, Anatol Maier et al. · International Journal of Biomedical Imaging · 2013 · 633 citations · Full text
Health Professions, Biomedical Engineering, Ophthalmology +17