Annotation in the field of Ophthalmology
Overview
Due to the shortage of ophthalmologists in low & middle-income countries, less number of people are being tested for diabetic retinopathy despite of a rise in cases
Due to the shortage of ophthalmologists in low & middle-income countries, less number of people are being tested for diabetic retinopathy despite of a rise in cases
The Problem
Requirements to annotate human eye fundus images to aid detection of ailments like Diabetic Retinopathy
Solution
Sourcing of high quality retina images and accurately annotate training data for the AI model to detect eye ailments, therby increasing accessibility of detecting DR without heavy equipments and testing
Process
STEP 1
Research on the use of AI in ophthalmology and scope of annotation activities
STEP 2
Identifying Diabetic Retinography types with expert pathologists
STEP 3
Sourcing & annotating human retina fundus images
STEP 1
Research on the use of AI in ophthalmology and scope of annotation activities
STEP 2
Identifying Diabetic Retinography types with expert pathologists
STEP 3
Sourcing & annotating human retina fundus images
Achievement
Improved access to eye examinations in underserved areas by enabling the AI model provision at medical centres that could not otherwise offer eye care
Identifying Diabetic Retinography types with expert pathologists
Sourcing & annotating human retina fundus images
Insights
Data training via annotation & labeling enables human like intelligence by the machine in the analysis, interpretation, and comprehension of complicated medical and healthcare data thereby aiding practices such as diagnosis, screening processes, treatment protocol development, drug development, personalized medicine, and patient monitoring and care.