https://github.com/tejacherukuri/rhd

Retinal Health Diagnostics is an Intelligent Computer Aided Diagnostic Application for diagnosing retinal diseases
https://github.com/tejacherukuri/rhd

aws computer-vision deep-learning flask machine-learning python tensorflow

Last synced: 3 months ago
JSON representation

Retinal Health Diagnostics is an Intelligent Computer Aided Diagnostic Application for diagnosing retinal diseases

• Host: GitHub
• URL: https://github.com/tejacherukuri/rhd
• Owner: TejaCherukuri
• Created: 2024-06-15T23:20:49.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-06-21T19:24:07.000Z (about 2 years ago)
• Last Synced: 2025-02-06T06:41:37.295Z (over 1 year ago)
• Topics: aws, computer-vision, deep-learning, flask, machine-learning, python, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 17.9 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
 Retinal Health Diagnostics - The Intelligent Application

Healthy Eyes & Healthy Life with Retinal Health Diagnostics, It's all in the Eyes!!


Retinal Health Diagnostics is an Intelligent Computer Aided Diagnostic Application built using a Novel Deep Learning based model called 'Hinge Attention Network' for retinal diseases diagnosis using color fundus retinal scan imaging & digital eye imaging techniques. This model was developed and tested on standard benchmark datasets. Results of this work revelaled the superiority of this approach by achieving state-of-the-art performance over several existing techniques.

This application diagnoses 3 different types of retinal diseases including

Cataracts

Diabetic Macular Edema

Diabetic Retinopathy


Dataset Information

Cataracts

Cataract-Eyes (Digital Eyes) - https://www.kaggle.com/datasets/himaniac/cataract-eye-dataset

ODIR-5k (Color Fundus Images) - https://www.kaggle.com/datasets/andrewmvd/ocular-disease-recognition-odir5k


Diabetic Macular Edema

Messidor2 (Color Fundus Photography) - https://www.kaggle.com/datasets/mariaherrerot/messidor2preprocess/data


Diabetic Retinopathy

APTOS 2019 (Color Fundus Photopgraphy) - https://www.kaggle.com/c/aptos2019-blindness-detection/data





Results

Performance in terms of Accuracy


Cataract-Eyes Dataset: 96.97%

ODIR Dataset: 97.95%
 

Messidor2 Dataset: 94.60%

APTOS 2019 Dataset: 85.64%


Technologies/Libraries Used

HTML

CSS

JavaScript

Python

Flask

Tensorflow

Keras

OpenCV


Setting up the project

Download required dependencies and just launch "Main.py" file. You can see the application running in your local server.