Deep learning in medical image analysis: introduction to underlying principles and reviewer guide using diagnostic case studies in paediatrics
Deep learning, a subset of artificial intelligence, has gained attention in recent years for its ability to achieve human level performance in medical image analysis. As deep learning is increasingly being studied in medical image analysis, it is essential that clinicians are familiar with its underlying principles, strengths, and possible pitfalls in their evaluation. This article aims to clarify deep learning techniques applied in medical image analysis and to help frontline clinicians understand how to read and appraise studies about this new and rapidly advancing technology. While image analysis using deep learning has the potential to enhance the diagnosis of various medical conditions, clinicians, policy makers, and patients should exercise caution when evaluating the available evidence.
Authors
- François Simon (ORCID: https://orcid.org/0000-0003-0082-538X)
- Laureline Berteloot (ORCID: https://orcid.org/0000-0001-9681-3142)
- Yasaman Vali (ORCID: https://orcid.org/0000-0001-7002-118X)
- Peter Bossuyt (ORCID: https://orcid.org/0000-0003-4027-7365)
- David Drummond (ORCID: https://orcid.org/0000-0002-7324-4992)
- Moritz Einfalt
- Emmanuel Delmas
- Héloïse Torchin (ORCID: https://orcid.org/0000-0003-4699-5384)
- Jérémie F. Cohen (ORCID: https://orcid.org/0000-0003-3572-8985)
- David Eigen
- Pauline Scherdel (ORCID: https://orcid.org/0000-0003-4517-9430)
- Constance Dubois (ORCID: https://orcid.org/0000-0002-8479-8309)
- Isabelle Bloch A (ORCID: https://orcid.org/0000-0002-6984-1532)
- Clara Lemaçon
Institutions
- Télécom Paris (FR)
- Hôpital Necker-Enfants Malades (FR)
- Centre National de la Recherche Scientifique (FR)
- Inserm (FR)
- Pontificia Universidad Católica de Chile (CL)
- Université Paris Cité (FR)
- Sorbonne Université (FR)
- Sorbonne Paris Cité (FR)
- Centre de Recherche des Cordeliers (FR)
- Centre Hospitalier Universitaire de Tours (FR)
- Assistance Publique – Hôpitaux de Paris (FR)
- Maternité Port Royal (FR)
- CHU Dijon Bourgogne (FR)
- Hôpital Robert-Debré (FR)
- Hôpital Saint-Louis (FR)
- Amsterdam University Medical Centers (NL)
- Laboratoire Traitement et Communication de l’Information (FR)
- Centre de Recherche Épidémiologie et Statistique (FR)
- Centre d’Investigation Clinique 1436 (FR)
- University of Amsterdam (NL)
- Amsterdam UMC Location Vrije Universiteit Amsterdam (NL)
Publication Details
- Journal
- BMJ
- Published
- 2024-11-21
- DOI
- https://doi.org/10.1136/bmj-2023-076703
- Citations
- 8
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.96