The University of Turin (UniTO) released the open-access dataset UniTOPatho collected for the homonymous Use Case 2 in the DeepHealth project.

UniTOPatho is a dataset of annotated high-resolution hematoxylin and eosin stained images, comprising different histological samples of colorectal polyps, collected from patients undergoing cancer screening. The dataset is a collection of the most relevant patch images extracted from 292 whole-slide images. The DeepHealth UNITO team makes publicly available a total of 9536 patches classified according to the following labels:

NORM – Normal tissue,
HP – Hyperplastic Polyp,
TA.HG – Tubular Adenoma, High-Grade dysplasia,
TA.LG – Tubular Adenoma, Low-Grade dysplasia,
TVA.HG – Tubulo-Villous Adenoma, High-Grade dysplasia,

TVA.LG – Tubulo-Villous Adenoma, Low-Grade dysplasia.

The dataset is available at


(Featured photo by Irwan on Unsplash)