ReXGroundingCT

ReXGroundingCT ReXGroundingCT is a dataset designed to link free-text radiology findings with pixel-level segmentations in 3D chest CT scans. Each sample consists of a volumetric CT scan, associated segmentation masks for one or more findings, and detailed textual descriptions.The dataset has segmentations for 8,028 findings across 14 different categories in 3,142 CT scans. There are 2,992 scans allocated for training, 50 for public validation, and 100 held privately to be… See the full description on the dataset page: huggingface.co/datasets/surajpaib/ReXGroundingCT.