TumourVision G2 (TVG-2), an advancement over TVG-1, incorporates PolyTrend methodologies to improve brain tumor detection in MRI scans. Utilizing a Convolutional Neural Network (CNN) architecture developed with PyTorch, TVG-2 classifies brain MRI scans for tumor detection. It employs Torch, TorchVision, and Matplotlib libraries for analysis and visualization. With around 22 million parameters, TVG-2 provides a robust computational framework. While TVG-1 achieves 56.45% accuracy, TVG-2 is in active development, enhancing diagnostic capabilities for medical professionals.
CLOD_formulas.webp
in full is Convolutional Layers' Output Dimensions. Just as an abbreviation for easy file naming
- Integration of PolyTrend's polynomial trend analysis for data preprocessing and feature extraction.
- Utilization of polynomial regression techniques to refine CNN predictions and improve classification accuracy.
- Seamless integration with existing TVG-1 architecture for easy adoption and deployment.
The dataset used for training and testing TVG-1 was sourced from two Kaggle datasets:
You can install "TumorVision" via pip by running:
pip install tumorvision
Alternatively, if you prefer to install it from the source code, you can follow these steps:
- Clone the TVG-2 repository:
git clone https://github.com/Josh-The-Developapa/TumorVision.git
- Navigate to the project directory:
cd TumorVision
- Set up a Python virtual environment (recommended):
python -m venv venv
source venv/bin/activate # On Unix or MacOS
venv\Scripts\activate # On Windows
- Install the required dependencies:
pip install -r requirements.txt
- Follow additional setup instructions provided in the README files of TVG-1 and PolyTrend projects for any specific configurations or requirements.
This project is licensed under the MIT License - see the LICENSE file for details.
- Joshua Mukisa - Developer of TVG-1
- Emmanuel Asiimwe - Developer of PolyTrend