Metrics Reloaded

The mission of Metrics Reloaded toolkit is to guide researchers in the selection of appropriate performance metrics for biomedical image analysis problems and to provide a comprehensive online resource for metric-related information and pitfalls.

The Metrics Reloaded framework aims to provide users with the ability to make informed decisions about which metrics to use for a given biomedical problem. The framework currently supports image-level classification, semantic segmentation, object detection and instance segmentation problems. To improve the user experience, all the work and knowledge of the Metrics Reloaded Framework is implemented as an online toolkit. Following the convergence of machine learning methodology across application domains, Metrics Reloaded fosters the convergence of validation methodology. Its applicability is demonstrated for various biomedical use cases.

The Metrics Reloaded toolkit is available at https://metrics-reloaded.dkfz.de