Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise

TL;DR

This paper presents a two-phase active label refinement method combining learning with noisy labels and active learning to improve robustness and dataset quality in imbalanced, noisy medical image classification tasks.

Contribution

It introduces a novel variance of gradients approach within LNL and actively refines labels, addressing class imbalance and noise simultaneously.

Findings

Outperforms previous methods in handling class imbalance and noise.

Effectively relabels important incorrect labels within limited annotation budgets.

Demonstrates superior robustness on imbalanced noisy medical datasets.

Abstract

The robustness of supervised deep learning-based medical image classification is significantly undermined by label noise. Although several methods have been proposed to enhance classification performance in the presence of noisy labels, they face some challenges: 1) a struggle with class-imbalanced datasets, leading to the frequent overlooking of minority classes as noisy samples; 2) a singular focus on maximizing performance using noisy datasets, without incorporating experts-in-the-loop for actively cleaning the noisy labels. To mitigate these challenges, we propose a two-phase approach that combines Learning with Noisy Labels (LNL) and active learning. This approach not only improves the robustness of medical image classification in the presence of noisy labels, but also iteratively improves the quality of the dataset by relabeling the important incorrect labels, under a limited annotation budget. Furthermore, we introduce a novel Variance of Gradients approach in LNL phase, which complements the loss-based sample selection by also sampling under-represented samples. Using two imbalanced noisy medical classification datasets, we demonstrate that that our proposed technique is superior to its predecessors at handling class imbalance by not misidentifying clean samples from minority classes as mostly noisy samples.