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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Guang, Togo, Ren, Ogawa, Takahiro, Haseyama, Miki
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929462021455872
author Li, Guang
Togo, Ren
Ogawa, Takahiro
Haseyama, Miki
author_facet Li, Guang
Togo, Ren
Ogawa, Takahiro
Haseyama, Miki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2211_00313
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle RGMIM: Region-Guided Masked Image Modeling for Learning Meaningful Representations from X-Ray Images
Li, Guang
Togo, Ren
Ogawa, Takahiro
Haseyama, Miki
Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
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.
title RGMIM: Region-Guided Masked Image Modeling for Learning Meaningful Representations from X-Ray Images
topic Computer Vision and Pattern Recognition
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2211.00313