Project Julie is a research project aimed at increasing cancer diagnosis accuracy using computer vision and machine learning techniques, specifically for thyroid cancer detection. Our solution leverages Kubernetes for scalability and ease of deployment.
We have developed a machine learning model that analyzes CT scans for possible thyroid cancer. The model compares input scans to a large dataset of images and produces a probability rating percentage of the high probability of it being cancerous. The project follows the below steps:
- Data collection
- Data preprocessing
- Labeling
- Model selection
- Model training
- Model evaluation
- Deployment
- Continuous improvement
- Python 3.7 or higher
- TensorFlow 2.x
- Keras
- OpenCV
- NumPy
- Scikit-learn
- Docker (for Kubernetes deployment)
- Kubernetes manifest