To develop an Artificial Intelligence-based etiology classification algorithm. This tool uses machine learning and deep learning algorithms to analyze high-resolution whole-slide digital pathology images of blood clots and classify the etiology to either CE (Cardioembolic - i.e. originating from the heart) or LAA (Large Artery Atherosclerosis- i.e., originating from the plaque in the inner lining of an artery).
To run this project, you will need the following dependencies:
- Python 3.6 or higher
- PyTorch 1.7 or higher
- Tensorflow 2.0 or higher
- NumPy
- Matplotlib
The dataset into consideration has been identified from Kaggle, published by the Mayo Clinic under the competition name –“Mayo Clinic –Strip AI: Image classification of Stroke Blood Clot Origin.” The dataset contains 1,158 files(images) with over 390Gb of high-resolution whole-slide digital pathology images. Each slide depicts a blood clot from a patient that had experienced an acute ischemic stroke.