Masked Modeling-Based Ultrasound Image Classification via Self-Supervised Learning

Recently, deep learning-based methods have emerged as the preferred approach for ultrasound data analysis. However, these methods often require large-scale annotated datasets for training deep models, which are not readily available in practical scenarios. Additionally, the presence of speckle noise...

Full description

Saved in:
Bibliographic Details
Published in:IEEE open journal of engineering in medicine and biology 2024-01, Vol.5, p.226-237
Main Authors: Xu, Kele, You, Kang, Zhu, Boqing, Feng, Ming, Feng, Dawei, Yang, Cheng
Format: Article
Language:English
Subjects:
Annotations
Classification
Data analysis
Data mining
Data models
Datasets
Deep learning
Feature extraction
Image classification
Imaging
masked modeling
Masking
Modelling
Pre-training
self-supervised
Self-supervised learning
Task analysis
Training
Ultrasonic imaging
Ultrasonic testing
Ultrasound
ultrasound image
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, deep learning-based methods have emerged as the preferred approach for ultrasound data analysis. However, these methods often require large-scale annotated datasets for training deep models, which are not readily available in practical scenarios. Additionally, the presence of speckle noise and other imaging artifacts can introduce numerous hard examples for ultrasound data classification. In this paper, drawing inspiration from self-supervised learning techniques, we present a pre-training method based on mask modeling specifically designed for ultrasound data. Our study investigates three different mask modeling strategies: random masking, vertical masking, and horizontal masking. By employing these strategies, our pre-training approach aims to predict the masked portion of the ultrasound images. Notably, our method does not rely on externally labeled data, allowing us to extract representative features without the need for human annotation. Consequently, we can leverage unlabeled datasets for pre-training. Furthermore, to address the challenges posed by hard samples in ultrasound data, we propose a novel hard sample mining strategy. To evaluate the effectiveness of our proposed method, we conduct experiments on two datasets. The experimental results demonstrate that our approach outperforms other state-of-the-art methods in ultrasound image classification. This indicates the superiority of our pre-training method and its ability to extract discriminative features from ultrasound data, even in the presence of hard examples.
ISSN:2644-1276
2644-1276
DOI:10.1109/OJEMB.2024.3374966