Toward a Pre-Cancer Image Atlas through Crowdsourcing and Machine Learning
Abstract: We describe how crowdsourcing can be combined with advanced machine learning for early cancer detection. We demonstrate our system for lung cancer (using data from the National Lung cancer Screen Trial), but in such a fashion that it can easily be replicated for other organs. Thus this becomes a step towards the pre-cancer image atlas, a focus area of the National Cancer Institute. Additionally, by keeping explainability and interpretability at the core of our deep learning methods, we make the endeavor reproducible.
Archive Materials
Back to Fourth Computational Approaches for Cancer Workshop (CAFCW18) Archive Listing
Back to Full Workshop Archive Listing