Developing Explainable Machine Learning Model using Augmented Concept Activation Vector

TL;DR

This paper introduces a method to quantify the influence of human-understandable high-level concepts on machine learning decisions, enhancing explainability especially in imbalanced datasets like medical imaging.

Contribution

It presents a novel approach to measure and isolate the impact of high-level concepts on model decisions, applied to fundus images for medical diagnosis.

Findings

Quantitatively measured the impact of radiomic patterns on model decisions.

Identified prevalent high-level concepts in imbalanced datasets.

Enhanced interpretability of machine learning models in medical imaging.

Abstract

Machine learning models use high dimensional feature spaces to map their inputs to the corresponding class labels. However, these features often do not have a one-to-one correspondence with physical concepts understandable by humans, which hinders the ability to provide a meaningful explanation for the decisions made by these models. We propose a method for measuring the correlation between high-level concepts and the decisions made by a machine learning model. Our method can isolate the impact of a given high-level concept and accurately measure it quantitatively. Additionally, this study aims to determine the prevalence of frequent patterns in machine learning models, which often occur in imbalanced datasets. We have successfully applied the proposed method to fundus images and managed to quantitatively measure the impact of radiomic patterns on the model decisions.