-
preprocessing: RGB -> BGR
-
Upload image
-
Patient Information
-
Upload OCT image
-
Save into online Patient's Information
-
eye_OCT1
-
eye_OCT2
-
eye_OCT3
-
Connected between OCT structure and Deep Learning model
-
Diagnosis & Classification
-
Diagnosis
-
eye_OCT4
SheCodes Vietnam 2020
Description :
Millions of people suffer from diabetic retinopathy, the leading cause of blindness among working aged adults. We hope to detect and prevent this disease among people.
We are going to build a deep learning model to speed up disease detection.We have to work with thousands of images collected in rural areas to help identify diabetic retinopathy automatically.
Data Description :
Large set of retina images taken using fundus photography under a variety of imaging conditions. A clinician has rated each image for the severity of diabetic retinopathy on a scale of 0 to 4:
- 0 - No DR
- 1 - Mild
- 2 - Moderate
- 3 - Severe
- 4 - Proliferative DR
Benefits
Better diagnosis accuracy
Saving patient's time
Results
Accuracy Test: 66%
Public Score: 0.83
Private Score: 0.66
Workflow
Sign-up & Log-in form
Patient Information
Take OCT photo and diagnose
Diagnosis and RD Classification
Save the result into Patient's National Online Case-Record and print out
Next Step
Business Plan
Marketing Research
Log in or sign up for Devpost to join the conversation.