Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset
This dataset addresses the need for annotated data in veterinary and human pathology for tumor classification, but it is incremental as it primarily provides a new resource rather than a novel method.
The authors tackled the challenge of differentiating histologic sections of cutaneous tumors by creating a publicly available dataset of 350 whole slide images with 12,424 polygon annotations for 13 histologic classes, including seven canine cutaneous tumor subtypes, and validated it with a deep neural network achieving a class-averaged Jaccard coefficient of 0.7047 and slide-level accuracy of 0.9857.
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.