PanTS: The Pancreatic Tumor Segmentation Dataset
This provides a new benchmark for AI models in pancreatic CT analysis, addressing a domain-specific need for medical imaging researchers.
The authors tackled the problem of limited data for pancreatic CT analysis by creating PanTS, a large-scale dataset with 36,390 CT scans and over 993,000 expert-validated annotations, which led to significantly better performance in tumor detection, localization, and segmentation compared to existing datasets.
PanTS is a large-scale, multi-institutional dataset curated to advance research in pancreatic CT analysis. It contains 36,390 CT scans from 145 medical centers, with expert-validated, voxel-wise annotations of over 993,000 anatomical structures, covering pancreatic tumors, pancreas head, body, and tail, and 24 surrounding anatomical structures such as vascular/skeletal structures and abdominal/thoracic organs. Each scan includes metadata such as patient age, sex, diagnosis, contrast phase, in-plane spacing, slice thickness, etc. AI models trained on PanTS achieve significantly better performance in pancreatic tumor detection, localization, and segmentation compared to those trained on existing public datasets. Our analysis indicates that these gains are directly attributable to the 16x larger-scale tumor annotations and indirectly supported by the 24 additional surrounding anatomical structures. As the largest and most comprehensive resource of its kind, PanTS offers a new benchmark for developing and evaluating AI models in pancreatic CT analysis.