A systematic review of generalization research in medical image classification

Sarah Matta, Mathieu Lamard, Philippe Zhang, Alexandre Le Guilcher, Laurent Borderie, Béatrice Cochener, Gwenolé Quellec

Abstract: Highlights•A survey paper on recent development of generalization methods for medical image classification.•A novel taxonomy based on the type of medical shift, namely covariate shift and concept shift.•A presentation of public medical datasets and open source libraries to enhance future research in this field.•A presentation of best practices for implementing generalization techniques in research.•A discussion on future challenges and envisioned future developments.