A CT Dataset with RECIST Measurements and Comprehensive Segmentation Masks for Tumors and Lymph Nodes

The RECIST 1.1 protocol is the gold standard for evaluating tumor response in oncological clinical trials and routine care. It requires identifying all lesions in CT scans and categorizing and measuring target lesions by size and location. While artificial intelligence (AI) holds great promise for automating these tasks, progress is hindered by the lack of public datasets with comprehensive lesion annotations and RECIST-compliant measurements. To address this gap, we present a dataset of 1,236 manually segmented lesions from 58 CT scans of 22 cancer patients treated at the Clinical Hospital of the University of Chile (HCUCH). All cases were evaluated under RECIST 1.1, with diameter measurements reported for 82 target lesions. This resource supports diverse applications, including validating automated RECIST tools, applying radiomics to study metastatic heterogeneity, comparing 2D and 3D lesion metrics, benchmarking segmentation algorithms, and advancing foundation models in medical imaging. By including data from a Latin American institution, this dataset also promotes global representation in the development of generalizable medical AI tools.