System Maintenance Notice

Please note that maintenance work is scheduled between 4 AM and 5 AM - CET. During this time, you may experience reduced performance. Thanks for your patience.

Publications

Journal Article Ahead of print

PubMed: 42869977 DOI: 10.1038/s41551-026-01812-6

Repurposing adult AI radiograph models for neonatal care through continual learning: an international multicentre study.

Nat Biomed Eng

Authors: Vishwanatha M Rao, Emma Chen, Agustina Saenz, Oishi Banerjee, Henrik Marklund, Lucas Bijnens, Sung Eun Kim, Evan Zucker, Susan Shelmerdine, Jeremy Palacio, Kent Ryan Kleinschmidt, Sathvik Suryadevara, Sri Sai Dinesh Jaliparthi, Jiaxi Lu, Rithvik Akula, Mario Scala, Julian F Niedermair, Nikolaus Stranger, Sebastian Tschauner, Georg M Schmölzer, Maria Jose Veloza Vega, Juan Sebastián Osorio Valencia, Oscar Jaramillo Robledo, Oscar Julian López Uribe, Saif Afat, Thomas Küstner, Soroosh Tayebi Arasteh, Daniel Truhn, Kelsey L Pomykala, Jens Kleesiek, Naela Himayati Afifah, Rozan M Irfan, Reza Shahriarirad, Amirhossein Erfani, Israel Amirav, Moria Be'er, Yasuhito Mitsuyama, Daiju Ueda, Alain S Abi-Ghanem, Safaa Al Zakleet, Mossad Abdelhak Shaban Mohamed, Wan Irfan Bin W Mustapha, Naila Nizami, Rafeah Khan, Khalid Al-Kharazi, Zafar Iqbal, Abdullah Al Shahrani, Amna Kashgari, Tijana Prodanovic, Nikola Prodanovic … and 25 other authors

Affiliations

  • Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
  • Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA.
  • Department of Bioengineering, School of Engineering and Applied Science, University of Pennsylvania, Philadelphia, PA, USA.
  • School of Engineering and Applied Sciences, Harvard University, Cambridge, MA, USA.
  • Department of Medicine, Brigham and Women's Hospital, Boston, MA, USA.
  • Department of Computer Science, Stanford University, Stanford, CA, USA.
  • Department of Imaging and Pathology, KU Leuven, Leuven, Belgium.
  • Department of Radiology/Pediatric Radiology, Stanford University, Palo Alto, CA, USA.
  • Department of Clinical Radiology, Great Ormond Street Hospital for Children, London, UK.
  • Saint Louis University School of Medicine, Saint Louis University, Saint Louis, MO, USA.
  • Central Radiology Institute, Johannes Kepler University Linz, Kepler University Hospital GmbH, Linz, Austria.
  • Division of Virtual Morphology, Institute of Anatomy and Cell Biology, Johannes Kepler University, Linz, Austria.
  • Division of Pediatric Radiology, Department of Radiology, Medical University of Graz, Graz, Austria.
  • Department of Pediatrics, Faculty of Medicine and Dentistry, University of Alberta, Edmonton, Alberta, Canada.
  • Artificial Intelligence Committee, Colombian Association of Radiology, Medellín, Colombia.
  • Medical Imaging and AI in Health SURA, Bioscience Center, Ayudas Diagnósticas SURA, Medellín, Colombia.
  • Education and Research Department, Servicios Especiales de Salud Hospital Universitario de Caldas, Manizales, Colombia.
  • Department of Pediatrics and Neonatology, Servicios Especiales de Salud Hospital Universitario de Caldas, Manizales, Colombia.
  • Department of Diagnostic and Interventional Radiology, Eberhard Karls University, Tuebingen University Hospital, Tuebingen, Germany.
  • Medical Image and Data Analysis (MIDAS) Laboratory, University Hospital of Tübingen, Tübingen, Germany.
  • Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany.
  • Department of Urology, Stanford University, Stanford, CA, USA.
  • Lab for AI in Medicine, Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany.
  • Institute for AI in Medicine (IKIM), University Medicine Essen, Essen, Germany.
  • Department of Radiology, RSUP Dr Sardjito, Faculty of Medicine, Universitas Gadjah Mada, Yogyakarta, Indonesia.
  • Thoracic and Vascular Surgery Research Center, Namazi Hospital, Shiraz University of Medical Sciences, Shiraz, Iran.
  • Pediatric Pulmonology Institute, Dana Children's Hospital, Tel Aviv Sourasky University Medical Center (Ichilov), Tel Aviv, Israel.
  • Gray Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, Israel.
  • Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan.
  • Department of Artificial Intelligence, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan.
  • Department of Diagnostic Radiology, American University of Beirut, Beirut, Lebanon.
  • Department of Paediatrics, Sultan Ahmad Shah Medical Centre (SASMEC), International Islamic University Malaysia, Kuantan, Malaysia.
  • Department of Radiology, Sultan Ahmad Shah Medical Centre @IIUM, International Islamic University Malaysia, Kuantan, Malaysia.
  • Department of Neonatal Pediatrics, The Indus Hospital and Health Network, Karachi, Pakistan.
  • Department of Diagnostic Radiology, The Indus Hospital and Health Network, Karachi, Pakistan.
  • Department of Neurosurgery, Sidra Medicine, Doha, Qatar.
  • Department of Radiology, Sidra Medicine, Doha, Qatar.
  • Manager of Diagnostic Imaging Section, King Abdul-Aziz Medical City, Ministry of National Guard Health Affairs, Riyadh, Saudi Arabia.
  • Pediatric Radiology Consultant, King Abdullah Specialized Children Hospital, Riyadh, Saudi Arabia.
  • Department of Pediatrics, Faculty of Medical Sciences, University of Kragujevac, Kragujevac, Serbia.
  • Department of Surgery, Faculty of Medical Sciences, University of Kragujevac, Kragujevac, Serbia.

Abstract

Despite growing clinical adoption of artificial intelligence in radiology, fewer than one in five commercially available models are cleared for paediatric use. Existing systems are trained predominantly on adult data and generalize poorly to neonates, yet efficient strategies for repurposing them without data sharing or large-scale local data curation are lacking. Here we present an international retrospective study of neonatal chest radiographs from 30 neonatal intensive care units across 20 countries and territories, evaluating continual learning as a privacy-preserving approach to adapt a deep learning model for adult endotracheal tube assessment to neonatal care. Each hospital contributed 50 radiographs for sequential model retraining without centralized data pooling. Continual learning achieved lower anatomical landmark localization error (0.67 cm versus 1.29 cm for hospital-specific fine-tuning and 4.30 cm for adult-only models) at 29 of 30 sites, with improved detection of deep intubations at 27 of 30 sites. These findings demonstrate that privacy-preserving collaborative learning can address critical gaps in paediatric AI deployment.

MeSH

Privacy, Biomedical Engineering, Learning, Artificial Intelligence