Skip to main content

Main menu

  • Home
  • Content
    • Current
    • Ahead of print
    • Past Issues
    • JNM Supplement
    • SNMMI Annual Meeting Abstracts
    • Continuing Education
    • JNM Podcasts
  • Subscriptions
    • Subscribers
    • Institutional and Non-member
    • Rates
    • Journal Claims
    • Corporate & Special Sales
  • Authors
    • Submit to JNM
    • Information for Authors
    • Assignment of Copyright
    • AQARA requirements
  • Info
    • Reviewers
    • Permissions
    • Advertisers
  • About
    • About Us
    • Editorial Board
    • Contact Information
  • More
    • Alerts
    • Feedback
    • Help
    • SNMMI Journals
  • SNMMI
    • JNM
    • JNMT
    • SNMMI Journals
    • SNMMI

User menu

  • Subscribe
  • My alerts
  • Log in
  • My Cart

Search

  • Advanced search
Journal of Nuclear Medicine
  • SNMMI
    • JNM
    • JNMT
    • SNMMI Journals
    • SNMMI
  • Subscribe
  • My alerts
  • Log in
  • My Cart
Journal of Nuclear Medicine

Advanced Search

  • Home
  • Content
    • Current
    • Ahead of print
    • Past Issues
    • JNM Supplement
    • SNMMI Annual Meeting Abstracts
    • Continuing Education
    • JNM Podcasts
  • Subscriptions
    • Subscribers
    • Institutional and Non-member
    • Rates
    • Journal Claims
    • Corporate & Special Sales
  • Authors
    • Submit to JNM
    • Information for Authors
    • Assignment of Copyright
    • AQARA requirements
  • Info
    • Reviewers
    • Permissions
    • Advertisers
  • About
    • About Us
    • Editorial Board
    • Contact Information
  • More
    • Alerts
    • Feedback
    • Help
    • SNMMI Journals
  • View or Listen to JNM Podcast
  • Visit JNM on Facebook
  • Join JNM on LinkedIn
  • Follow JNM on Twitter
  • Subscribe to our RSS feeds
Research ArticleIs It Really Happening?

Is the Clinical Implementation of In-House Artificial Intelligence–Developed Algorithms Happening?

David Gergely Kovacs, Claes Nøhr Ladefoged, Jacob Bak Rosenkjær, Fatima Mawassi, Line Akiti Hingelberg, Anna Olga Aaskilde Laursen, Barbara Malene Fischer and Flemming Littrup Andersen
Journal of Nuclear Medicine February 2025, 66 (2) 183-185; DOI: https://doi.org/10.2967/jnumed.124.268156
David Gergely Kovacs
1Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark;
2Department of Clinical Medicine, Faculty of Health and Medical Sciences, Copenhagen, Denmark;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Claes Nøhr Ladefoged
1Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark;
3Department of Applied Mathematics and Computer Science, Technical University of Denmark, Lyngby, Denmark; and
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Jacob Bak Rosenkjær
4Digital Regulation, Center for IT and Medical Technology, Capitol Region of Denmark, Copenhagen, Denmark
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Fatima Mawassi
4Digital Regulation, Center for IT and Medical Technology, Capitol Region of Denmark, Copenhagen, Denmark
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Line Akiti Hingelberg
4Digital Regulation, Center for IT and Medical Technology, Capitol Region of Denmark, Copenhagen, Denmark
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Anna Olga Aaskilde Laursen
4Digital Regulation, Center for IT and Medical Technology, Capitol Region of Denmark, Copenhagen, Denmark
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Barbara Malene Fischer
1Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark;
2Department of Clinical Medicine, Faculty of Health and Medical Sciences, Copenhagen, Denmark;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
Flemming Littrup Andersen
1Department of Clinical Physiology and Nuclear Medicine, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark;
2Department of Clinical Medicine, Faculty of Health and Medical Sciences, Copenhagen, Denmark;
  • Find this author on Google Scholar
  • Find this author on PubMed
  • Search for this author on this site
  • Article
  • Figures & Data
  • Info & Metrics
  • PDF
Loading

The advent of artificial intelligence (AI) in medical imaging and nuclear medicine could revolutionize our approach to diagnosing and treating complex conditions. Our recent paper, “Clinical Evaluation of Deep Learning for Tumor Delineation on 18F-FDG PET/CT of Head and Neck Cancer,” (1) showcases the potential of in-house AI in clinical practice. Clinically, we often find ourselves in need of a legitimate path to apply in-house developments. Here, Article 5(5) of the European Medical Device Regulation (MDR) 2017/745 regulations (2), the “in-house rule,” may provide a solution. The in-house rule allows health institutions to develop and use devices solely within their facilities, reducing the need for exhaustive external documentation and oversight typical of full conformité européenne marking. By focusing on a tailored quality management system (QMS) for safety and performance, institutions can save considerable time and resources compared with the comprehensive requirements for commercial distribution.

In line with Saboury et al.’s call for trustworthy AI frameworks (3), this article elucidates how the in-house rule supports structured and reliable clinical implementation and testing of our in-house AI algorithm. Please note that this article is intended for inspiration and should not be used as a direct guide or precedent for applying the in-house rule in practice. Interpretation and implementation will vary by institution and country because of national regulatory nuances. By sharing our experience as one of the first adopters in Denmark’s Capital Region, we hope to inspire and encourage other jurisdictions to adopt approaches that support hospital-based innovation within the framework of Article 5(5).

THE IN-HOUSE RULE: A CATALYST FOR INNOVATION AT HEALTH INSTITUTIONS

The in-house rule is a provision within the European MDR that permits health institutions to develop and use their own medical device software, provided they comply with specific regulatory requirements (2). This rule allows health institutions to create local solutions for clinical needs not addressed by commercial entities (4). In our recent work, we successfully integrated an AI algorithm for tumor delineation into our clinical pipeline, making prospective clinical testing possible. However, authors and developers should be aware early on that several requirements must be met before the in-house rule can be applied. First, a document of user requirements must be predefined before requesting approval for use under the in-house rule. Developers must have a clearly defined specific intended use and conduct a risk classification of the product in accordance with MDR. Additionally, a market analysis should be performed to assess the availability of MDR-approved software with similar functionality. The in-house rule typically applies when there is a need for a solution that is not available on the market or when an existing solution requires customization to support the institution’s specific workflows and processes for patient care in a particular context.

ESTABLISHING A ROBUST AND ITERATIVE QMS

A critical requirement for using the in-house rule is the establishment of a robust QMS tailored to in-house-developed devices (5). The QMS must ensure that all necessary processes, risk assessments, and testing procedures are in place to comply with the MDR. Although the specific structure of a QMS may vary across institutions, certain key themes are essential for ensuring the safety and effectiveness of the medical device.

At the core of a robust QMS are comprehensive design, risk management, and testing processes, which are inherently iterative. The design process begins with a clear definition of the intended use, along with specifications that align with clinical needs. Risk management involves identifying, assessing, and mitigating potential risks associated with the device. These steps are interdependent: after conducting a risk analysis, the design may need to be revisited and refined to address identified risks, requiring updates to the product and associated documentation, including requirement specifications, test plans, and test reports.

The iterative nature of the QMS ensures that each revision of the product is tested and validated. Testing strategies must be developed to verify that the device meets its specifications and performs as intended. According to the RELAINCE guidelines, specific QMS measures such as periodic monitoring and postdeployment assessments play a critical role in ensuring ongoing safety and efficacy of AI algorithms in clinical environments (6). This includes planning, executing, and documenting tests that demonstrate the device’s reliability, safety, and effectiveness under expected conditions of use. The exact testing requirements depend on the MDR risk classification and the specific implementation of regulations at each institution.

For example, in our case, the QMS process led to the initiation of a prospective noninferiority study involving 150 patients, testing whether physicians become over-reliant on AI. This clinical test aims to provide evidence that the algorithm is safe and effective and that clinicians maintain appropriate clinical judgment when using AI, which is critical for the safe implementation of AI in clinical practice.

Overall, an appropriate QMS must be tailored to the specific requirements of the device and the institution while ensuring compliance with MDR. The design, risk, and testing processes must work in concert, with each cycle of refinement and validation bringing the product closer to clinical readiness. Each organization must interpret the requirements of Article 5(5) and implement a QMS that meets regulatory standards, supports quality assurance, and facilitates the safe introduction of in-house-developed medical devices into clinical practice.

ADDRESSING NICHE CLINICAL NEEDS

The creation of the in-house rule under European regulations enables innovation and allows institutions to address specific clinical challenges promptly (4). By leveraging this rule, health institutions can implement and clinically test their AI developments, ensuring they meet quality and safety standards, and ultimately implement these into clinical routine. This regulatory option is crucial for advancing medical science and improving patient care, especially in areas lacking commercial solutions.

Moreover, the in-house rule supports the development of AI solutions where commercial interest may be limited. For instance, AI models for rare diseases or small patient populations often do not attract commercial developers because of limited market potential. However, these areas are where innovative solutions are needed. As a health institution, we can acquire the necessary hardware and use open-source AI methods to train models tailored to these specific needs. This capability allows clinical researchers to advance medical care for conditions that might otherwise remain under-researched (7). In addition, it enables showcasing of AI solutions that could have a large clinical impact and potential commercial interest.

PRACTICAL IMPLEMENTATION AND FUTURE DIRECTIONS

We have implemented our AI method in our clinical pipeline and are testing it prospectively on incoming patients in a shadow testing phase. This parallel testing helps identify initial flaws and areas for improvement, leading to the next iteration of the product. Subsequently, we plan to evaluate the impact of the AI tool on clinical decisions through masked assessments by oncologists. This prospective evaluation is crucial for validating the tool’s effectiveness and ensuring its safe integration into clinical practice (2,4). However, the path to clinical implementation has challenges. Establishing a QMS requires significant organizational commitment and resources. In the Capital Region of Denmark, the information technology department has a department dedicated to Digital Regulation with a team for handling QMS of products approved under the in-house rule. The documentation process is extensive, demanding meticulous attention and rigorous adherence to regulatory standards. Institutions must develop documents of user requirements that precisely define the intended use and performance expectations of the AI tool. Additionally, institutions need to ensure consistent documentation of development stages and any incidents or deviations, ensuring traceability and accountability throughout the development process.

PRODUCT EXPLANATION AND INTEGRATION TO CLINICAL SOFTWARE

Our product is a deep-learning algorithm designed for tumor delineation on 18F-FDG PET/CT scans of the head and neck (Fig. 1). The intended use of the product is “to automatically generate a qualified estimate of the 18F-FDG PET/CT-positive malignant area (abbreviated as PET-GTV, PET-positive Gross Tumor Volume) in scans of Head and neck cancer patients. The intended use is limited to decision support for nuclear medicine specialists in defining PET-GTV. The output PET-GTV is specifically intended for guiding the final gross tumor volume definition, which is subsequently used to define the Clinical Target Volume that forms the basis for radiotherapy treatment planning.” The algorithm leverages convolutional neural networks to analyze PET/CT images, providing precise and consistent tumor boundaries. The effectiveness of this AI tool was validated through a thorough clinical study, which demonstrated its equivalent performance compared with traditional methods. By integrating this AI solution into our clinical workflow, we hope to partially automate workflows, to reduce interobserver variability in tumor delineation, and to ultimately improve patient outcomes (1).

FIGURE 1.
  • Download figure
  • Open in new tab
  • Download powerpoint
FIGURE 1.

Visualization of function and quality of algorithm in axial plane of 50-y-old man with cancer of rhinopharynx. (Reprinted from (1).) HU = Hounsfield units.

A program was developed specifically for implementation in our clinical pipelines (available at https://github.com/Rigshospitalet-KFNM/HeadNeckPETGTV). This program provides a comprehensive pipeline for segmenting tumors in 18F-FDG PET/CT images of head and neck cancer using deep-learning techniques. The primary functionalities include data preprocessing, model application, and format conversion. The application utilizes a trained convolutional neural network previously published (1) to delineate tumor boundaries on the preprocessed images. The model used for segmentation, which takes the preprocessed PET/CT image as input and produces the delineations as output using DICOM Radiotherapy Structure Sets, is available online (https://rigshospitalet-tumor-segmentation.regionh.dk/). Using this pipeline, the AI algorithm can be effectively incorporated into the clinical workflow using the treatment planning system of choice, ensuring that tumor delineation is both precise and efficient.

CONCLUSION

The in-house rule is an enabler of innovation in medical practice, allowing health institutions to develop and implement AI solutions tailored to their specific needs. By adhering to regulatory requirements and maintaining rigorous documentation, institutions can bring in-house-developed AI tools to clinical practice, advancing patient care and addressing unmet clinical needs. Though the path to clinical implementation is challenging, the potential benefits for patient care are clear. Our experience implementing an AI method for tumor delineation demonstrates the in-house rule’s practical application and highlights the importance of a robust QMS, comprehensive documentation, and thorough risk analysis. As we move forward, it is essential for each organization to independently assess and document their processes, ensuring their AI developments meet the necessary regulatory standards and can be safely integrated into clinical practice. By doing so, we can continue to innovate and improve patient care, leveraging the full potential of AI in medicine.

DISCLOSURE

David Petersen received research funding from Brødrene Hartmanns Fond. Barbara Fischer received research funding from Aage and Johanne Louis-Hansen Fonden and has received support from Siemens Healthineers to attend meetings. No other potential conflict of interest relevant to this article was reported.

Footnotes

  • Published online Dec. 12, 2024.

  • © 2025 by the Society of Nuclear Medicine and Molecular Imaging.

REFERENCES

  1. 1.↵
    1. Kovacs DG,
    2. Ladefoged CN,
    3. Andersen KF,
    4. et al
    . Clinical evaluation of deep learning for tumor delineation on 18F-FDG PET/CT of head and neck cancer. J Nucl Med. 2024;65:623–629.
    OpenUrlAbstract/FREE Full Text
  2. 2.↵
    Medical Device Regulation (MDR). 2017/745. Publications Office of the European Union Publications Office website. https://eur-lex.europa.eu/legal-content/EN/ALL/?uri=CELEX%3A32017R0745. Updated July 9, 2024. Accessed November 25, 2024.
  3. 3.↵
    1. Saboury B,
    2. Bradshaw T,
    3. Boellaard R,
    4. et al
    . Artificial intelligence in nuclear medicine: opportunities, challenges, and responsibilities toward a trustworthy ecosystem. J Nucl Med. 2023;64:188–196.
    OpenUrlAbstract/FREE Full Text
  4. 4.↵
    MDCG 2023-1: Guidance on the health institution exemption under Article 5(5) of Regulation (EU) 2017/745 and Regulation (EU) 2017/746. Medical Device Coordination Group website. https://health.ec.europa.eu/system/files/2023-01/mdcg_2023-1_en.pdf. Published January 2023. Accessed November 25, 2024.
  5. 5.↵
    1. Recht MP,
    2. Dewey M,
    3. Dreyer K,
    4. et al
    . Integrating artificial intelligence into the clinical practice of radiology: challenges and recommendations. Eur Radiol. 2020;30:3576–3584.
    OpenUrlCrossRefPubMed
  6. 6.↵
    1. Jha AK,
    2. Bradshaw TJ,
    3. Buvat I,
    4. et al
    . Nuclear medicine and artificial intelligence: best practices for evaluation (the RELAINCE guidelines). J Nucl Med. 2022;63:1288–1299.
    OpenUrlAbstract/FREE Full Text
  7. 7.↵
    1. Kelly CJ,
    2. Karthikesalingam A,
    3. Suleyman M,
    4. Corrado G,
    5. King D
    . Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019;17:195.
    OpenUrlCrossRefPubMed
  • Received for publication August 30, 2024.
  • Accepted for publication November 14, 2024.
PreviousNext
Back to top

In this issue

Journal of Nuclear Medicine: 66 (2)
Journal of Nuclear Medicine
Vol. 66, Issue 2
February 1, 2025
  • Table of Contents
  • Table of Contents (PDF)
  • About the Cover
  • Index by author
  • Complete Issue (PDF)
Print
Download PDF
Article Alerts
Sign In to Email Alerts with your Email Address
Email Article

Thank you for your interest in spreading the word on Journal of Nuclear Medicine.

NOTE: We only request your email address so that the person you are recommending the page to knows that you wanted them to see it, and that it is not junk mail. We do not capture any email address.

Enter multiple addresses on separate lines or separate them with commas.
Is the Clinical Implementation of In-House Artificial Intelligence–Developed Algorithms Happening?
(Your Name) has sent you a message from Journal of Nuclear Medicine
(Your Name) thought you would like to see the Journal of Nuclear Medicine web site.
Citation Tools
Is the Clinical Implementation of In-House Artificial Intelligence–Developed Algorithms Happening?
David Gergely Kovacs, Claes Nøhr Ladefoged, Jacob Bak Rosenkjær, Fatima Mawassi, Line Akiti Hingelberg, Anna Olga Aaskilde Laursen, Barbara Malene Fischer, Flemming Littrup Andersen
Journal of Nuclear Medicine Feb 2025, 66 (2) 183-185; DOI: 10.2967/jnumed.124.268156

Citation Manager Formats

  • BibTeX
  • Bookends
  • EasyBib
  • EndNote (tagged)
  • EndNote 8 (xml)
  • Medlars
  • Mendeley
  • Papers
  • RefWorks Tagged
  • Ref Manager
  • RIS
  • Zotero
Share
Is the Clinical Implementation of In-House Artificial Intelligence–Developed Algorithms Happening?
David Gergely Kovacs, Claes Nøhr Ladefoged, Jacob Bak Rosenkjær, Fatima Mawassi, Line Akiti Hingelberg, Anna Olga Aaskilde Laursen, Barbara Malene Fischer, Flemming Littrup Andersen
Journal of Nuclear Medicine Feb 2025, 66 (2) 183-185; DOI: 10.2967/jnumed.124.268156
Twitter logo Facebook logo LinkedIn logo Mendeley logo
  • Tweet Widget
  • Facebook Like
  • Google Plus One
Bookmark this article

Jump to section

  • Article
    • THE IN-HOUSE RULE: A CATALYST FOR INNOVATION AT HEALTH INSTITUTIONS
    • ESTABLISHING A ROBUST AND ITERATIVE QMS
    • ADDRESSING NICHE CLINICAL NEEDS
    • PRACTICAL IMPLEMENTATION AND FUTURE DIRECTIONS
    • PRODUCT EXPLANATION AND INTEGRATION TO CLINICAL SOFTWARE
    • CONCLUSION
    • DISCLOSURE
    • Footnotes
    • REFERENCES
  • Figures & Data
  • Info & Metrics
  • PDF

Related Articles

  • No related articles found.
  • PubMed
  • Google Scholar

Cited By...

  • No citing articles found.
  • Google Scholar

More in this TOC Section

  • Is 211At Really Happening?
  • Are FAP Theranostics Really Happening? Will Radiochemistry or Biology Win?
  • SPECT Deserves RESPECT: The Potential of SPECT/CT to Optimize Patient Outcomes with Theranostics Therapy
Show more Is It Really Happening?

Similar Articles

SNMMI

© 2025 SNMMI

Powered by HighWire