Entropy-Guided Self-Supervised Learning for Medical Image Classification

TL;DR

This paper presents an entropy-guided self-supervised learning framework combining transfer learning and ensemble methods to improve medical image classification accuracy and robustness across multiple datasets.

Contribution

It introduces a novel ensemble approach using models pre-trained with entropy-guided Masked Autoencoders and ImageNet, achieving state-of-the-art results in medical imaging tasks.

Findings

MAE pre-training enhances domain-specific feature learning.

Ensemble strategy outperforms individual models and existing methods.

Approach demonstrates robustness across diverse medical datasets.

Abstract

Accurate and robust medical image classification is paramount for early disease diagnosis and treatment planning. However, challenges such as limited annotated data, high intra-class variability, and subtle inter-class differences often hinder the performance of deep learning models. This paper introduces a synergistic deep learning framework that leverages the strengths of self-supervised learning and transfer learning for enhanced medical image classification. Our approach employs two distinct ConvNeXt-Tiny models: one pre-trained on a large-scale natural image dataset (ImageNet) and another pre-trained using an entropy-guided Masked Autoencoder (MAE) on the target medical dataset. Both models are then fine-tuned on specific medical image classification tasks. A final ensemble strategy, based on averaging predicted probabilities, is utilized to combine the complementary insights from these two models. Rigorous experimental validation across four diverse medical imaging datasets (Breast Ultrasound Images (BUSI), International Skin Imaging Collaboration (ISIC) 2018, Kvasir, and COVID) demonstrates the superior performance and robustness of our ensemble approach. The MAE pre-training significantly improves feature learning on domain-specific data, while the ImageNet pre-training provides strong generalizable features. The ensemble consistently achieves state-of-the-art results, outperforming individual models and existing methods, highlighting the efficacy of combining diverse pre-training strategies for challenging medical image analysis.