A Self supervised learning framework for imbalanced medical imaging datasets

2026-04-02

AI Summary

This work addresses the challenges of scarce annotations and severe class imbalance in medical image analysis by proposing an Asymmetric Multi-Image Multi-View (AMIMV) framework based on self-supervised learning. The method constructs multi-view sample pairs through a novel asymmetric augmentation strategy and systematically evaluates the robustness of various self-supervised algorithms under diverse long-tailed distributions. Extensive experiments across 11 medical imaging datasets, including MedMNIST, demonstrate that the proposed approach significantly improves classification performance, achieving accuracy gains of 4.25%, 1.88%, and 3.10% on RetinaMNIST, TissueMNIST, and DermaMNIST, respectively. These results validate the effectiveness and superiority of AMIMV in scenarios with limited labeled data and extreme class imbalance.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Medical and Biological Imaging
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Two problems often plague medical imaging analysis: 1) Non-availability of large quantities of labeled training data, and 2) Dealing with imbalanced data, i.e., abundant data are available for frequent classes, whereas data are highly limited for the rare class. Self supervised learning (SSL) methods have been proposed to deal with the first problem to a certain extent, but the issue of investigating the robustness of SSL to imbalanced data has rarely been addressed in the domain of medical image classification. In this work, we make the following contributions: 1) The MIMV method proposed by us in an earlier work is extended with a new augmentation strategy to construct asymmetric multi-image, multi-view (AMIMV) pairs to address both data scarcity and dataset imbalance in medical image classification. 2) We carry out a data analysis to evaluate the robustness of AMIMV under varying degrees of class imbalance in medical imaging . 3) We evaluate eight representative SSL methods in 11 medical imaging datasets (MedMNIST) under long-tailed distributions and limited supervision. Our experimental results on the MedMNIST dataset show an improvement of 4.25% on retinaMNIST, 1.88% on tissueMNIST, and 3.1% on DermaMNIST.

Problem

• self-supervised learning
• imbalanced data
• medical imaging
• class imbalance
• limited labeled data

Innovation

• self-supervised learning
• class imbalance
• medical imaging
• asymmetric multi-image multi-view
• data augmentation