Visual Evaluative AI: A Hypothesis-Driven Tool with Concept-Based Explanations and Weight of Evidence

TL;DR

This paper introduces Visual Evaluative AI, a tool that offers concept-based explanations and evidence evaluation for image-based decision-making, demonstrated in skin cancer diagnosis.

Contribution

It presents a novel decision aid that generates high-level concept evidence and Weight of Evidence for hypotheses in image analysis tasks.

Findings

Effective in skin cancer image analysis

Supports multiple concept-based explanation methods

Provides interpretable evidence for decision support

Abstract

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.