19 Jul Speculor: A Comprehensive Teleophthalmology Platform for People Centered Eyecare
There are over 240 million cases of preventable blindness globally. Many eye diseases are “silent-killers” of vision and current testing methods are often inaccessible for marginalized patients. Thus, diseases go undetected until it is too late. To combat this issue, I developed Speculor combining low-cost portable retinal imagers and smartphones with artificial intelligence algorithms. Imagers have been tested in a clinic and detect all clinically relevant features required for accurate diagnosis of the disease glaucoma. Novel image processing algorithms improve the acquired image quality. A new transfer learning method was invented to train convolutional neural networks on small datasets that has demonstrated the best reported results in literature for the classification of glaucoma.