Improving Explainability of Image Classification in Scenarios with Class Overlap: Application to COVID-19 and Pneumonia

TL;DR

This paper introduces a method using binary expert networks to improve explainability and localization in image classification tasks with overlapping classes, such as COVID-19 and pneumonia, without needing explicit localization training.

Contribution

The proposed approach enhances explainability in overlapping class scenarios by improving localization through binary expert networks, addressing a key challenge in medical image classification.

Findings

Improved localization accuracy in overlapping class scenarios

Effective in COVID-19 and pneumonia image classification

No need for explicit localization labels during training

Abstract

Trust in predictions made by machine learning models is increased if the model generalizes well on previously unseen samples and when inference is accompanied by cogent explanations of the reasoning behind predictions. In the image classification domain, generalization can be assessed through accuracy, sensitivity, and specificity. Explainability can be assessed by how well the model localizes the object of interest within an image. However, both generalization and explainability through localization are degraded in scenarios with significant overlap between classes. We propose a method based on binary expert networks that enhances the explainability of image classifications through better localization by mitigating the model uncertainty induced by class overlap. Our technique performs discriminative localization on images that contain features with significant class overlap, without explicitly training for localization. Our method is particularly promising in real-world class overlap scenarios, such as COVID-19 and pneumonia, where expertly labeled data for localization is not readily available. This can be useful for early, rapid, and trustworthy screening for COVID-19.