Glaucoma Detection From Raw Circumapillary OCT Images Using Fully Convolutional Neural Networks
This work addresses glaucoma detection for medical diagnosis, but it is incremental as it applies existing fine-tuning methods to a specific dataset.
The paper tackled glaucoma detection from raw circumpapillary OCT images using two deep learning approaches: training CNNs from scratch and fine-tuning state-of-the-art architectures, achieving an area under the ROC curve of 0.96 and accuracy of 0.92 with fine-tuned VGG networks on a small private dataset.
Nowadays, glaucoma is the leading cause of blindness worldwide. We propose in this paper two different deep-learning-based approaches to address glaucoma detection just from raw circumpapillary OCT images. The first one is based on the development of convolutional neural networks (CNNs) trained from scratch. The second one lies in fine-tuning some of the most common state-of-the-art CNNs architectures. The experiments were performed on a private database composed of 93 glaucomatous and 156 normal B-scans around the optic nerve head of the retina, which were diagnosed by expert ophthalmologists. The validation results evidence that fine-tuned CNNs outperform the networks trained from scratch when small databases are addressed. Additionally, the VGG family of networks reports the most promising results, with an area under the ROC curve of 0.96 and an accuracy of 0.92, during the prediction of the independent test set.