Test Dataset from Weng Z. et al. Nat Communications 2024

This dataset was generated under three different magnifications

1. MPP10.tar. MPP = 1.0 µm/px
2. MPP15.tar. MPP = 1.5 µm/px
3. MPP20.tar. MPP = 2.0 µm/px

Each of them contains 4 subfolder: Breast, Colon, Kidney and Prostate, which means that the tiles are extracted from the Whole Slide Image (WSI) of the specific organ:

1. 78 WSIs from Breast
2. 80 WSIs from Colon
3. 80 WSIs from Kidney
4. 80 WSIs from Prostate

Each of the subfolder contains the images and masks from different case. The manual annotations were generated by experts, including 8 classes:

1. Tissue
2. Fold
3. Dark Spot and Foreign Object
4. Pen Marker
5. Edge and Air Bubble
6. Out of Focus
7. Background

and 0 means "Non-annotated pixels (Ignore)".

This dataset is for non-commercial, academic research only.

If you use this dataset, you must cite original publication:

Weng, Z., Seper, A., Pryalukhin, A. et al. GrandQC: A comprehensive solution to quality control problem in digital pathology. Nat Commun 15, 10685 (2024). https://doi.org/10.1038/s41467-024-54769-y