Related Experiment Video
Updated: Jul 10, 2025
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
National Cancer Institute Imaging Data Commons: Toward Transparency, Reproducibility, and Scalability in Imaging
Andrey Fedorov1, William J R Longabaugh1, David Pot1
1From the Department of Radiology, Brigham and Women's Hospital and Harvard Medical School, 399 Revolution Dr, Somerville, MA 02145 (A.F., D.K., V.K.T., C.C., R.K.); Institute for Systems Biology, Seattle, Wash (W.J.R.L., D.L.G.); General Dynamics Information Technology, Rockville, Md (D.P.); PixelMed Publishing, Bangor, Pa (D.A.C.); Isomics, Cambridge, Mass (S.D.P.); Departments of Radiology (C.B.) and Pathology (M.D.H.), Massachusetts General Hospital and Harvard Medical School, Boston, Mass; Fraunhofer MEVIS, Bremen, Germany (A.H., D.P.S.); Radical Imaging, Boston, Mass (R.L.); Artificial Intelligence in Medicine Program, Mass General Brigham, Harvard Medical School, Boston, Mass (H.J.W.L.A., D.B.); Radiology and Nuclear Medicine, CARIM & GROW, Maastricht University, Maastricht, the Netherlands (H.J.W.L.A., D.B.); Frederick National Laboratory for Cancer Research, Rockville, Md (T.P., U.W.); and National Cancer Institute, Bethesda, Md (K.F., E.K.).
Artificial intelligence (AI) advances cancer research by enabling analysis of large, diverse biomedical imaging datasets. The National Cancer Institute
Area of Science:
- Biomedical imaging
- Artificial intelligence
- Cancer research
Background:
- Artificial intelligence (AI) is transforming biomedical imaging analysis.
- High-quality, diverse, and annotated datasets are crucial for AI tool development and validation.
- Challenges exist in establishing reproducible and transparent AI processing pipelines.
Purpose of the Study:
- To introduce the National Cancer Institute (NCI) Imaging Data Commons (IDC) as a resource for AI development in cancer imaging.
- To highlight the IDC's role in facilitating the development, validation, and clinical translation of AI tools.
- To address challenges in AI reproducibility and transparency in biomedical imaging.
Main Methods:
- Hosting large, diverse, and publicly available cancer image data collections.
- Harmonizing data to industry standards and providing colocalized analysis resources.
- Integrating commercial and open-source solutions with standard interfaces for agility and performance.
Main Results:
- The IDC provides a centralized repository for cancer imaging data.
- Data harmonization and colocalization with analysis tools simplify AI development.
- Emphasis on tools, use cases, and cloud-based analysis promotes adoption and best practices.
Conclusions:
- The NCI IDC is a key resource for advancing AI in cancer imaging research.
- Standardized data and integrated resources facilitate AI tool development and clinical translation.
- Integration with broader NCI infrastructure enables multiomics studies for accelerated cancer research breakthroughs.
