DIAGNijmegen / pathology-whole-slide-data

A package for working with whole-slide data including a fast batch iterator that can be used to train deep learning models.
https://diagnijmegen.github.io/pathology-whole-slide-data/
Apache License 2.0
93 stars 27 forks source link

QuPath annotations (.geojson) format not readable by parser #41

Closed tsikup closed 1 year ago

tsikup commented 1 year ago

The '.geojson' annotation files that QuPath exports are not readable by the annotation parser. This is due to the different structure of '.geojson' and the implemented parser of '.json' files. I will be submitting a fix soon.

martvanrijthoven commented 1 year ago

Dear Nikos Tsiknakis

Thank you for this issue. Indeed the current qupath annotation parser in v0.16.0 might follow a different structure (it was based on a custom export script that i made a while ago). If you can implement a correct parser that would be great! If it is possible please implement it for wholeslidedata==v0.1.0 version (which is now on the main branch but not on pypi yet). I actually noticed that in the main branch the qupath parser is empty: https://github.com/DIAGNijmegen/pathology-whole-slide-data/blob/main/wholeslidedata/interoperability/qupath/parser.py

It would be amazing if you could create a PR for a correct parser for qupath export!

Best wishes, Mart