Artificial Intelligence for Response Assessment in Pediatric Neuro-Oncology (AI-RAPNO), part 2: challenges, opportunities, and recommendations for clinical translation - 28/10/25

Doi : 10.1016/S1470-2045(25)00489-9

Anahita Fathi Kazerooni, PhD ^a,^b,^d,⁎ , Ariana M Familiar, PhD ^a,^b, Mariam Aboian, MD ^c, Sarah C Brüningk, PhD ^f, Arastoo Vossough, ProfMD ^a,^c,^e,^x, Marius George Linguraru, ProfPhD ^g,^h, Raymond Y Huang, MD ⁱ, Darren Hargrave, ProfMD ⁿ, Andrew C Peet, ProfPhD ^o,^p, Adam C Resnick, ProfPhD ^a,^b,^d, Phillip B Storm, ProfMD ^a,^b,^d, David Mirsky, MD ^q, Kristen W Yeom, MD ^r, Michael Weller, ProfMD ^s, Michael Prados, ProfMD ^t, Susan M Chang, ProfMD ^v, Sabine Mueller, ProfMD ^t, Javier E Villanueva-Meyer, MD ^u, Spyridon Bakas, PhD ^w,^x,^y,^z, Jason Fangusaro, ProfMD ^aa, Benjamin H Kann, MD ^j,^k,^l,^m,^{*
Contributed equally}, Ali Nabavizadeh, MD ^a,^e,^{*
Contributed equally}
for the
Response Assessment in Pediatric Neuro-Oncology (RAPNO) group

^a Center for Data-Driven Discovery in Biomedicine, The Children’s Hospital of Philadelphia, Philadelphia, PA, USA

^b Department of Neurosurgery, The Children’s Hospital of Philadelphia, Philadelphia, PA, USA

^c Department of Radiology, The Children’s Hospital of Philadelphia, Philadelphia, PA, USA

^d Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA

^e Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA

^f Department of Radiation Oncology, Inselspital, Bern University Hospital and University of Bern, Bern, Switzerland

^g Sheikh Zayed Institute for Pediatric Surgical Innovation, Children’s National Hospital, Washington, DC, USA

^h School of Medicine and Health Sciences, George Washington University, Washington, DC, USA

ⁱ Department of Radiology, Brigham and Women’s Hospital, Boston, MA, USA

^j Department of Radiation Oncology, Brigham and Women’s Hospital, Boston, MA, USA

^k Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, USA

^l Artificial Intelligence in Medicine Program, Mass General Brigham, Boston, MA, USA

^m Boston Children’s Hospital, Boston, MA, USA

ⁿ Great Ormond Street Institute of Child Health, University College London, London, UK

^o Department of Cancer and Genomic Sciences, University of Birmingham, Birmingham, UK

^p Oncology Department, Birmingham Children’s Hospital, Birmingham, UK

^q Department of Radiology, Children’s Hospital Colorado, University of Colorado, CO, USA

^r Division of Neuroradiology, Department of Radiology, Stanford University, Stanford, CA, USA

^s Department of Neurology, University Hospital and University of Zurich, Zurich, Switzerland

^t Department of Neurology and Pediatrics, University of California San Francisco, San Francisco, CA, USA

^u Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, CA, USA

^v Division of Neuro-Oncology, Department of Neurosurgery, University of California, San Francisco, CA, USA

^w Division of Computational Pathology, Department of Pathology and Laboratory Medicine, Indiana University School of Medicine, Indianapolis, IN, USA

^x Indiana University Melvin and Bren Simon Comprehensive Cancer Center, Indianapolis, IN, USA

^y Department of Computer Science, Luddy School of Informatics, Computing, Engineering, Indiana University, Indianapolis, IN, USA

^z Medical Research Group, MLCommons, San Francisco, CA, USA

^aa The Aflac Cancer Center, Children’s Healthcare of Atlanta and the Emory University School of Medicine, Atlanta, GA, USA

^* Correspondence to: Assist Prof Anahita Fathi Kazerooni, Department of Neurosurgery, Children’s Hospital of Philadelphia, Philadelphia, PA 19146, USA Department of Neurosurgery Children’s Hospital of Philadelphia Philadelphia PA 19146 USA

Summary

The Response Assessment in Pediatric Neuro-Oncology (RAPNO) criteria provide an important framework for evaluating treatment efficacy and tumour progression in clinical studies of paediatric brain tumours. As artificial intelligence (AI) rapidly transforms clinical practice, integrating AI into the RAPNO framework presents a unique opportunity to enhance quantitative, data-driven approaches for response assessment. However, successful clinical implementation faces challenges, including variability in imaging protocols, scarce annotated datasets, and regulatory and ethical considerations. To address these barriers, this Policy Review, led by the AI for Assessment in Pediatric Neuro-Oncology (AI-RAPNO) subcommittee, outlines key challenges and proposes recommendations to improve AI trustworthiness, generalisability, and implementation in paediatric neuro-oncology. We highlight the potential of AI for response assessment, multimodal integration, and synthetic control groups in clinical trials. Our recommendations emphasise the need for standardised imaging protocols, robust validation frameworks, and infrastructure to support AI readiness in clinical studies. By addressing these needs, AI-RAPNO aims to bridge the gap between AI research and clinical application, ensuring reliable and actionable AI-driven tools for paediatric neuro-oncology.

Le texte complet de cet article est disponible en PDF.

Plan

Introduction

AI readiness and infrastructure for clinical translation

Imaging standardisation and subregion differentiation

Measures for response assessment

Paediatric-specific tools for image processing and analysis

Infrastructure to support AI-readiness in clinical studies

Scarce, fragmented, and imbalanced data

Siloed datasets, models, and codes

Generalisability and benchmarks for validations

Next generation of AI research in paediatric neuro-oncology

Multimodal analysis to facilitate precision diagnostics

Synthetic control arms

Conclusion

Search strategy and selection criteria

Contributors

Export

Vol 26 - N° 11

P. e607-e618 - novembre 2025 Retour au numéro

Article précédent

Artificial Intelligence for Response Assessment in Pediatric Neuro-Oncology (AI-RAPNO), part 1: review of the current state of the art
Benjamin H Kann, Arastoo Vossough, Sarah C Brüningk, Ariana M Familiar, Mariam Aboian, Marius George Linguraru, Kristen W Yeom, Susan M Chang, Darren Hargrave, David Mirsky, Phillip B Storm, Raymond Y Huang, Adam C Resnick, Michael Weller, Sabine Mueller, Michael Prados, Andrew C Peet, Javier E Villanueva-Meyer, Spyridon Bakas, Jason Fangusaro, Ali Nabavizadeh, Anahita Fathi Kazerooni, Response Assessment in Pediatric Neuro-Oncology (RAPNO) group

| Article suivant

A red patch on the palate
Emmanuelle Vigarios, Jérôme Sarini, Saman Warnakulasuriya, Béatrice Barres-Herbault, Vincent Sibaud, Delphine Maret

Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.

Déjà abonné à cette revue ?

connectez-vous ou créez un compte

Artificial Intelligence for Response Assessment in Pediatric Neuro-Oncology (AI-RAPNO), part 2: challenges, opportunities, and recommendations for clinical translation - 28/10/25

Summary

Plan

Export citations

Fichier

Contenu

Accès rapides

Mon compte

Aide & support

Plateformes Elsevier Masson

Déclaration CNIL