Breast Cancer Classification System

Introduction

This project is a breast cancer classification system, utilizing advanced technologies to accurately classify breast cancer types. The system integrates a front-end developed in HTML, CSS, and JavaScript with a Flask-based backend. The core of the classification relies on a Convolutional Neural Network (CNN) architecture, specifically VGG-16, for model training. Data management is handled through an SQL database.

Table of Contents

1. Introduction
2. Installation
3. Usage
4. Technologies Used
5. Dependencies
6. Configuration
7. Database Setup
8. Contributing
9. License

Installation

To run this system, several technologies and dependencies need to be installed:

1. HTML, CSS, and JavaScript for the frontend.
2. Flask for frontend-backend integration.
3. VGG-16 for the CNN model.
4. SQL for database management.
5. Python and necessary libraries.
6. XAMPP for database management.
7. Visual Studio Code (or any preferred IDE) for coding.

Setting Up a Virtual Environment

• Install Python on your system.
• Create a virtual environment.
• Activate the virtual environment.

Installing Dependencies

• Inside the virtual environment, install all required Python libraries.
• Ensure Python and Flask are installed on your system.
• Clone the repository or download the source code. -Install required dependencies listed in requirements.txt.
• Set up a MySQL database and configure the connection in the application.

Technologies Used

• Frontend: HTML, CSS, JavaScript
• Backend: Flask
• Machine Learning Model: VGG-16 (CNN Architecture)
• Database: SQL

#Usage Run the Flask app to start the server. Access the application through a web browser to register users, manage patient data, classify medical images, and generate reports.

Features

• User and patient management.
• Medical image classification using TensorFlow and Keras.
• Email functionalities for notifications.
• Dynamic PDF generation for reports and diagnostics.
• Comprehensive forms for data entry and validation.

Dependencies

• Flask
• TensorFlow and Keras
• Flask-Mail
• MySQL
• pdfkit and wkhtmltopdf
• Additional Python libraries.

Configuration

Configure the MySQL database settings, email server details, and file upload paths as per your environment.

Documentation

The source code contains comments for easier understanding of the functionalities. Ensure to read the Flask and TensorFlow documentation for detailed understanding.

Examples

• Registering a new user or patient.
• Classifying a medical image to detect specific conditions.
• Generating PDF reports for patient history and diagnostics.

Troubleshooting

• Ensure all Python dependencies are installed.
• Verify the database and email configurations.
• Check for errors in the Flask server logs.

Contributors

• Kamal Hussain (Developer)