Related Experiment Video
Updated: Jun 21, 2025
Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
Published on: October 27, 2023
Advancing Medical Imaging Research Through Standardization: The Path to Rapid Development, Rigorous Validation, and
Kyulee Jeon1, Woo Yeon Park, Charles E Kahn
1From the Department of Biomedical Systems Informatics, Yonsei University, Seoul, South Korea (K.J., S.C.Y.); Institution for Innovation in Digital Healthcare, Yonsei University, Seoul, South Korea (K.J., S.C.Y.); Biomedical Informatics and Data Science, Johns Hopkins University, Baltimore, MD (W.Y.P., P.N.); Department of Radiology, University of Pennsylvania, Philadelphia, PA (C.E.K.); and Department of Radiology, Seoul National University College of Medicine, Seoul National University Hospital, Seoul, South Korea (S.H.Y.).
Standardizing medical imaging data with the OMOP Common Data Model is crucial for advancing artificial intelligence (AI) in radiology. This approach enhances data interoperability, enabling global collaboration and reproducible AI development.
Area of Science:
- Radiology
- Medical Informatics
- Artificial Intelligence
Background:
- Artificial intelligence (AI) shows promise in radiology, but faces challenges due to fragmented, non-standardized data.
- Lack of high-quality, large-scale, and standardized global medical imaging datasets hinders AI development, validation, and reproducibility.
Purpose of the Study:
- To propose a standardized framework for medical imaging data integration with structured clinical data.
- To facilitate large-scale, international AI research in radiology through data harmonization and interoperability.
Main Methods:
- Leveraging the Observational Health Data Sciences and Informatics (OHDSI) community's OMOP Common Data Model for structured data.
- Proposing a Medical Imaging Common Data Model to integrate DICOM-formatted images and derived features with clinical data, ensuring provenance.
Main Results:
- Standardization enables syntactic and semantic interoperability of medical imaging and clinical data.
- Facilitates privacy-protected, cross-border research collaborations and federated learning.
- Supports the development of foundation models trained on diverse, multimodal datasets.
Conclusions:
- Harmonized medical imaging and clinical data are essential for advancing AI in radiology.
- Standardization promotes equitable AI development, enhances reproducibility, and drives innovation in clinical applications.
More Related Videos
09:08Author Spotlight: Standardization and Best Practices for Advancing Lung Imaging Using 129Xe MRI
Published on: November 21, 2023
06:33Construction of a Preclinical Multimodality Phantom Using Tissue-mimicking Materials for Quality Assurance in Tumor Size Measurement
Published on: July 29, 2013