Dataset Information

Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset.

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.

SUBMITTER: Wilm F

PROVIDER: S-EPMC9515104 | biostudies-literature | 2022 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset.

Wilm Frauke F Fragoso Marco M Marzahl Christian C Qiu Jingna J Puget Chloé C Diehl Laura L Bertram Christof A CA Klopfleisch Robert R Maier Andreas A Breininger Katharina K Aubreville Marc M

Scientific data 20220927 1

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 po ...[more]

PMID: 36167846

Similar Datasets

Project description:The tumor microenvironment is a complex system, where neoplastic cells interact with immune and stromal cells. Tumor-associated macrophages (TAMs) are considered among the most numerically and biologically noteworthy cellular components in tumors and the attention on this cellular population has been growing during the last decade, both for its prognostic role and as a potential future therapeutic target. Melanoma, particularly the oral form, despite being one of the most immunogenic tumors, bears a poor prognosis in dogs and humans, due to its highly aggressive biological behavior and limited therapeutic options. The aims of this study are to characterize and quantify TAMs (using CD163, CD204, Iba1, and MAC387) in canine melanocytic tumors and to evaluate the association of these markers with diagnosis, histologic prognostic features, presence of metastases, and outcome, and to provide preliminary data for possible future therapies targeting TAMs. Seventy-two melanocytic tumors (27 oral melanomas, 25 cutaneous melanomas, 14 cutaneous melanocytomas, and 6 oral melanocytomas) were retrospectively selected and submitted to immunohistochemistry and double immunofluorescence. Double immunolabeling revealed that most CD163+ and CD204+cells co-expressed Iba1, which labeled also dendritic cells. Iba1 was instead rarely co-expressed with MAC387. Nevertheless, the expression of macrophagic markers showed a mild to moderate association among the four markers, except for CD204 and MAC387. The number of CD163+, CD204+, and MAC387+ cells was significantly higher in oral melanomas compared to oral melanocytomas (p < 0.001; p < 0.05 and p < 0.01, respectively), whereas Iba1 was differentially expressed in cutaneous melanomas and melanocytomas (p < 0.05). Moreover, CD163, IBA1 and MAC387 expression was associated with nuclear atypia and mitotic count. The number of CD163+cells was associated with the presence of metastases and tumor-related death in oral melanocytic tumors (p < 0.05 and p = 0.001, respectively).

Dataset Information

Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset.

Publications

Pan-tumor CAnine cuTaneous Cancer Histology (CATCH) dataset.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets