Worldwide, around 285 million people are visually impaired and around 45 million are blind. 90% of the world’s blind live in the developing world, and 80% of those cases of blindness are preventable.
The RetinaSense system was created to reduce the rate of preventable eye diseases causing vision loss in the developing world. Our aim is to enable remote camera operators to provide a full retinal analysis service from the ground with no need to set-up new infrastructure.
In the RetinaSense project, we are deploying a number of Snap Out’s strongest skills – from computer vision to crowdsourcing – to tackle the very real and pressing problem of global eye disease and blindness.
RetinaSense enables remote camera operators to provide a full retinal analysis service from the ground with no need to set up any new infrastructure. When using RetinaSense, camera operators are connected virtually with ophthalmologists who can provide easy, fast, low-cost and accurate image-based diagnoses. Operators anywhere in the world can upload images captured with traditional cameras or smartphones to a cloud-based service which covers image upload, analysis and reporting in an all-in-one cloud-based solution.
Fundus images are captured by ophthalmic camera operators with conventional or smartphone-connected device.
The fundus image is uploaded to RetinaSense in a manual or automated approach.
RetinaSense manages the user unique identifiers, fundus images, and healthcare professionals workload.
Registered image reader specialists are notified of new images in a job queue that requires evaluation. Images are analyzed in RetinaSense secure portal using MediNote toolset to manipulate and evaluate images.
RetinaSense returns a report directly to the end user in SMS, email or other system integration including annotated retinal images and diagnosis.
Remote smartphone camera
Streamlining the management, analysis and reporting of retinal images
Optional integration with computer vision algorithms for triaging and annotation guidance
User-friendly image annotation and notes, automatic image quality evaluation
We designed and developed a user interface for a system that monitors financial trading communications.
We built a system that opens up the diagnosis of eye disease to crowdsourcing, allowing users to learn while annotating pictures of retinal scans.