We plan to construct a clinically useful model to identify several ocular diseases automatically, and improve the efficiency of diagnosis.
Artificial intelligence (AI) has the potential to revolutionize disease diagnosis and management by performing classification difficult for human experts. Within ophthalmology, artificial intelligence is already augmenting diagnostic imaging capabilities, which may soon lead to deployment of cost-efficient telemedicine screening programs worldwide. The majority of these early efforts have focused on the analysis of color fundus photographs or optical coherence tomography (OCT) scans for detection of posterior segment diseases such as diabetic retinopathy, age-related macular degeneration, and glaucoma. Deep learning refers to a subset of artificial intelligence, composed of algorithms that use a cascade of multilayered artificial neural networks for feature extraction and transformation. Drawing inspiration from the structure of the human mind, convolutional neural networks consist of thousands of individual neurons capable of performing complex tasks, such as image recognition and classification, based on pixel or voxel intensity. Each successive layer in the network uses the output from the previous layer as input, with the final layer revealing the diagnostic output. There are a lot of studies for retinal image classification selected binary classification. But the results of studies about multi-categorical retinal image classification were not as good as binary classification. In the other hand, many ocular diseases have been considered genetically defined complex disorders such as AMD and DR. For example, with 50% or more of the heritability of AMD already explained by two major loci harboring coding and non-coding variation at chromosomes 1q (CFH) and 10q (ARMS2/HTRA1). So it’s available to identify some ocular diseases through genetic classifier.
We expect to finish this project in 3 years. If all goes well, this study will increase efficiency of medical diagnosis, reduce barriers to access for areas where an eye care provider may not be present, provide earlier detection of referable eye disease, improve prognosis and decreasing healthcare costs through earlier intervention of treatable disease.
