Colorectal Cancer Histology Image Tiles and CycleGAN-based Normalization Model for Tissue Classification
Nicola Altini, Tommaso Maria Marvulli, Simona De Summa, Mariapia Caputo, Stefania Tommasi, Amalia Azzariti, Antonio Brunetti, Berardino Prencipe, Eliseo Mattioli, Francesco Alfredo Zito, Vitoantonio Bevilacqua · Zenodo (CERN European Organization for Nuclear Research) · 2021
Content The present dataset is linked to a research aimed at discovering the best normalization pipeline and classification model for colorectal cancer multi-class tissue classification. The 15,856 histological image tiles are completely anomized and are extracted from 10 formalin-fized paraffine-embedded samples of patients affected by colorectal cancer. The materials are split in two folders: “CRC_Tiles_IRCCS_ISTITUTO_TUMORI_BARI.zip”: a zipped folder containing tiles (n=15,856) annotated by a pathologist, grouped in 6 subdirectories, each of them representing a class. Tiles are of size 224 x 224 px, taken at a resolution of 0.5 μm/px. “tcga2tecno.zip”: CycleGAN-based normalization model for colorectal cancer tissue. It has to be used in conjunction with the following repository available on GitHub: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix. Ethical Statement The study has been funded by “Tecnopolo per la Medicina di Precisione (CUP B84I18000540002)”. The institutional Ethic Committee approved the study (Prot n. 780/CE). Related Datasets and Works For further details concerning the aforementioned dataset, refer to the paper below. Please cite this article if you need this dataset for your research. Altini N. et al. (2021) Multi-class Tissue Classification in Colorectal Cancer with Handcrafted and Deep Features. In: Huang DS., Jo KH., Li J., Gribova V., Bevilacqua V. (eds) Intelligent Computing Theories and Application. ICIC 2021. Lecture Notes in Computer Science, vol 12836. Springer, Cham. https://doi.org/10.1007/978-3-030-84522-3_42 Please also consider the dataset offered in our previous work: Altini N. et al. (2021). Pathologist's Annotated Image Tiles for Multi-Class Tissue Classification in Colorectal Cancer (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.4785131