Fully Automatic ROP Screening System: NeoScan



 DESCRIPTION (provided by applicant): This Phase II project is motivated by current issues associated with screening for retinopathy of prematurity (ROP). ROP is the leading cause of blindness in infants. In recent years the number of infants at risk for ROP has been increasing. In the United States, the rate of prematurity has risen from 9.4% of all births in 1981 to 12% in 2010, for a total of over 500,000 preterm births. Preterm neonate disease management depends largely on timely screening and intervention. Unfortunately, low reimbursement levels for ROP screening, insufficient equipment for ROP screening in remote locations, and long-term exposure to medical malpractice actions make it difficult to provide appropriate care to neonates at risk. To mitigate these problems, VisionQuest Biomedical LLC and its collaborators, Oakland University (MI) and the Retina Institute of South Texas (RIST), will demonstrate and test NeoScan, a family of software products aimed at improving the management and detection of ROP. NeoScan consists of two products: NeoScan-Assist and NeoScan-Detect. NeoScan-Assist is aimed at increasing the productivity and reducing the variability in interpretation by th neonatal healthcare providers through accurate quantification of vasculature tortuosity and caliber, factors that have been demonstrated to correlate with the presence of advanced stages of ROP. The objectives of NeoScan-Assist are to reduce variability in the diagnosis of advanced stages of ROP and to provide a tool for accurate screening and staging of ROP in neonates. NeoScan-Detect is aimed at automatically identifying infants that need further examination by an ophthalmologist. The objectives of this project will be accomplished through three specific aims. In Aim 1 we will finalize the product development of NeoScan-Assist by productizing the methods developed during Phase I of this project. In Aim 2, a prospective clinical study will be performed to evaluate the effectiveness of NeoScan-Assist and to provide data for validation of NeoScan- Detect. In Aim 3 we will demonstrate the image processing techniques that will be part of NeoScan-Detect. At the end of this Phase II project we will be ready to submit an FDA 510(k) market clearance for NeoScan-Assist, and, in parallel with that submission, we will perform a clinical trial to demonstrate the safety and effectiveness of NeoScan-Detect in preparation for an FDA market clearance submission of that product.