Visual Evaluative AI: A Hypothesis-Driven Tool with Concept-Based Explanations and Weight of Evidence
This addresses the need for transparent AI tools in medical domains like dermatology, though it appears incremental as it builds on existing concept-based explanation approaches.
The paper tackles the problem of providing interpretable evidence for decision-making in image analysis by introducing Visual Evaluative AI, a tool that identifies human concepts in images and calculates Weight of Evidence for hypotheses, with evaluation in skin cancer diagnosis showing effectiveness across explanation methods.
This paper presents Visual Evaluative AI, a decision aid that provides positive and negative evidence from image data for a given hypothesis. This tool finds high-level human concepts in an image and generates the Weight of Evidence (WoE) for each hypothesis in the decision-making process. We apply and evaluate this tool in the skin cancer domain by building a web-based application that allows users to upload a dermatoscopic image, select a hypothesis and analyse their decisions by evaluating the provided evidence. Further, we demonstrate the effectiveness of Visual Evaluative AI on different concept-based explanation approaches.