VSI: Artificial Intelligence and Big Data
Ophthalmology Science has published a special virtual issue featuring Big Data & Artificial Intelligence (AI) articles. The collection includes novel methodologies, such as non-traditional statistical approaches that can be applied to Big Data and machine learning/deep learning studies. Our goal for this special issue is to initiate discussions of current challenges and potential strategies to overcome them. Some examples include standardization of datasets, data sharing processes, data privacy, and obstacles for transferring research findings into clinical care. Understanding both the potential and limitations of Big Data and AI approaches through an array of diverse studies and commentaries is the primary goal of this Ophthalmology Science special issue. We are grateful for authors who submitted to this special collection and we thank our guest editors, James D. Brandt, MD (University of California Davis Medical Center), Aaron Yuntai Lee, MD, MSCI (University of Washington), and Cecilia Lee, MD (University of Washington) for sharing their time and expertise.
- To evaluate the performance of a deep learning (DL) algorithm for retinopathy of prematurity (ROP) screening in Nepal and Mongolia.
- Rapid developments in artificial intelligence (AI) promise improved diagnosis and care for patients, but raise ethical issues.1–5 Over 6 months, in consultation with the American Academy of Ophthalmology Committee on Artificial Intelligence, we analyzed potential ethical concerns, with a focus on applications of AI in ophthalmology that are deployed or will be deployed in the near future.6 We identified 3 pressing issues: (1) transparency, paradigmatically through the explanation or interpretation of AI models; (2) attribution of responsibility issues for particular harms arising from the use or misuse of AI; and (3) scalability of use cases and screening infrastructure.
- Developing robust artificial intelligence (AI) models for medical image analysis requires large quantities of diverse, well-chosen data that can prove challenging to collect because of privacy concerns, disease rarity, or diagnostic label quality. Collecting image-based datasets for retinopathy of prematurity (ROP), a potentially blinding disease, suffers from these challenges. Progressively growing generative adversarial networks (PGANs) may help, because they can synthesize highly realistic images that may increase both the size and diversity of medical datasets.
- To compare the efficacy and efficiency of training neural networks for medical image classification using comparison labels indicating relative disease severity versus diagnostic class labels from a retinopathy of prematurity (ROP) image dataset.
- Generative adversarial networks (GANs) are deep learning (DL) models that can create and modify realistic-appearing synthetic images, or deepfakes, from real images. The purpose of our study was to evaluate the ability of experts to discern synthesized retinal fundus images from real fundus images and to review the current uses and limitations of GANs in ophthalmology.