Cataract disease is the world's leading cause of blindness with a majority of the world's population affected by it; however, it is easily treatable with surgery.
In Mexico, of the 16 million people who suffer from some form of vision loss, 63% of the population (~10 million people) are blind due to cataract disease.
There are four obstacles to receiving cataract surgery:
-
Lack of awareness
-
Bad service
-
Cost
-
Distance for treatment
63% of the Mexican population has a smartphone, so a smartphone application would be the best mode to reach our audience.
Our data pipeline uses various services provided through Amazon Web Services. The user of our cataract detection service uploads an image to the mobile application which then sends the image to Amazon S3 which is a data storage service. After the image is uploaded, a prediction is automatically made on the image using AWS Lambda. AWS Lambda accesses Tensorflow model weights which are stored in another S3 bucket and builds a model using ResNet-50 which makes a prediction on the image. After the prediction is made, the prediction is stored in DynamoDB which is a NoSQL database. Lastly, after these processes occur the mobile application sends a HTTP request to AWS API Gateway which subsequently accesses the most recent entry into the DynamoDB database and sends the result back to the user.
