The Glaucoma Eye Diseases Prediction project utilizes the InspectionV2 architecture to develop a deep learning model capable of predicting the presence of glaucoma in eye images. Glaucoma is a serious eye condition that can lead to vision loss and blindness if not detected and treated early. This project aims to leverage the power of deep learning algorithms to assist in the early detection and diagnosis of glaucoma, enabling timely intervention and better patient outcomes.
Dataset that relies in this project is from kaggle where there are three different datasets and used all together. This datasets are opensource. The Paper of the dataset are:
ORIGA: https://pubmed.ncbi.nlm.nih.gov/21095735/
REFUGE: https://ieee-dataport.org/documents/refuge-retinal-fundus-glaucoma-challenge
G1020: https://arxiv.org/abs/2006.09158
Total of 745 images where 486 images are Glaucoma negative image and 259 Glaucoma positive images.
drive link : https://drive.google.com/drive/folders/1n2Kd9SQgWaqD5XWjlmbfu-PL_y6b0Xoc?usp=drive_link
- Clone the repository : git clone https://github.com/RajKumarBiswokarma/GlaucomaEyeDiseases-Detection.git
- Navigate to the project directory: cd GlaucomaEyeDiseases
- Install the requirements : pip install -r requirements.txt
- Run the interference code: gradio gradio_interface.py