CURVETE: Curriculum Learning and Progressive Self-supervised Training for Medical Image Classification

2025-10-27

AI Summary

To address the scarcity of high-quality annotated data and severe class imbalance in medical image classification, this paper proposes a novel framework integrating curriculum learning with progressive self-supervised training. Methodologically, it introduces (1) a curriculum learning mechanism based on sample decomposition granularity to dynamically schedule the learning order of easy versus hard samples, and (2) a class decomposition strategy tailored to downstream tasks to mitigate long-tailed distribution and enhance discriminative capability for minority classes. Evaluated on brain tumor MRI, digital knee X-ray, and Mini-DDSM mammography datasets using ResNet-50 and DenseNet-121 backbones, the framework achieves classification accuracies of 96.60%, 80.36%, and 93.35%, respectively—substantially outperforming state-of-the-art methods. These results demonstrate superior generalization and robustness under limited supervision and imbalanced class distributions.

Technology Category

• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Identifying high-quality and easily accessible annotated samples poses a notable challenge in medical image analysis. Transfer learning techniques, leveraging pre-training data, offer a flexible solution to this issue. However, the impact of fine-tuning diminishes when the dataset exhibits an irregular distribution between classes. This paper introduces a novel deep convolutional neural network, named Curriculum Learning and Progressive Self-supervised Training (CURVETE). CURVETE addresses challenges related to limited samples, enhances model generalisability, and improves overall classification performance. It achieves this by employing a curriculum learning strategy based on the granularity of sample decomposition during the training of generic unlabelled samples. Moreover, CURVETE address the challenge of irregular class distribution by incorporating a class decomposition approach in the downstream task. The proposed method undergoes evaluation on three distinct medical image datasets: brain tumour, digital knee x-ray, and Mini-DDSM datasets. We investigate the classification performance using a generic self-supervised sample decomposition approach with and without the curriculum learning component in training the pretext task. Experimental results demonstrate that the CURVETE model achieves superior performance on test sets with an accuracy of 96.60% on the brain tumour dataset, 75.60% on the digital knee x-ray dataset, and 93.35% on the Mini-DDSM dataset using the baseline ResNet-50. Furthermore, with the baseline DenseNet-121, it achieved accuracies of 95.77%, 80.36%, and 93.22% on the brain tumour, digital knee x-ray, and Mini-DDSM datasets, respectively, outperforming other training strategies.

Problem

• Addresses limited annotated medical image samples
• Handles irregular class distribution in datasets
• Improves classification performance via curriculum learning

Innovation

• Curriculum learning with granular sample decomposition
• Progressive self-supervised training for limited samples
• Class decomposition approach for irregular distribution