MetricsReloaded
MetricsReloaded copied to clipboard
Evaluation suite - output
Context Following the evaluation process on a set of references / output pairs, an aggregated report should be produced
Describe the solution you'd like 2 separate aggregations should be proposed:
- Raw aggregation - All the calculated metrics for each reference/output pair should be made available
- Population aggregation - Core statistics of the metrics over the population of reference/output pair should be produced including
- central tendency and variation
- indication of range
- indication of cases at 5, 25, 50, 75, 95 percentile of performance for each metric
- The reports should be made available as pandas data frame with the option to save in a specified format (csv, xlsx, html)
Additional context https://github.com/Project-MONAI/MONAI/wiki/Evaluation-metrics-task-force @jenspetersen @danieltudosiu @AReinke
For the first step, I will try to implement a summary report tool based on ignite handler.
Thanks.