SBIR Phase II: Feasibility of a Wearable Blindness Prevention System

SBIR第二阶段项目的更广泛的商业影响旨在进一步推动用于青光眼患者的新型可穿戴技术，并为该技术的广泛采用做好准备。青光眼是导致不可逆转失明的主要原因，原因不明，全球有超过7000万人受到青光眼的影响。目前，青光眼还没有治愈的方法，但早期青光眼往往可以挽救视力。眼压是预测和监测青光眼最常用的指标。在这项SBIR项目下开发的可穿戴技术将全天监测眼压，并允许临床医生为高危患者提供更高质量的护理。这项技术使用照片来测量眼睛在高压下的伸展情况。该项目旨在将成像技术应用于时尚的眼镜框，并开发定制软件，将照片转换为眼压测量，向供应商提供信息，并提高与家庭用药相关的依从性。该项目旨在推动一项新技术的发展，在该技术中，可穿戴眼镜框架通过成像与眼前组织-特别是暴露的巩膜-相关的压力诱导的机械应变水平来跟踪眼内压(IOP)。到目前为止，眼压是预测青光眼最常用的指标，青光眼是导致不可逆转失明的主要原因。在这个项目中，一个定制的机器学习算法将识别位于巩膜图像的小区域中的特征模式，并通过跟踪这些区域因压力引起的位移来计算眼压。第二阶段的关键目标是通过人体活体研究，在框架中加入必要的电子设备，准确测量真实世界条件下的眼压。这项技术将进一步开发，以提高算法与图像收集期间捕获的传统IOP的相关性。该奖项反映了NSF的法定使命，并已通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader/commercial impact of this SBIR Phase II project aims to further advance novel wearable technology for glaucoma patients and prepare the technology for broad adoption. Glaucoma, the leading cause of irreversible blindness, has an unknown cause and affects more than 70 million people worldwide. Currently, there is no cure for glaucoma, but early can often save one’s vision. Eye pressure is the most commonly used measure for predicting and monitoring glaucoma. The wearable technology developed under this SBIR project will monitor eye pressure throughout the day and allow clinicians to provide a higher quality of care for at-risk patients. The technology uses photographs to measure how the eye stretches under high pressure. This project aims to adapt the imaging technology into stylish eyeglass frames and develop custom software for converting photographs to eye pressure measurements, informing providers and improving compliance associated with at-home medication. This project aims to advance a novel technology in which wearable eyeglass frames are used to track intraocular pressure (IOP) by imaging the level of pressure-induced mechanical strain associated with the tissue at the front of the eye - specifically, exposed sclera. IOP is, by far, the most commonly used metric for predicting glaucoma, the leading cause of irreversible blindness. In this project, a custom machine learning algorithm will identify characteristic patterns residing in small regions of the scleral images and, by tracking pressure-induced displacement of the regions, calculate IOP. The key objective of Phase II is to accurately measure IOP in real-world conditions with human in-vivo studies, incorporating necessary electronics in the frames. The technology will be further developed in order to improve correlation of the algorithm with conventional IOP captured during the image collection period.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.