Histopathological characterization of colorectal polyps allows to tailor patients' management and follow up with the ultimate aim of avoiding or promptly detecting an invasive carcinoma. Colorectal polyps characterization relies on the histological analysis of tissue samples to determine the polyps malignancy and dysplasia grade. Deep neural networks achieve outstanding accuracy in medical patterns recognition, however they require large sets of annotated training images. We introduce UniToPatho, an annotated dataset of 9536 hematoxylin and eosin (H&E) stained patches extracted from 292 whole-slide images, meant for training deep neural networks for colorectal polyps classification and adenomas grading. We present our dataset and provide insights on how to tackle the problem of automatic colorectal polyps characterization.
@article{arxiv.2101.09991,
title = {UniToPatho, a labeled histopathological dataset for colorectal polyps classification and adenoma dysplasia grading},
author = {Carlo Alberto Barbano and Daniele Perlo and Enzo Tartaglione and Attilio Fiandrotti and Luca Bertero and Paola Cassoni and Marco Grangetto},
journal= {arXiv preprint arXiv:2101.09991},
year = {2022}
}