The Artefact dataset contains 22 Whole-Slide Images, with H&E or IHC staining, showing various types and levels of defect to the slides. Of the 22 slides, 20 came from the same tissue block (Block A). One came from another block (Block B) with the same IHC marker evidenced on a different tissue type, and one from a third block (Block C) with another marker and tissue type, as detailed in the table below:
| Block | Stain | Tissue type |
|---|---|---|
| Block A (20 slides) | 10 H&E + 10 IHC (anti-pan-cytokeratin) | Colorectal cancer |
| Block B (1 slide) | IHC (anti-pan-cytokeratin) | Gastroesophageal junction lesion |
| Block C (1 slide) | IHC (anti-NR2F2) | Mouth cancer |
The dataset is available on Zenodo: doi.org/10.5281/zenodo.3773097.
The dataset is released under the Creative Commons BY-NC 4.0 license (attribution, non-commercial use only).