Abstract illustration of a butterfly-shaped network

Image IntelliGently™

Pediatric Radiology and AI Resources to Support Your Practice 

Artificial intelligence (AI) in medical imaging is rapidly growing to advance healthcare in adults but is less developed in the pediatric population. Unfortunately, many of the algorithms developed for use in adults cannot be used for children. This inability to translate adult tools to pediatric patients is due to many factors, including the wide range of body sizes, normal growth and development, different disease types, diverse manifestations of similar disorders, imaging bioeffects (such as to contrast media and radiation), and unique socioeconomic factors.

Pediatric patient needs are not being sufficiently considered when AI is developed, tested or deployed, and applications may be ineffective or detrimental to pediatric patients.Specifically, to date, none of commercially available medical imaging AI tools that diagnose, triage, or detect abnormalities were designed to be used in pediatric patients, and only a handful of tools for image processing or quantification have been developed to be used in pediatric patients. For this reason a Pediatric AI Working Group in the °ϲʹ® Informatics Commission has been established and is sponsoring the Image IntelliGently™ campaign to ensure equal access to high-quality and safe AI for pediatric patients.

Understand the Impact of AI in Pediatric Radiology

Simulated workflows illustrating the potential impact on pediatric patients when Artificial Intelligence is used for worklist prioritization.

Blonde girl wearing overalls high-fiving a male African American physician wearing a white coat
To ensure pediatric patient access and safety in medical imaging AI we endorse the following statements:
  1. AI used in pediatric patients should be designed for and shown to work in pediatric patients.
  2. Healthcare systems that care for both adults and children should consider an AI algorithm’s impact on pediatric patients before the AI is used only in adults.
  3. Regulatory changes are needed to ensure pediatric patient safety. Specifically, visible standard verbiage for all FDA-labeled medical devices to include (1) the age of subjects for which the devices were tested, (2) the age group in whom the devices are applicable, and (3) a warning when a device has not been cleared for pediatric use.
  4. Collaboration between pediatric radiologists, data scientists, vendors and regulatory bodies is needed to promote the development of safe, clinically useful AI for pediatric patients.

°ϲʹ DSI Resources

Hand holding abstract radiology image of a brain

The Pediatric Panel of the °ϲʹ Data Science Institute® (DSI) is charged with creating use cases designed to guide developers through the creation of pediatric-focused AI algorithms needed to Image IntelliGently. Explore the variety of pediatric cases and additional resources available:

with the °ϲʹ DSI.

Advocacy Efforts

African American mother and daughter reviewing imaging results with female radiologist

AI algorithms for medical imaging that are trained, validated and tested only on ADULTS pose a potential safety risk to children. Regulatory and legislative stakeholder engagement is key to ensuring the medical community continues to Image IntelliGently. Read our latest advocacy efforts:

Get Involved

If you’re using AI in pediatric patients, we want to hear from you!

Group high-five among medical workers

What can you do?

If you’re using AI in adults, but not pediatric patients in your practice, address its impact on pediatric patients. For example:

  1. Do radiologists and technologists know that AI isn’t being used on pediatric patients? If not, communication is needed.
  2. Check to see if the turnaround times for pediatric patients are being impacted when triage algorithms are used only in adults.
  3. If you’re using AI to shorten MRI sequences, audit your data to ensure it works as well in pediatric patients as it does in adults.

If you’re using AI in pediatric patients, share your experience. For example:

  1. Which adult tools are you using in pediatric patients? How well do they work?
  2. Does the AI work well across all pediatric ages or are there differences with subsets? For example, does the algorithm work well in teenagers, but not in infants?
  3. Are there extra steps you are taking to make sure AI keeps working as well in pediatric patients as does is in your adult patients?

If you want to help but aren’t yet using AI, educate and advocate for pediatric imaging AI. For example:

  1. Advocate for consistent inclusion of pediatric applicability labeling on FDA clearance documents.
  2. Advocate for incentives to promote the development of pediatric AI. This may take the form of additional funding for research studies or resources within the FDA for clearance.
  3. Support prioritization of pediatric radiology AI anytime you can influence development. It’s needed ASAP, just to catch up!
  4. Ask vendors if their algorithms have been tested in children
  5. Ask vendors if their algorithms have been FDA-cleared for use in children
  6. Advocate for the consistent inclusion of pediatric applicability labeling on FDA clearance documents

Who We Are


Image IntelliGently is composed of a wide variety of stakeholders, including private practices, academic settings and individuals with close ties to other relevant societies including , , and , and a variety of expertise in educational, clinical and research domains. The group is charged, through stakeholder consensus, with providing guidance to ensure that all pediatric patients will have equitable access to clinically meaningful AI as it becomes increasingly available for use in adults.

Through Image IntelliGently, our mission is to ensure access to safe and clinically useful AI for all pediatric patients.

Yasmin Akbari, MD
Richard Barth, MD
Steven Blumer, MD, MBA, CPE, FAAP
Jonathan R. Dillman, MD, MSc, F°ϲʹ, FSAR
Steven Don, MD
Shannon G. Farmakis, MD, FAAP
Donald P. Frush, MD, F°ϲʹ, FAAP, FSABI
Ami A. Gokli, MD
Safwan Halabi, MD
Mai-Lan Ho, MD
Ramesh Iyer, MD
Aparna Joshi, MD
Jeannie K. Kwon, MD
David B. Larson, MD, MBA
 

Robert D. MacDougall, PhD, DABR, CIIP
Brandon Nelson
Hansel J. Otero, MD, FAAP
Marla Sammer, MD, MHA, FAAP (Chair)
Gary Schooler, MD
Andrew Sher, MD
Susan Sotardi, MD
Benjamin Taragin, MD, F°ϲʹ
Alexander J. Towbin, MD, F°ϲʹ, FAAP
Andy Tsai, MD, PhD
Christoph Wald, MD, PhD, MBA, F°ϲʹ (Informatics Commission, Chair)
Paul Yi, MD
Vaz Zavaletta, MD, PhD