This repository contains implementations for cancer detection using deep learning techniques across various architectures. The project includes lung cancer prediction, brain cancer detection, and segmentation tasks, leveraging advanced models to achieve high accuracy and efficiency.
-
Lung Cancer Prediction: Achieves 99% accuracy on the test dataset using a robust CNN architecture designed for effective feature extraction and classification.
-
Brain Cancer Detection: This component compares MobileNet and linear architectures. The linear architecture was selected due to its faster inference speed and lower model load, making it suitable for real-time applications.
-
Segmentation Model: Implements advanced segmentation techniques for precise localization of cancerous areas in medical images, enhancing diagnostic capabilities.
- Lung Cancer Prediction Accuracy: 99%
- Brain Cancer Detection Accuracy: 93%
- Clone this repository.
- Install required dependencies.
- Prepare your dataset of images for lung and brain cancer.
- Train the respective models for prediction and segmentation tasks.
- Use the trained models to make predictions on new data.
- Trained ML Models can be found here
Contributions are welcome! Please feel free to submit a Pull Request or open an Issue for any suggestions or bug reports.
Feel free to reach out if you have any questions or suggestions!