This collection contains the WORC Database: imaging data, segmentations, and ground truth labels (e.g. diagnosis, phenotype, genetics) of 930 anonymized patients collected at the Erasmus Medical Center (Rotterdam, the Netherlands) with a variety of tumor types (e.g. liver, soft tissue, lung metastases) as published in the following two papers: 1) Starmans et al. "Reproducible radiomics through automated machine learning validated on twelve clinical applications", submitted, preprint available from https://arxiv.org/abs/2108.08618; and 2) Starmans et al. "The WORC* database: MRI and CT scans, segmentations, and clinical labels for 930 patients from six radiomics studies", submitted, preprint available from https://doi.org/10.1101/2021.08.19.21262238. By downloading the data, you agree to the following Data Usage Policy: The dataset is freely available under the following license: https://xnat.bmia.nl/data/projects/worc/resources/License/files/WORC_data_license.pdf. This license dictates among others that: 1) others can remix, adapt and build upon this work only non-commercially; 2) the data may not be redistributed. 3) when using (part of) this dataset, please cite the two above mentioned papers. See the license for all conditions. Code to download the data and reproduce the radiomics experiments as detailed in the above papers can be found at https://github.com/MStarmans91/WORCDatabase. Feature and cross-validation split files can be found in both the Github and here, see https://xnat.health-ri.nl/data/projects/worc/resources.