Investigating the Usability of XAI in AI-based Image Classification

This paper investigates the usability of XAI (Explainable Artificial Intelligence) in AI-based image classification, particularly for non-experts like medical professionals. XAI provides the user of AI systems with an explanation for a particular decision. But the usability of such explanations remains an open point of discussion. The investigation highlights that there is a need for integrating explainability in the design of the classification approach. This paper will present an approach to classify the parts of an object separately and then utilize a white box model (decision tree) for the final classification. This is enriched by additional information, achieving understandability of the classification.