The importance of multi-modal imaging and clinical information for humans and AI-based algorithms to classify breast masses (INSPiRED 003): an international, multicenter analysis.

André PfobChris Sidey-GibbonsRichard G BarrVolker DudaZaher AlwafaiCorinne BalleyguierDirk-André ClevertSarah FastnerChristina GomezManuela GoncaloInes GruberMarkus HahnAndré HennigsPanagiotis KapetasSheng-Chieh LuJuliane NeesRalf OhlingerFabian RiedelMatthieu RuttenBenedikt SchaefgenMaximilian SchuesslerAnne StieberRiku TogawaMitsuhiro TozakiSebastian WojcinskiCai XuGeraldine RauchJoerg HeilMichael Golatta

Published in: European radiology (2022)

• The performance of humans and AI-based algorithms improves with multi-modal information. • Multimodal AI-based algorithms do not necessarily outperform expert humans. • Unimodal AI-based algorithms do not represent optimal performance to classify breast masses.

Keyphrases

machine learning
artificial intelligence
deep learning
health information
high resolution
contrast enhanced
pain management
clinical trial
cross sectional
mass spectrometry
social media
photodynamic therapy