PatchChestCT: A patch-level spatial annotation dataset for nine abnormalities in chest CT

PatchChestCT provides 3D patch-level binary annotations for nine clinically significant abnormalities across 2,201 physician-reviewed chest CT volumes derived from the CT-RATE dataset (Hamamci et al., Nature Biomedical Engineering, 2026). Each annotation is stored as a binary NumPy array (.npz) with shape (24, 12, 12), corresponding to the 3D patch grid of the preprocessed CT volume. Annotated abnormalities: Arterial wall calcification · Coronary artery calcification · Pericardial effusion · Hiatal hernia · Lymphadenopathy · Atelectasis · Lung opacity · Consolidation · Bronchiectasis IMPORTANT — This deposit contains ONLY annotation files (.npz). No CT images, radiology reports, or original CT-RATE metadata are included. To use these annotations, you must independently obtain the source CT volumes fromthe official CT-RATE repository and agree to its Data Usage Agreement: https://huggingface.co/datasets/ibrahimhamamci/CT-RATE Each subdirectory is named using the original CT-RATE volume identifier (e.g., train_1003_a_1/), enabling unambiguous alignment with the source data. For alignment code and full usage instructions, see the companion code repository: https://github.com/SadVoxel/PatchChestCT