PatchChestCT: A patch-level spatial annotation dataset for nine abnormalities in chest CT.
Authors
Affiliations (9)
Affiliations (9)
- School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China (USTC), Hefei, Anhui, 230026, China.
- Center for Medical Imaging, Robotics, Analytic Computing & Learning (MIRACLE), Suzhou Institute for Advance Research, USTC, Suzhou, Jiangsu, 215123, China.
- Department of Radiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230001, China.
- Department of Radiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, 230001, China. [email protected].
- School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China (USTC), Hefei, Anhui, 230026, China. [email protected].
- Center for Medical Imaging, Robotics, Analytic Computing & Learning (MIRACLE), Suzhou Institute for Advance Research, USTC, Suzhou, Jiangsu, 215123, China. [email protected].
- Jiangsu Provincial Key Laboratory of Multimodal Digital Twin Technology, Suzhou, Jiangsu, 215123, China. [email protected].
- State Key Laboratory of Precision and Intelligent Chemistry, USTC, Hefei, Anhui, 230026, China. [email protected].
- Biomedical Basic Research Center (BBRC) of Jiangsu Province, Suzhou, Jiangsu, 215123, China. [email protected].
Abstract
The development of generalist artificial intelligence (AI) models for radiology is hindered by a lack of large-scale, three-dimensional (3D) imaging datasets with precise spatial annotations. While numerous datasets provide image-level labels for chest computed tomography (CT), these are insufficient for training models that can accurately localize findings. To address this gap, we present PatchChestCT, a large-scale, publicly available dataset for multi-abnormality localization in non-contrast chest CT. Using CT-RATE as the source cohort, PatchChestCT provides 3D patch-level annotations for nine clinically significant abnormalities across 2,201 physician-reviewed CT studies, with one reconstructed volume labeled per study. We introduce a token-aligned annotation scheme that is efficient, scalable, and naturally integrates with modern deep learning architectures like Transformers. To validate the dataset's utility, we show that models trained with our patch-level labels achieved higher localization performance than weakly supervised baselines trained on image-level labels alone, across multiple architectures. PatchChestCT provides a public resource for training localization-aware models in chest CT.