Automated detection of exudative age-related macular degeneration in spectral domain optical coherence tomography using deep learning

Abstract

With a deep learning-based approach using TensorFlow™, it is possible to detect AMD in SD-OCT with high sensitivity and specificity. With more image data, an expansion of this classifier for other macular diseases or further details in AMD is possible, suggesting an application for this model as a support in clinical decisions. Another possible future application would involve the individual prediction of the progress and success of therapy for different diseases by automatically detecting hidden image information.

Current state and future prospects of artificial intelligence in ophthalmology: a review

“…His group included 108 312 images (from 4686 patients) to train the MLC and a separate 1000 images (from 633 patients) to validate its capabilities. 38,[46][47][48] Ultimately, as the MLCs perform at a level similar to professional graders, it appears that an MLC created using a CNN could be a useful system for screening for AMD. The MLC achieved a sensitivity of 0.978, a specificity of 0.974 and a AUROC of 0.999 in its task of retinal disease classification.…”

“…Kermany et al developed a diagnostic tool for screening patients with common treatable blinding retinal diseases, including diabetic macular oedema (DME) and AMD. 47 48 All of these studies used a variation of a CNN, which is good at classifying images as the input is assessed at the pixel level. 46 The MLC stratified the conditions according to need for the patient to be seen, with conditions like choroidal neovascularization and DME classified as 'urgent referrals', and drusen as part of dry AMD classified as a 'routine referral'.…”

“…Treder et al used OCT imaging (1112 images) to create a MLC that differentiates a healthy macula with one showing exudative AMD, with a sensitivity of 1.00 and a specificity of 0.92. 48 All of these studies used a variation of a CNN, which is good at classifying images as the input is assessed at the pixel level. 38,[46][47][48] Ultimately, as the MLCs perform at a level similar to professional graders, it appears that an MLC created using a CNN could be a useful system for screening for AMD.…”

Application of machine learning in ophthalmic imaging modalities

“…The results showed that classifications of low-and high-treatment requirement subgroups demonstrated AUCs of 0.7 and 0.77, respectively [86]. Treder et al showed that a DL algorithm exhibited good performance for automated detection of AMD in spectral domain OCT [87]. This pilot study was an important step toward automated image-guided prediction of treatment intervals in patients with neovascular AMD.…”

Two-Stream CNN with Loose Pair Training for Multi-modal AMD Categorization

“…The majority of previous works are based on a single modality, let it be color fundus images capturing the posterior pole [1,3,2,6] or OCT images [12,9,14,13,10]. In [1], for instance, Burlina et al employ a deep convolutional neural network (CNN) pretrained on ImageNet to extract visual features from fundus images and then train a linear SVM classifier.…”