nascent-bot / cancer_app Goto Github PK

BREAST CANCER DETECTION

Prediction of Breast Cancer using histopathology image
Explore the docs »

View Demo · Report Bug · Request Feature

A Convolutional Neural Network, also known as CNN or ConvNet, is a class of neural networks that specializes in processing data that has a grid-like topology, such as an image. The benefits of deep learning in healthcare are plentiful – fast, efficient, accurate – but they don’t stop there. Even more benefits lie within the neural networks formed by multiple layers of AI and ML and their ability to learn. With the help of these great technologies, I have created a model that could predict whether a person is malignant with Breast Cancer or not.

Breast cancer is an uncontrolled growth of breast cells.

Why Breast Cancer is dangerous:

• 1 in 8 women who live to be age 70 will develop breast cancer in her lifetime.
• Breast cancer is the second most common cancer in women in Ireland.
• In 2020, there were 2.3 million women diagnosed with breast cancer and 685 000 deaths globally WHO
• In 2022, it is estimated that 43,250 women and 530 men will die of breast cancer. ACS

But there is good news:

• Breast Cancer's mortality rate has been declining since 1989
• Women whose breast cancer is detected at an early stage have a 93 percent or higher survival rate

Based on the experimental results, the proposed model achieved 90% accuracy

(back to top)

Here is the list of frameworks and libraries used to create this project.

System Information OS-Windows11, Processor-AMD Ryzen 5 5500U, Graphics-Radeon Graphics, Physical Memory (RAM) 8.00 GB

(back to top)

To get a local copy up and running follow these simple steps.

Clone the Repo.

git clone https://github.com/ACM40960/project-RaghulRavikumar.git

Below is the list of applications that are needed to be installed to view and execute this project locally.

Frameworks

1. Anaconda (Steps to Install) ⚠️select python version above 3.5
2. Atom (Steps to Install)

Launch the terminal by following the below steps

1. Execute Anaconda Navigator
2. Click on Environments
3. Create an Environment
4. Select created environment -> Open Terminal

Now you are good to install the required packages using console. Use the below commands to install them in your environment.

To Execute the Model

conda install numpy

conda install pandas

conda install matplotlib

conda install seaborn

conda install scikit-learn

pip install pytest-shutil

pip3 install opencv-python

conda install tensorflow

To Render with UI

pip install streamlit

pip install pybase64

pip install datetime

pip install Pillow

(back to top)

To Train The Model

1. Open Anaconda Navigator
2. Launch Jupyter Notebook Note: Please Install if require
3. Upload "Second version.ipynb"
4. Press Shift+Enter to run cells one by one More information about the model are given in the file

To View as Web Application

1. Launch Anaconda terminal as mentioned here
2. Navigate to the location were the project is cloned using cd command
3. Make sure information.py file is located and file structure is maintained
4. Now use below command to host the application locally

  streamlit run information.py

Once the webpage is launched click on the Predict tab

• Step 1: Fill the User Information (Not Mandatory)
• Step 2: Upload The Image
  • Step 2.1: Browse File to upload the histopathology image
  • Step 2.2: You can also use sample image if you don't have any by selecting Use Sample Image
• Step 3: Click "Run On This Image"
• Step 4: Please Wait

You can see the result for the uploaded image

For detailed steps with screenshot, please refer to the How-To-Use

(back to top)

• Improve Accuracy of the Model (Current Accuracy at 92%)
• Include Login Functionality
• Introduce Database to store user information
• Fix Issues if any
• Mobile Application Development
  • Android
  • iOS

(back to top)

If you have a suggestion that would make this project better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

This Application is currently not licensed and is free to use by everyone.

(back to top)

Your Name - Sukesh Perla - [email protected]

Project Link: Breast Cancer Detection

(back to top)

Use this space to list resources you find helpful and would like to give credit to. I've included a few of my favorites to kick things off!

• Machine Learning
• Breast Cancer Detection from thermogram
• Breast Cancer using CNN
• Breast Cancer Centres
• Img Shields
• GitHub Pages
• Font Awesome
• Streamlit Documentation

(back to top)