A framework for falsifiable explanations of machine learning models with an application in computational pathology

David Schuhmacher, Stephanie Schörner, Claus Küpper, Frederik Großerüschkamp, Carlo Sternemann, Celine Lugnier, Anna-Lena Kraeft, Hendrik Jütte, Andrea Tannapfel, Anke Reinacher-Schick, Klaus Gerwert, Axel Mosig

Abstract: Highlights•We define an explanation of a machine learning model as a falsifiable hypothesis.•The explaining hypothesis involves a variable inferred by the machine learning model.•The hypothesis refers to the sample from which the input data originate.•Our proposed CompSegNet uses the hypothesis as a tool to model inductive bias.•Our framework connects inductive machine learning with deductive reasoning.