A Comprehensive Deep Learning Framework for Microwave Stroke Classification: Combining Signal Analysis, Clinical Variables, and Antenna System Measurements

Microwave signal-based binary classification for detecting the presence of stroke presents a promising avenue for cost-effective and portable diagnosis. However, implementing this technology in real-world settings remains challenging due to difficulties in accurately modeling wave scattering, which...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Yuan, Phawis Thammasorn, Lingxiao Wang, Shih Mo
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10907859/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849731380991229952
author Wei Yuan
Phawis Thammasorn
Lingxiao Wang
Shih Mo
author_facet Wei Yuan
Phawis Thammasorn
Lingxiao Wang
Shih Mo
author_sort Wei Yuan
collection DOAJ
description Microwave signal-based binary classification for detecting the presence of stroke presents a promising avenue for cost-effective and portable diagnosis. However, implementing this technology in real-world settings remains challenging due to difficulties in accurately modeling wave scattering, which often leads to suboptimal performance of classification systems. Our proposed deep learning framework addresses this issue by bypassing complex modeling tasks and directly extracting stroke signatures from wavelet-filtered microwave signals, combined with clinical variables and antenna measurements. Experiments conducted with total of 431 real-world stroke patients demonstrate that our system significantly outperforms recent classification approaches achieving 76.19% accuracy. Furthermore, our approach shows comparable performance to magnetic resonance imaging (MRI) based deep learning classification, in scenarios with limited imaging data. These results not only highlight the potential of microwave imaging (MWI) as a critical diagnostic tool but also suggest that MWI devices could become a viable option for clinical stroke diagnosis in the near future.
format Article
id doaj-art-49d475d22e304cb28e43445ff4300995
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-49d475d22e304cb28e43445ff43009952025-08-20T03:08:35ZengIEEEIEEE Access2169-35362025-01-0113399353994910.1109/ACCESS.2025.354655810907859A Comprehensive Deep Learning Framework for Microwave Stroke Classification: Combining Signal Analysis, Clinical Variables, and Antenna System MeasurementsWei Yuan0Phawis Thammasorn1https://orcid.org/0000-0002-1592-9766Lingxiao Wang2Shih Mo3Chengdu Pidu District People’s Hospital, Chengdu, ChinaTiposi, Milpitas, CA, USATiposi, Milpitas, CA, USATiposi, Milpitas, CA, USAMicrowave signal-based binary classification for detecting the presence of stroke presents a promising avenue for cost-effective and portable diagnosis. However, implementing this technology in real-world settings remains challenging due to difficulties in accurately modeling wave scattering, which often leads to suboptimal performance of classification systems. Our proposed deep learning framework addresses this issue by bypassing complex modeling tasks and directly extracting stroke signatures from wavelet-filtered microwave signals, combined with clinical variables and antenna measurements. Experiments conducted with total of 431 real-world stroke patients demonstrate that our system significantly outperforms recent classification approaches achieving 76.19% accuracy. Furthermore, our approach shows comparable performance to magnetic resonance imaging (MRI) based deep learning classification, in scenarios with limited imaging data. These results not only highlight the potential of microwave imaging (MWI) as a critical diagnostic tool but also suggest that MWI devices could become a viable option for clinical stroke diagnosis in the near future.https://ieeexplore.ieee.org/document/10907859/Deep learningmicrowave signal processingstroke classificationhealth caremedical image analysis
spellingShingle Wei Yuan
Phawis Thammasorn
Lingxiao Wang
Shih Mo
A Comprehensive Deep Learning Framework for Microwave Stroke Classification: Combining Signal Analysis, Clinical Variables, and Antenna System Measurements
IEEE Access
Deep learning
microwave signal processing
stroke classification
health care
medical image analysis
title A Comprehensive Deep Learning Framework for Microwave Stroke Classification: Combining Signal Analysis, Clinical Variables, and Antenna System Measurements
title_full A Comprehensive Deep Learning Framework for Microwave Stroke Classification: Combining Signal Analysis, Clinical Variables, and Antenna System Measurements
title_fullStr A Comprehensive Deep Learning Framework for Microwave Stroke Classification: Combining Signal Analysis, Clinical Variables, and Antenna System Measurements
title_full_unstemmed A Comprehensive Deep Learning Framework for Microwave Stroke Classification: Combining Signal Analysis, Clinical Variables, and Antenna System Measurements
title_short A Comprehensive Deep Learning Framework for Microwave Stroke Classification: Combining Signal Analysis, Clinical Variables, and Antenna System Measurements
title_sort comprehensive deep learning framework for microwave stroke classification combining signal analysis clinical variables and antenna system measurements
topic Deep learning
microwave signal processing
stroke classification
health care
medical image analysis
url https://ieeexplore.ieee.org/document/10907859/
work_keys_str_mv AT weiyuan acomprehensivedeeplearningframeworkformicrowavestrokeclassificationcombiningsignalanalysisclinicalvariablesandantennasystemmeasurements
AT phawisthammasorn acomprehensivedeeplearningframeworkformicrowavestrokeclassificationcombiningsignalanalysisclinicalvariablesandantennasystemmeasurements
AT lingxiaowang acomprehensivedeeplearningframeworkformicrowavestrokeclassificationcombiningsignalanalysisclinicalvariablesandantennasystemmeasurements
AT shihmo acomprehensivedeeplearningframeworkformicrowavestrokeclassificationcombiningsignalanalysisclinicalvariablesandantennasystemmeasurements
AT weiyuan comprehensivedeeplearningframeworkformicrowavestrokeclassificationcombiningsignalanalysisclinicalvariablesandantennasystemmeasurements
AT phawisthammasorn comprehensivedeeplearningframeworkformicrowavestrokeclassificationcombiningsignalanalysisclinicalvariablesandantennasystemmeasurements
AT lingxiaowang comprehensivedeeplearningframeworkformicrowavestrokeclassificationcombiningsignalanalysisclinicalvariablesandantennasystemmeasurements
AT shihmo comprehensivedeeplearningframeworkformicrowavestrokeclassificationcombiningsignalanalysisclinicalvariablesandantennasystemmeasurements