RGMIM: Region-Guided Masked Image Modeling for Learning Meaningful Representations from X-Ray Images

TL;DR

RGMIM introduces a region-guided masked image modeling approach that leverages organ masks to improve representation learning from X-ray images, especially in limited data scenarios, leading to high lung disease detection accuracy.

Contribution

The paper presents a novel masking strategy using organ masks for self-supervised learning on X-ray images, enhancing performance with small datasets.

Findings

Achieves 0.962 lung disease detection accuracy with full training data.

Significantly improves performance with only 5-10% of training data.

Outperforms state-of-the-art self-supervised methods in experiments.

Abstract

In this study, we propose a novel method called region-guided masked image modeling (RGMIM) for learning meaningful representations from X-ray images. Our method adopts a new masking strategy that utilizes organ mask information to identify valid regions for learning more meaningful representations. We conduct quantitative evaluations on an open lung X-ray image dataset as well as masking ratio hyperparameter studies. When using the entire training set, RGMIM outperformed other comparable methods, achieving a 0.962 lung disease detection accuracy. Specifically, RGMIM significantly improved performance in small data volumes, such as 5% and 10% of the training set compared to other methods. RGMIM can mask more valid regions, facilitating the learning of discriminative representations and the subsequent high-accuracy lung disease detection. RGMIM outperforms other state-of-the-art self-supervised learning methods in experiments, particularly when limited training data is used.