Imbalanced Classification in Medical Imaging via Regrouping

TL;DR

This paper introduces a novel approach for imbalanced medical image classification by regrouping majority classes into smaller classes, transforming the problem into balanced multiclass classification, which improves performance.

Contribution

The paper presents a new regrouping strategy that differs from existing loss reweighting and resampling methods, offering a natural solution to imbalanced classification.

Findings

Significant boost in average precision (AUPRC) on medical image datasets.

Regrouping approach outperforms traditional reweighting and resampling methods.

Method effectively addresses class imbalance in medical imaging tasks.

Abstract

We propose performing imbalanced classification by regrouping majority classes into small classes so that we turn the problem into balanced multiclass classification. This new idea is dramatically different from popular loss reweighting and class resampling methods. Our preliminary result on imbalanced medical image classification shows that this natural idea can substantially boost the classification performance as measured by average precision (approximately area-under-the-precision-recall-curve, or AUPRC), which is more appropriate for evaluating imbalanced classification than other metrics such as balanced accuracy.