Trustworthy and Self-explanatory Artificial Intelligence for the Classification of Non-Hodgkin Lymphoma by Immunophenotype

Abstract

Diagnostic immunophenotyping of malignant non-Hodgkin-lymphoma (NHL) by multiparameter flow cytometry (MFC) relies on highly trained physicians. Artificial intelligence (AI) systems have been proposed for this diagnostic task, often requiring more learning examples than are usually available. In contrast, Flow XAI has reduced the number of needed learning data by a factor of 100. It selects and reports diagnostically relevant cell populations and expression patterns in a discernable and clear manner so that immunophenotyping experts can understand the rationale behind the AI’s decisions. A self-organized and unsupervised view of the complex multidimensional MFC data provides information about the immunophenotypic structures in the data. Flow XAIintegrates human expert knowledge into its decision process. It reports a self-competence estimation for each case and delivers human-understandable explanations for its decisions. Flow XAI outperformed comparable AI systems in qualitative and quantitative assessments. This self-explanatory AI system can be used for real-world AI lymphoma immunophenotyping.