Skip to main content
Top

29-01-2025 | Artificial Intelligence

Medical Imaging Data Strategies for Catalyzing AI Medical Device Innovation

Authors: Ravi K. Samala, Brandon D. Gallas, Ghada Zamzmi, Krishna Juluru, Amir Khan, Catherine Bahr, Robert Ochs, Dorn Carranza, Jason Granstedt, Edward Margerrison, Aldo Badano

Published in: Journal of Imaging Informatics in Medicine

Login to get access

Abstract

Continuous and consistent access to quality medical imaging data stimulates innovations in artificial intelligence (AI) technologies for patient care. Breakthrough innovations in data-driven AI technologies are founded on seamless communication between data providers, data managers, data users and regulators or other evaluators to determine the standards for quality data. However, the complexity in imaging data quality and heterogeneous nature of AI-enabled medical devices and their intended uses presents several challenges limiting the clinical translation of novel AI technologies. In this commentary, we discuss these challenges across different characteristics of data, such as data size, data labels, data diversity, data sequestration and reuse, and data drift. We discuss strategies around a data platform that incorporates protocols and checklists for ensuring data quality, tools and interactive guidelines that may help assess data diversity, study design and performance metrics for data usage and monitoring for data analytics. We envision this data platform to catalyze AI-enabled medical device innovation by providing a more efficient development and evaluation environment for bringing safe and effective AI technologies to the clinic.
Literature
1.
go back to reference Clark, K. et al. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. Journal of Digital Imaging 26, 1045-1057 (2013).CrossRefPubMedPubMedCentral Clark, K. et al. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. Journal of Digital Imaging 26, 1045-1057 (2013).CrossRefPubMedPubMedCentral
2.
go back to reference Dong, J. et al. Clinical trials for artificial intelligence in cancer diagnosis: a cross-sectional study of registered trials in ClinicalTrials. gov. Frontiers in oncology 10, 1629 (2020). Dong, J. et al. Clinical trials for artificial intelligence in cancer diagnosis: a cross-sectional study of registered trials in ClinicalTrials. gov. Frontiers in oncology 10, 1629 (2020).
3.
go back to reference U.S. Food & Drug Administration & Center for Devices and Radiological Health. Guidance for Industry: General/Specific Intended Use. (1998). U.S. Food & Drug Administration & Center for Devices and Radiological Health. Guidance for Industry: General/Specific Intended Use. (1998).
4.
go back to reference Sahiner, B., Chen, W., Samala, R. K. & Petrick, N. Data drift in medical machine learning: implications and potential remedies. The British Journal of Radiology 96, 20220878 (2023).CrossRefPubMedPubMedCentral Sahiner, B., Chen, W., Samala, R. K. & Petrick, N. Data drift in medical machine learning: implications and potential remedies. The British Journal of Radiology 96, 20220878 (2023).CrossRefPubMedPubMedCentral
5.
go back to reference Viergever, R. F. & Hendriks, T. C. The 10 largest public and philanthropic funders of health research in the world: what they fund and how they distribute their funds. Health research policy and systems 14, 1-15 (2016).CrossRef Viergever, R. F. & Hendriks, T. C. The 10 largest public and philanthropic funders of health research in the world: what they fund and how they distribute their funds. Health research policy and systems 14, 1-15 (2016).CrossRef
7.
go back to reference Faheem, H. & Dutta, S. Artificial Intelligence Failure at IBM'Watson for Oncology'. IUP Journal of Knowledge Management 21, 47-75 (2023). Faheem, H. & Dutta, S. Artificial Intelligence Failure at IBM'Watson for Oncology'. IUP Journal of Knowledge Management 21, 47-75 (2023).
9.
go back to reference U.S. Food & Drug Administration. Using Artificial Intelligence & Machine Learning in the Development of Drug & Biological Products: Discussion Paper and Request for Feedback. (2023). U.S. Food & Drug Administration. Using Artificial Intelligence & Machine Learning in the Development of Drug & Biological Products: Discussion Paper and Request for Feedback. (2023).
11.
go back to reference Tsai, E. et al. Data from Medical Imaging Data Resource Center (MIDRC) - RSNA International COVID Radiology Database (RICORD) Release 1c - Chest x-ray, Covid+ (MIDRC-RICORD-1C). The Cancer Imaging Archive. (2021). https://doi.org/10.7937/91ah-v663 Tsai, E. et al. Data from Medical Imaging Data Resource Center (MIDRC) - RSNA International COVID Radiology Database (RICORD) Release 1c - Chest x-ray, Covid+ (MIDRC-RICORD-1C). The Cancer Imaging Archive. (2021). https://​doi.​org/​10.​7937/​91ah-v663
12.
go back to reference Glynn, P. & Greenland, P. Contributions of the UK biobank high impact papers in the era of precision medicine. European Journal of Epidemiology 35, 5-10 (2020).CrossRefPubMed Glynn, P. & Greenland, P. Contributions of the UK biobank high impact papers in the era of precision medicine. European Journal of Epidemiology 35, 5-10 (2020).CrossRefPubMed
15.
go back to reference Sammer, M. B. et al. Use of artificial intelligence in radiology: impact on pediatric patients, a white paper from the ACR pediatric AI workgroup. Journal of the American College of Radiology 20, 730-737 (2023).CrossRefPubMed Sammer, M. B. et al. Use of artificial intelligence in radiology: impact on pediatric patients, a white paper from the ACR pediatric AI workgroup. Journal of the American College of Radiology 20, 730-737 (2023).CrossRefPubMed
16.
go back to reference Sunoqrot, M. R., Saha, A., Hosseinzadeh, M., Elschot, M. & Huisman, H. Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges. European radiology experimental 6, 35 (2022).CrossRefPubMedPubMedCentral Sunoqrot, M. R., Saha, A., Hosseinzadeh, M., Elschot, M. & Huisman, H. Artificial intelligence for prostate MRI: open datasets, available applications, and grand challenges. European radiology experimental 6, 35 (2022).CrossRefPubMedPubMedCentral
17.
go back to reference U. S. Food and Drug Administration. Center for Devices and Radiological Health, 2022–2025 Strategic Priorities. (U. S. Food and Drug Administration,, 2022). U. S. Food and Drug Administration. Center for Devices and Radiological Health, 2022–2025 Strategic Priorities. (U. S. Food and Drug Administration,, 2022).
18.
go back to reference U.S. Food & Drug Administration. Pulse Oximeters - Premarket Notification Submissions [510(k)s] Guidance for Industry and Food and Drug Administration Staff. (2013). U.S. Food & Drug Administration. Pulse Oximeters - Premarket Notification Submissions [510(k)s] Guidance for Industry and Food and Drug Administration Staff. (2013).
19.
go back to reference Wolf, R. M., Channa, R., Abramoff, M. D. & Lehmann, H. P. Cost-effectiveness of autonomous point-of-care diabetic retinopathy screening for pediatric patients with diabetes. JAMA ophthalmology 138, 1063-1069 (2020).CrossRefPubMed Wolf, R. M., Channa, R., Abramoff, M. D. & Lehmann, H. P. Cost-effectiveness of autonomous point-of-care diabetic retinopathy screening for pediatric patients with diabetes. JAMA ophthalmology 138, 1063-1069 (2020).CrossRefPubMed
20.
go back to reference U.S. Food & Drug Administration. Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data - Premarket Notification [510(k)] Submissions: Guidance for Industry and Food and Drug Administration Staff. (2012). U.S. Food & Drug Administration. Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data - Premarket Notification [510(k)] Submissions: Guidance for Industry and Food and Drug Administration Staff. (2012).
21.
go back to reference U.S. Food & Drug Administration. Clinical Performance Assessment: Considerations for Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data in Premarket Notification (510(k)) Submissions: Guidance for Industry and FDA Staff. (2020). U.S. Food & Drug Administration. Clinical Performance Assessment: Considerations for Computer-Assisted Detection Devices Applied to Radiology Images and Radiology Device Data in Premarket Notification (510(k)) Submissions: Guidance for Industry and FDA Staff. (2020).
22.
go back to reference Davis, S. E., Lasko, T. A., Chen, G., Siew, E. D. & Matheny, M. E. Calibration drift in regression and machine learning models for acute kidney injury. Journal of the American Medical Informatics Association 24, 1052-1061 (2017).CrossRefPubMedPubMedCentral Davis, S. E., Lasko, T. A., Chen, G., Siew, E. D. & Matheny, M. E. Calibration drift in regression and machine learning models for acute kidney injury. Journal of the American Medical Informatics Association 24, 1052-1061 (2017).CrossRefPubMedPubMedCentral
23.
go back to reference U.S. Food & Drug Administration. FDA and Industry Actions on Premarket Notification (510(k)) Submissions: Effect on FDA Review Clock and Goals: Guidance for Industry and Food and Drug Administration Staff. (2022). U.S. Food & Drug Administration. FDA and Industry Actions on Premarket Notification (510(k)) Submissions: Effect on FDA Review Clock and Goals: Guidance for Industry and Food and Drug Administration Staff. (2022).
24.
go back to reference Elfer, K. et al. Reproducible Reporting of the Collection and Evaluation of Annotations for Artificial Intelligence Models. Modern Pathology 37, 100439 (2024).CrossRefPubMed Elfer, K. et al. Reproducible Reporting of the Collection and Evaluation of Annotations for Artificial Intelligence Models. Modern Pathology 37, 100439 (2024).CrossRefPubMed
25.
go back to reference Shah, N. H. et al. A Nationwide Network of Health AI Assurance Laboratories. JAMA 331, 245-249 (2024).CrossRefPubMed Shah, N. H. et al. A Nationwide Network of Health AI Assurance Laboratories. JAMA 331, 245-249 (2024).CrossRefPubMed
26.
go back to reference Sizikova, E. et al. Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses. Advances in Neural Information Processing Systems 36 (2024). Sizikova, E. et al. Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses. Advances in Neural Information Processing Systems 36 (2024).
27.
29.
go back to reference Jeong, J. J. et al. The EMory BrEast imaging Dataset (EMBED): A racially diverse, granular dataset of 3.4 million screening and diagnostic mammographic images. Radiology: Artificial Intelligence 5, e220047 (2023). Jeong, J. J. et al. The EMory BrEast imaging Dataset (EMBED): A racially diverse, granular dataset of 3.4 million screening and diagnostic mammographic images. Radiology: Artificial Intelligence 5, e220047 (2023).
Metadata
Title
Medical Imaging Data Strategies for Catalyzing AI Medical Device Innovation
Authors
Ravi K. Samala
Brandon D. Gallas
Ghada Zamzmi
Krishna Juluru
Amir Khan
Catherine Bahr
Robert Ochs
Dorn Carranza
Jason Granstedt
Edward Margerrison
Aldo Badano
Publication date
29-01-2025
Publisher
Springer International Publishing
Published in
Journal of Imaging Informatics in Medicine
Print ISSN: 2948-2925
Electronic ISSN: 2948-2933
DOI
https://doi.org/10.1007/s10278-024-01374-6