Link to project webpage: Project Webpage
Our project focuses on detecting the presence of malignant tumors in chest X-rays. In order to aid radiologists around the world, we propose to exploit supervised and unsupervised Machine Learning algorithms for lung cancer detection. We aim to showcase ‘explainable’ models that could perform close to human accuracy levels for cancer-detection.
1. The overall architecture of feature_extraction + grad_cam visualization + data augmentation via VAEs is new and has not been approached on a medical image dataset to the best of our knowledge.
2. If our approach can show improved results, it could mean that we do not necessarily have to collect a large amount of data at all times and would be able to manage with smaller datasets.
Note: This repo has been moved (partially) from our internal private repository to serve as documentation. For more info, please reach out over email.