Our paper in Cancer Research describes HistomicsML, an interactive system for interactive training machine learning models on large whole-slide imaging datasets. This is a centrally-hosted web-accessible system that is designed to help clinical and basic science investigators extract quantitative measurements from their whole-slide imaging datasets without expertise in image analysis. This system uses learn-by-example training of machine learning classifiers and active learning criteria to help users identify the most informative training examples for labeling, and can be used to develop classifiers for prospective application or as a rapid annotation tool that is adaptable to different cancer types. See our documentation to learn more about HistomicsML and our Docker deployment tools.