This is the fifth T5 Data Science Bootcamp project, which is about deep learning and building classification models that address a useful prediction and/or interpretation problem using Python with Sklearn. Below are details about an eye disease classification for a hospital in Saudi Arabia that we are collaborating with to help them solve their problem and describe the dataset and tools we will be using for the project.
In this project, based on the diagnosis of the left and right eye diseases which they were classified into 3 classes. When you enter a picture of a patient's eye, a prediction will be made to know what the diagnosis is for the patient.
The dataset is Eyes Disease from Kaggle Website, it contains 6392 rows and 19 columns. For a better understanding of the database there is the description of a column below:
| Variable | Definition |
|---|---|
| ID | Unique ID. |
| Patient Age | the Age of Patient |
| Patient Sex | the Sex of Patient |
| Left-Fundus | The patient's left eye |
| Right-Fundus | IThe patient's right eye |
| Left-Diagnostic Keywords | Keywords diagnosis of the left eye |
| Right-Diagnostic Keywords | Keywords diagnosis of the right eye |
| N | Normal |
| D | Diabetes |
| G | Glaucoma |
| C | Cataract |
| A | Age related Macular Degeneration |
| H | Hypertension |
| M | Pathological Myopia |
| O | Other diseases/abnormalities |
| filepath | file path of the picture |
| labels | disease classification |
| target | the target disease classification |
| filename | name of the picture |
These are the technologies and libraries that we will be using for this project:
- Technologies: Python, Jupyter Notebook.
- Libraries: NumPy, Pandas, Matplotlib, Seaborn, plotly, keras and tensorflow.
Please feel free to let me know if you have any questions. Email: [email protected] and [email protected]