Artificial Intelligence Assisted Panoramic Optical Coherence Tomography Angiography for Retinopathy of Prematurity

Oregon Health & Science University, Portland OR

Investigators

Linked publications & trials

Abstract

PROJECT SUMMARY The long-term goal of this project is to determine whether optical coherence tomography (OCT) and OCT angiography (OCTA) might lead more accurate and objective diagnosis, earlier intervention, and improved outcomes in retinopathy of prematurity (ROP). It is well established that due to the subjectivity of the ophthalmoscopic examination, and systematic bias between examiners, there is significant variation in treatment of the most severe forms of ROP in the real world. This leads to both under-treatment (and poor outcomes due to retinal detachment) and over-treatment (exposing neonates to the ocular and systemic risks of treatment). Roughly 20,000 babies per year develop retinal detachments (RD) due to ROP and there is strong evidence that most of these are preventable. In adult retinal vascular diseases, most notably diabetic retinopathy, OCT and OCTA can detect and quantify disease features such as diabetic macular edema and retinal neovascularization before they are noted clinically, enabling earlier treatment and reducing the risk of blindness from RD. However, evaluating the use of this technology in neonates requires comprehensive examination of the retina, and the commercially available handheld OCTs are too slow for ultra-widefield (UWF) OCT and OCTA imaging. In the last grant period, we have successfully developed several faster and wider FOV handheld OCT prototypes with advances in both hardware and software, performed more than 2,300 individual eye examinations using UWF- OCT, and demonstrated for the first time that the stage of ROP can be measured in axial thickness. In this competitive renewal, we will (1) improve our existing handheld OCT to make it simpler to operate, less dependent on pupillary dilation, and reduce concerns about infection, (2) extend prior work to develop automated deep learning biomarkers for zone, stage, and plus disease and (3) evaluate whether OCT-derived biomarkers may facilitate automated and objective measurement of disease progression, regression, and risk. The specific aims of this proposal are: (1) Develop non-mydriatic quantitative UWF-OCT/OCTA through innovations in hardware and software. (2) Develop and validate automated UWF-OCT/OCTA derived biomarkers for ROP diagnosis. (3) Evaluate the clinical significance of UWF-OCT/OCTA derived biomarkers.