Cover Image

Deep learning-based microcirculation performance classification using multispectral photoacoustic technology

Investigation of microcirculation is the key to diagnose circulatory dysfunction. Tissue circulation monitoring is a crucial part of the care of patients with severe chronic illnesses because it affects oxygen delivery to tissue. Recent technology, such as hyperspectral imaging, has allowed visualiz...

Full description

Saved in:
Bibliographic Details
Main Authors: Chua, Hui Ling, Huong, Audrey
Format: Article
Language:English
Published: 2024
Subjects:
RC Internal medicine
Online Access:http://eprints.uthm.edu.my/11981/1/J17621_ba3f0e8aacb3c8b364a0f1afb7fc1cdf.pdf
http://eprints.uthm.edu.my/11981/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uthm.eprints.11981
record_format eprints
spelling my.uthm.eprints.119812025-01-21T00:43:00Z http://eprints.uthm.edu.my/11981/ Deep learning-based microcirculation performance classification using multispectral photoacoustic technology Chua, Hui Ling Huong, Audrey RC Internal medicine Investigation of microcirculation is the key to diagnose circulatory dysfunction. Tissue circulation monitoring is a crucial part of the care of patients with severe chronic illnesses because it affects oxygen delivery to tissue. Recent technology, such as hyperspectral imaging, has allowed visualization of microcirculation at the price of high computation resources. Meanwhile, pulse oximeter performance varies with factors like the subject’s skin colour. This study explores the feasibility of using an in-house assembled multispectral photoacoustic (PA) system to investigate microcirculation performance in human subjects. We used pretrained Alexnet, Long Short-Term Memory (LSTM), and a hybrid Alexnet-LSTM network for the prediction task. This research included thirty-seven healthy participants in this cross-sectional study. The ultrasonic waves collected from their posterior left arm under two experimental settings, namely at rest (i.e., control) and with arterial blood flow occlusions, were used to predict the microcirculation changes in tissue using the deep networks. Our findings showed the superiority of the hybrid model over the Alexnet and LSTM, with an average testing accuracy of 95.7 % and precision of 98.2 %, making it an ideal deep learning model for the task. This study concluded that the proposed deep learning incorporated photoacoustic system has a promising future for diagnosing and treating patients with compromised microcirculatory conditions. 2024 Article PeerReviewed text en http://eprints.uthm.edu.my/11981/1/J17621_ba3f0e8aacb3c8b364a0f1afb7fc1cdf.pdf Chua, Hui Ling and Huong, Audrey (2024) Deep learning-based microcirculation performance classification using multispectral photoacoustic technology. -, 39 (2). pp. 2565-2583. ISSN 1001-0920
institution Universiti Tun Hussein Onn Malaysia
building UTHM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Tun Hussein Onn Malaysia
content_source UTHM Institutional Repository
url_provider http://eprints.uthm.edu.my/
language English
topic RC Internal medicine
spellingShingle RC Internal medicine
Chua, Hui Ling
Huong, Audrey
Deep learning-based microcirculation performance classification using multispectral photoacoustic technology
description Investigation of microcirculation is the key to diagnose circulatory dysfunction. Tissue circulation monitoring is a crucial part of the care of patients with severe chronic illnesses because it affects oxygen delivery to tissue. Recent technology, such as hyperspectral imaging, has allowed visualization of microcirculation at the price of high computation resources. Meanwhile, pulse oximeter performance varies with factors like the subject’s skin colour. This study explores the feasibility of using an in-house assembled multispectral photoacoustic (PA) system to investigate microcirculation performance in human subjects. We used pretrained Alexnet, Long Short-Term Memory (LSTM), and a hybrid Alexnet-LSTM network for the prediction task. This research included thirty-seven healthy participants in this cross-sectional study. The ultrasonic waves collected from their posterior left arm under two experimental settings, namely at rest (i.e., control) and with arterial blood flow occlusions, were used to predict the microcirculation changes in tissue using the deep networks. Our findings showed the superiority of the hybrid model over the Alexnet and LSTM, with an average testing accuracy of 95.7 % and precision of 98.2 %, making it an ideal deep learning model for the task. This study concluded that the proposed deep learning incorporated photoacoustic system has a promising future for diagnosing and treating patients with compromised microcirculatory conditions.
format Article
author Chua, Hui Ling
Huong, Audrey
author_facet Chua, Hui Ling
Huong, Audrey
author_sort Chua, Hui Ling
title Deep learning-based microcirculation performance classification using multispectral photoacoustic technology
title_short Deep learning-based microcirculation performance classification using multispectral photoacoustic technology
title_full Deep learning-based microcirculation performance classification using multispectral photoacoustic technology
title_fullStr Deep learning-based microcirculation performance classification using multispectral photoacoustic technology
title_full_unstemmed Deep learning-based microcirculation performance classification using multispectral photoacoustic technology
title_sort deep learning-based microcirculation performance classification using multispectral photoacoustic technology
publishDate 2024
url http://eprints.uthm.edu.my/11981/1/J17621_ba3f0e8aacb3c8b364a0f1afb7fc1cdf.pdf
http://eprints.uthm.edu.my/11981/
_version_ 1823094297341198336
score 13.23648

Similar Items