Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset

TL;DR

This paper introduces a comprehensive dataset of canine skin tumor images with detailed annotations, enabling improved deep learning models for tumor classification and segmentation, which can also benefit human cancer research.

Contribution

The creation of a large, annotated dataset of canine cutaneous tumors with validated labels and baseline deep learning benchmarks for segmentation and classification.

Findings

High consistency in tumor annotations across raters

Deep neural network achieved 0.7047 class-averaged Jaccard coefficient

Slide-level accuracy of 0.9857 in tumor classification

Abstract

Due to morphological similarities, the differentiation of histologic sections of cutaneous tumors into individual subtypes can be challenging. Recently, deep learning-based approaches have proven their potential for supporting pathologists in this regard. However, many of these supervised algorithms require a large amount of annotated data for robust development. We present a publicly available dataset of 350 whole slide images of seven different canine cutaneous tumors complemented by 12,424 polygon annotations for 13 histologic classes, including seven cutaneous tumor subtypes. In inter-rater experiments, we show a high consistency of the provided labels, especially for tumor annotations. We further validate the dataset by training a deep neural network for the task of tissue segmentation and tumor subtype classification. We achieve a class-averaged Jaccard coefficient of 0.7047, and 0.9044 for tumor in particular. For classification, we achieve a slide-level accuracy of 0.9857. Since canine cutaneous tumors possess various histologic homologies to human tumors the added value of this dataset is not limited to veterinary pathology but extends to more general fields of application.