Hi @lorenzocerrone ,

Supercool project! LEveraging ome-zarr is the next-big thing to think about. This is 50% thinking out loud and 50% feature request: Is it possible to build the iterator so that it can also spit out ROIs instead of label images? I mean the spec doesn't currently support ROIs but things like object detection (i.e., maximum detection, YOLO classifiers) are not super uncommon. The output would have to be handled without outside ome-zarr but it would be supercool to be able to do it in the first place.