Skip to content

NienCongChua/skin-notebook

Repository files navigation

Skin Disease Diagnosis Project

Description

This project is a web application that uses a machine learning model to diagnose skin diseases based on uploaded images. Users can upload images of their skin lesions and receive a prediction of the possible condition.

Features

  • Upload images of skin lesions.
  • Diagnose the condition using a trained machine learning model.
  • Display the predicted diagnosis and detailed information (if available).
  • Allow users to report inaccurate results.

Technologies Used

  • Backend: Python, Flask
  • Machine Learning: TensorFlow, Keras
  • Frontend: HTML, CSS, JavaScript
  • Other: None

Folder Structure

skin-notebook/

├── data3/
│ ├── test/
│ └── train/

├── static/
│ ├── script.js
│ └── style.css

├── templates/
│ └── index.html

├── requirements.txt
├── app.py
├── disease_details.json
├── predict-colab.ipynb
├── predict.ipynb
├── skin_disease_cnn_model_newv2.keras
└── README.md

Installation

Warming: sure that using Python 3.10 to compile this project

  1. Clone the repository: git clone https://github.com/NienCongChua/skin-notebook.git or click download to faster.
  2. Download the directory data from the link: data3 or alternative data3 to train the model. (This HAM10000 dataset is preprocessed by LewPie, you can check his repository)
  3. Create a virtual environment: python3.10 -m venv env
  4. Activate the virtual environment: source env/bin/activate
  5. Install the required libraries: pip install -r requirements.txt
  6. Run the application: python app.py

Usage

  1. Open a web browser and go to http://127.0.0.1:5000/.
  2. Choose an image of the skin lesion you want to diagnose.
  3. Click the "Upload and Predict" button.
  4. View the predicted diagnosis displayed below.
  5. If you have any questions, please click "Report".

Limitations

  • The accuracy of the model depends on the quality and quantity of the training data.
  • This application should not be used for self-diagnosis or treatment.
  • Always consult with a healthcare professional for accurate diagnosis and treatment.

Author

Warming

  • If you have any problem with model skin_disease_cnn_model_newv2.keras, you can download it from my file

About

for identifying skin diseases

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors