VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zelong, Tieu, Andrew, Patel, Nikhil, Soultanidis, Georgios, Deyer, Louisa, Wang, Ying, Huver, Sean, Zhou, Alexander, Mei, Yunhao, Fayad, Zahi A., Deyer, Timothy, Mei, Xueyan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912192776896512
author Liu, Zelong
Tieu, Andrew
Patel, Nikhil
Soultanidis, Georgios
Deyer, Louisa
Wang, Ying
Huver, Sean
Zhou, Alexander
Mei, Yunhao
Fayad, Zahi A.
Deyer, Timothy
Mei, Xueyan
author_facet Liu, Zelong
Tieu, Andrew
Patel, Nikhil
Soultanidis, Georgios
Deyer, Louisa
Wang, Ying
Huver, Sean
Zhou, Alexander
Mei, Yunhao
Fayad, Zahi A.
Deyer, Timothy
Mei, Xueyan
contents Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of generalizability, and the necessity to incorporate multi-modal data effectively. A foundation model, which is a large-scale pre-trained AI model, offers a versatile base that can be adapted to a variety of specific tasks and contexts. Here, we present VIsualization and Segmentation Masked AutoEncoder (VIS-MAE), novel model weights specifically designed for medical imaging. Specifically, VIS-MAE is trained on a dataset of 2.5 million unlabeled images from various modalities (CT, MR, PET,X-rays, and ultrasound), using self-supervised learning techniques. It is then adapted to classification and segmentation tasks using explicit labels. VIS-MAE has high label efficiency, outperforming several benchmark models in both in-domain and out-of-domain applications. In addition, VIS-MAE has improved label efficiency as it can achieve similar performance to other models with a reduced amount of labeled training data (50% or 80%) compared to other pre-trained weights. VIS-MAE represents a significant advancement in medical imaging AI, offering a generalizable and robust solution for improving segmentation and classification tasks while reducing the data annotation workload. The source code of this work is available at https://github.com/lzl199704/VIS-MAE.
format Preprint
id arxiv_https___arxiv_org_abs_2402_01034
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification
Liu, Zelong
Tieu, Andrew
Patel, Nikhil
Soultanidis, Georgios
Deyer, Louisa
Wang, Ying
Huver, Sean
Zhou, Alexander
Mei, Yunhao
Fayad, Zahi A.
Deyer, Timothy
Mei, Xueyan
Image and Video Processing
Computer Vision and Pattern Recognition
Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of generalizability, and the necessity to incorporate multi-modal data effectively. A foundation model, which is a large-scale pre-trained AI model, offers a versatile base that can be adapted to a variety of specific tasks and contexts. Here, we present VIsualization and Segmentation Masked AutoEncoder (VIS-MAE), novel model weights specifically designed for medical imaging. Specifically, VIS-MAE is trained on a dataset of 2.5 million unlabeled images from various modalities (CT, MR, PET,X-rays, and ultrasound), using self-supervised learning techniques. It is then adapted to classification and segmentation tasks using explicit labels. VIS-MAE has high label efficiency, outperforming several benchmark models in both in-domain and out-of-domain applications. In addition, VIS-MAE has improved label efficiency as it can achieve similar performance to other models with a reduced amount of labeled training data (50% or 80%) compared to other pre-trained weights. VIS-MAE represents a significant advancement in medical imaging AI, offering a generalizable and robust solution for improving segmentation and classification tasks while reducing the data annotation workload. The source code of this work is available at https://github.com/lzl199704/VIS-MAE.
title VIS-MAE: An Efficient Self-supervised Learning Approach on Medical Image Segmentation and Classification
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.01034