Highly Efficient Representation and Active Learning Framework and Its Application to Imbalanced Medical Image Classification

TL;DR

This paper introduces a highly data-efficient active learning framework combining unsupervised CNN representation learning and Gaussian Processes, effectively addressing class imbalance in medical image classification tasks.

Contribution

The paper presents a novel framework that integrates unsupervised CNN features with Gaussian Processes for active learning, improving data and label efficiency in imbalanced medical image classification.

Findings

Achieves comparable accuracy with only 10% labeled data

Effectively handles class imbalance in medical images

Demonstrates success on COVID-19 and colonoscopy datasets

Abstract

We propose a highly data-efficient active learning framework for image classification. Our novel framework combines: (1) unsupervised representation learning of a Convolutional Neural Network and (2) the Gaussian Process (GP) method, in sequence to achieve highly data and label efficient classifications. Moreover, both elements are less sensitive to the prevalent and challenging class imbalance issue, thanks to the (1) feature learned without labels and (2) the Bayesian nature of GP. The GP-provided uncertainty estimates enable active learning by ranking samples based on the uncertainty and selectively labeling samples showing higher uncertainty. We apply this novel combination to the severely imbalanced case of COVID-19 chest X-ray classification and the Nerthus colonoscopy classification. We demonstrate that only . 10% of the labeled data is needed to reach the accuracy from training all available labels. We also applied our model architecture and proposed framework to a broader class of datasets with expected success.