Procedia Computer Science · 2016 · 951 citations · 15 references
ComputingComputer ScienceOphthalmologyComputer VisionMachine LearningMachine VisionComputer-aided DiagnosisDeep LearningDiabetic RetinopathyFeature DetectionImage ClassificationMedical Image AnalysisConvolutional Neural Network DetectionConvolutional Neural NetworksData AugmentationDeep Learning-based ClassificationDeep Learning-based DiagnosisDiabetic Retinopathy GradingMedical Image ClassificationRetinal Feature Detection
Diagnosis of diabetic retinopathy from color fundus images is laborious and requires experienced clinicians to detect numerous small features within a complex grading system. This study proposes a convolutional neural network to diagnose diabetic retinopathy from digital fundus images and accurately classify its severity. The authors built a CNN with data augmentation that automatically detects microaneurysms, exudates, and hemorrhages, and trained it on a GPU using the publicly available Kaggle dataset. On 80,000 training images, the CNN achieved 95 % sensitivity and 75 % accuracy on a 5,000‑image validation set.
The diagnosis of diabetic retinopathy (DR) through colour fundus images requires experienced clinicians to identify the presence and significance of many small features which, along with a complex grading system, makes this a difficult and time consuming task. In this paper, we propose a CNN approach to diagnosing DR from digital fundus images and accurately classifying its severity. We develop a network with CNN architecture and data augmentation which can identify the intricate features involved in the classification task such as micro-aneurysms, exudate and haemorrhages on the retina and consequently provide a diagnosis automatically and without user input. We train this network using a high-end graphics processor unit (GPU) on the publicly available Kaggle dataset and demonstrate impressive results, particularly for a high-level classification task. On the data set of 80,000 images used our proposed CNN achieves a sensitivity of 95% and an accuracy of 75% on 5,000 validation images.
15
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Dropout: a simple way to prevent neural networks from overfitting
Nitish Srivastava, Geoffrey E. Hinton, Alex Krizhevsky et al. · 2014 · 34.3K citations
Advances in neural information processing systems 7
Krzysztof J. Cios, Mark E. Shields · Neurocomputing · 1997 · 22.3K citations