A review of lightweight convolutional neural networks for ultrasound signal classification

Ultrasound signal processing plays an important role in medical image analysis. Embedded ultrasonography systems with low power consumption and high portability are suitable for disaster rescue, but due to the difficulty of ultrasonic signal recognition, operators need to have strong professional kn...

Full description

Saved in:
Bibliographic Details
Main Authors: Bokun Zhang, Zhengping Li, Yuwen Hao, Lijun Wang, Xiaoxue Li, Yuan Yao
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Physiology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphys.2025.1536542/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850155494086279168
author Bokun Zhang
Zhengping Li
Yuwen Hao
Lijun Wang
Xiaoxue Li
Yuan Yao
author_facet Bokun Zhang
Zhengping Li
Yuwen Hao
Lijun Wang
Xiaoxue Li
Yuan Yao
author_sort Bokun Zhang
collection DOAJ
description Ultrasound signal processing plays an important role in medical image analysis. Embedded ultrasonography systems with low power consumption and high portability are suitable for disaster rescue, but due to the difficulty of ultrasonic signal recognition, operators need to have strong professional knowledge, and it is not easy to deploy ultrasonography systems in areas with relatively weak infrastructures. In recent years, with the continuous development in the field of deep learning and artificial intelligence, lightweight convolutional neural networks have brought new opportunities for ultrasound signal processing. This paper focuses on investigating lightweight convolutional neural networks applied to ultrasound signal classification. Combined with the characteristics of ultrasound signals, this paper provides a detailed review of lightweight algorithms from two perspectives: model compression and operational optimization. Among them, model compression deals with the overall framework to reduce network redundancy, and the latter aims at the lightweight design of the basic operational module “convolution” in the network. The experimental results of some classical models and algorithms on the ImageNet dataset are summarized. Through the comprehensive analysis, we present some problems and provide an outlook on the future development of lightweight techniques for ultrasound signal classification.
format Article
id doaj-art-3e366bdd832b4088a2046429ece88e22
institution OA Journals
issn 1664-042X
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Physiology
spelling doaj-art-3e366bdd832b4088a2046429ece88e222025-08-20T02:24:54ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2025-04-011610.3389/fphys.2025.15365421536542A review of lightweight convolutional neural networks for ultrasound signal classificationBokun Zhang0Zhengping Li1Yuwen Hao2Lijun Wang3Xiaoxue Li4Yuan Yao5School of Information Science and Technology, North China University of Technology, Beijing, ChinaSchool of Information Science and Technology, North China University of Technology, Beijing, ChinaDisaster Medicine Research Center, Medical Innovation Research Division of the Chinese PLA General Hospital Beijing, China Beijing Key Laboratory of Disaster Medicine, Beijing, ChinaHangzhou Institute of Technology, Xidian University, Xi’an, ChinaHangzhou Institute of Technology, Xidian University, Xi’an, ChinaEmergency Department, 903rd Hospital of PLA Joint Logistic Support Force, Hangzhou, ChinaUltrasound signal processing plays an important role in medical image analysis. Embedded ultrasonography systems with low power consumption and high portability are suitable for disaster rescue, but due to the difficulty of ultrasonic signal recognition, operators need to have strong professional knowledge, and it is not easy to deploy ultrasonography systems in areas with relatively weak infrastructures. In recent years, with the continuous development in the field of deep learning and artificial intelligence, lightweight convolutional neural networks have brought new opportunities for ultrasound signal processing. This paper focuses on investigating lightweight convolutional neural networks applied to ultrasound signal classification. Combined with the characteristics of ultrasound signals, this paper provides a detailed review of lightweight algorithms from two perspectives: model compression and operational optimization. Among them, model compression deals with the overall framework to reduce network redundancy, and the latter aims at the lightweight design of the basic operational module “convolution” in the network. The experimental results of some classical models and algorithms on the ImageNet dataset are summarized. Through the comprehensive analysis, we present some problems and provide an outlook on the future development of lightweight techniques for ultrasound signal classification.https://www.frontiersin.org/articles/10.3389/fphys.2025.1536542/fullultrasoundsignal classificationlightweight technologymodel compressionoptimization of lightweight networkconvolutional neural network
spellingShingle Bokun Zhang
Zhengping Li
Yuwen Hao
Lijun Wang
Xiaoxue Li
Yuan Yao
A review of lightweight convolutional neural networks for ultrasound signal classification
Frontiers in Physiology
ultrasound
signal classification
lightweight technology
model compression
optimization of lightweight network
convolutional neural network
title A review of lightweight convolutional neural networks for ultrasound signal classification
title_full A review of lightweight convolutional neural networks for ultrasound signal classification
title_fullStr A review of lightweight convolutional neural networks for ultrasound signal classification
title_full_unstemmed A review of lightweight convolutional neural networks for ultrasound signal classification
title_short A review of lightweight convolutional neural networks for ultrasound signal classification
title_sort review of lightweight convolutional neural networks for ultrasound signal classification
topic ultrasound
signal classification
lightweight technology
model compression
optimization of lightweight network
convolutional neural network
url https://www.frontiersin.org/articles/10.3389/fphys.2025.1536542/full
work_keys_str_mv AT bokunzhang areviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT zhengpingli areviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT yuwenhao areviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT lijunwang areviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT xiaoxueli areviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT yuanyao areviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT bokunzhang reviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT zhengpingli reviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT yuwenhao reviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT lijunwang reviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT xiaoxueli reviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification
AT yuanyao reviewoflightweightconvolutionalneuralnetworksforultrasoundsignalclassification