LDCT-and-Projection-data
Library of patient CT projection data in a vendor-neutral format to facilitate the development and validation of new CT reconstruction and/or denoising algorithms, including those associated with machine learning or artificial intelligence.
dataset2026-09-1558729766
40

Overview

Schema Version

https://atlas.rsna.org/schemas/2025-11/dataset.json

Name

LDCT-and-Projection-data

Link

https://www.cancerimagingarchive.net/?s=LDCT-and-Projection-data

Indexing

Keywords: Low Dose CT, CT Projection Data, Reconstruction Algorithms, Denoising Algorithms, Machine Learning, Artificial Intelligence, Vendor-neutral format, DICOM, Head, Chest, Abdomen, Phantom, Filtered Back Projection
Content: CT, HN, CH, GI, MI

Author(s)

McCollough, C.
Chen, B.
Holmes III, D.
Duan, X.
Yu, Z.
Yu, L.
Leng, S.
Fletcher, J.

Organization(s)

Mayo Clinic
The Cancer Imaging Archive (TCIA)
National Institute of Biomedical Imaging and Bioengineering (NIBIB)
American Association of Physicists in Medicine (AAPM)

Version

7

License

Text: Creative Commons Attribution 4.0 International
URL: https://creativecommons.org/licenses/by/4.0/

Contact

McCollough.Cynthia@mayo.edu

Funding

National Institute of Biomedical Imaging and Bioengineering (NIBIB) grants EB017095 and EB017185; Foundation for the National Institutes of Health (FNIH); American Association of Physicists in Medicine (AAPM); Mayo Clinic.

Comments

Investigators at the Mayo Clinic have built a library of CT patient projection data in an open and vendor-neutral format, referred to as DICOM-CT-PD. The de-identified patient projection data in the library were decoded with help of the manufacturer and have been converted into an open standardized format. Reconstructed images, patient age, and pathology annotation are also provided. The library consists of scans from various exam types, including non-contrast head CT scans, low-dose non-contrast chest scans, and contrast-enhanced CT scans of the abdomen. Part of this collection was used in the 2016 Low Dose CT Grand Challenge. Multiple licenses apply to this dataset: Chest and Liver data are under CC BY 4.0, Head data is under the NIH Controlled Data Access Policy, and supporting documents are under CC BY 3.0.

Date

Updated: 2025-08-14
Published: 2020

Dataset

Motivation

To provide a public library of patient CT projection data in a vendor-neutral format to facilitate the development and validation of new CT reconstruction and/or denoising algorithms, including those associated with machine learning or artificial intelligence.

Sampling

All CT scans were acquired at routine dose levels for the practice at which they were obtained using standard-clinical protocols for the anatomical region of interest.

Confidentiality

Data is de-identified. Some data in this collection contains images that could potentially be used to reconstruct a human face. Access to these data is restricted and requires following the NIH Controlled Data Access Policy.