Fine-Grained Self-Supervised Learning with Jigsaw Puzzles for Medical Image Classification

TL;DR

This paper introduces FG-SSL, a self-supervised learning approach using hierarchical Jigsaw puzzles to improve fine-grained lesion classification in medical images, outperforming existing methods on multiple datasets.

Contribution

The paper proposes a novel hierarchical self-supervised learning method that enhances fine-grained feature extraction without requiring negative samples or asymmetric models.

Findings

Outperforms state-of-the-art on ISIC2018, APTOS2019, ISIC2017 datasets.

Does not rely on negative sampling or asymmetric models.

Effective in classifying subtle medical image lesions.

Abstract

Classifying fine-grained lesions is challenging due to minor and subtle differences in medical images. This is because learning features of fine-grained lesions with highly minor differences is very difficult in training deep neural networks. Therefore, in this paper, we introduce Fine-Grained Self-Supervised Learning(FG-SSL) method for classifying subtle lesions in medical images. The proposed method progressively learns the model through hierarchical block such that the cross-correlation between the fine-grained Jigsaw puzzle and regularized original images is close to the identity matrix. We also apply hierarchical block for progressive fine-grained learning, which extracts different information in each step, to supervised learning for discovering subtle differences. Our method does not require an asymmetric model, nor does a negative sampling strategy, and is not sensitive to batch size. We evaluate the proposed fine-grained self-supervised learning method on comprehensive experiments using various medical image recognition datasets. In our experiments, the proposed method performs favorably compared to existing state-of-the-art approaches on the widely-used ISIC2018, APTOS2019, and ISIC2017 datasets.