Enhancing Sensitivity of Point-of-Care Thyroid Diagnosis via Computational Analysis of Lateral Flow Assay Images Using Novel Textural Features and Hybrid-AI Models

Lateral flow assays are widely used in point-of-care diagnostics but face challenges in sensitivity and accuracy when detecting low analyte concentrations, such as thyroid-stimulating hormone biomarkers. This study aims to enhance assay performance by leveraging textural features and hybrid artifici...

Full description

Saved in:
Bibliographic Details
Main Authors: Towfeeq Fairooz, Sara E. McNamee, Dewar Finlay, Kok Yew Ng, James McLaughlin
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Biosensors
Subjects:
Online Access:https://www.mdpi.com/2079-6374/14/12/611
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846105549207240704
author Towfeeq Fairooz
Sara E. McNamee
Dewar Finlay
Kok Yew Ng
James McLaughlin
author_facet Towfeeq Fairooz
Sara E. McNamee
Dewar Finlay
Kok Yew Ng
James McLaughlin
author_sort Towfeeq Fairooz
collection DOAJ
description Lateral flow assays are widely used in point-of-care diagnostics but face challenges in sensitivity and accuracy when detecting low analyte concentrations, such as thyroid-stimulating hormone biomarkers. This study aims to enhance assay performance by leveraging textural features and hybrid artificial intelligence models. A modified Gray-Level Co-occurrence Matrix, termed the Averaged Horizontal Multiple Offsets Gray-Level Co-occurrence Matrix, was utilised to compute the textural features of the biosensor assay images. Significant textural features were selected for further analysis. A deep learning Convolutional Neural Network model was employed to extract features from these textural features. Both traditional machine learning models and hybrid artificial intelligence models, which combine Convolutional Neural Network features with traditional algorithms, were used to categorise these textural features based on the thyroid-stimulating hormone concentration levels. The proposed method achieved accuracy levels exceeding 95%. This pioneering study highlights the utility of textural aspects of assay images for accurate predictive disease modelling, offering promising advancements in diagnostics and management within biomedical research.
format Article
id doaj-art-27d7ae810016481cb98d1b2feefa5169
institution Kabale University
issn 2079-6374
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Biosensors
spelling doaj-art-27d7ae810016481cb98d1b2feefa51692024-12-27T14:14:16ZengMDPI AGBiosensors2079-63742024-12-01141261110.3390/bios14120611Enhancing Sensitivity of Point-of-Care Thyroid Diagnosis via Computational Analysis of Lateral Flow Assay Images Using Novel Textural Features and Hybrid-AI ModelsTowfeeq Fairooz0Sara E. McNamee1Dewar Finlay2Kok Yew Ng3James McLaughlin4School of Engineering, Ulster University, Belfast BT15 1ED, UKSchool of Engineering, Ulster University, Belfast BT15 1ED, UKSchool of Engineering, Ulster University, Belfast BT15 1ED, UKSchool of Engineering, Ulster University, Belfast BT15 1ED, UKSchool of Engineering, Ulster University, Belfast BT15 1ED, UKLateral flow assays are widely used in point-of-care diagnostics but face challenges in sensitivity and accuracy when detecting low analyte concentrations, such as thyroid-stimulating hormone biomarkers. This study aims to enhance assay performance by leveraging textural features and hybrid artificial intelligence models. A modified Gray-Level Co-occurrence Matrix, termed the Averaged Horizontal Multiple Offsets Gray-Level Co-occurrence Matrix, was utilised to compute the textural features of the biosensor assay images. Significant textural features were selected for further analysis. A deep learning Convolutional Neural Network model was employed to extract features from these textural features. Both traditional machine learning models and hybrid artificial intelligence models, which combine Convolutional Neural Network features with traditional algorithms, were used to categorise these textural features based on the thyroid-stimulating hormone concentration levels. The proposed method achieved accuracy levels exceeding 95%. This pioneering study highlights the utility of textural aspects of assay images for accurate predictive disease modelling, offering promising advancements in diagnostics and management within biomedical research.https://www.mdpi.com/2079-6374/14/12/611convolutional neural network (CNN)lateral flow assay (LFA)point-of-care (POC)gray-level co-occurrence matrix (GLCM)region of interest (ROI)texture analysis
spellingShingle Towfeeq Fairooz
Sara E. McNamee
Dewar Finlay
Kok Yew Ng
James McLaughlin
Enhancing Sensitivity of Point-of-Care Thyroid Diagnosis via Computational Analysis of Lateral Flow Assay Images Using Novel Textural Features and Hybrid-AI Models
Biosensors
convolutional neural network (CNN)
lateral flow assay (LFA)
point-of-care (POC)
gray-level co-occurrence matrix (GLCM)
region of interest (ROI)
texture analysis
title Enhancing Sensitivity of Point-of-Care Thyroid Diagnosis via Computational Analysis of Lateral Flow Assay Images Using Novel Textural Features and Hybrid-AI Models
title_full Enhancing Sensitivity of Point-of-Care Thyroid Diagnosis via Computational Analysis of Lateral Flow Assay Images Using Novel Textural Features and Hybrid-AI Models
title_fullStr Enhancing Sensitivity of Point-of-Care Thyroid Diagnosis via Computational Analysis of Lateral Flow Assay Images Using Novel Textural Features and Hybrid-AI Models
title_full_unstemmed Enhancing Sensitivity of Point-of-Care Thyroid Diagnosis via Computational Analysis of Lateral Flow Assay Images Using Novel Textural Features and Hybrid-AI Models
title_short Enhancing Sensitivity of Point-of-Care Thyroid Diagnosis via Computational Analysis of Lateral Flow Assay Images Using Novel Textural Features and Hybrid-AI Models
title_sort enhancing sensitivity of point of care thyroid diagnosis via computational analysis of lateral flow assay images using novel textural features and hybrid ai models
topic convolutional neural network (CNN)
lateral flow assay (LFA)
point-of-care (POC)
gray-level co-occurrence matrix (GLCM)
region of interest (ROI)
texture analysis
url https://www.mdpi.com/2079-6374/14/12/611
work_keys_str_mv AT towfeeqfairooz enhancingsensitivityofpointofcarethyroiddiagnosisviacomputationalanalysisoflateralflowassayimagesusingnoveltexturalfeaturesandhybridaimodels
AT saraemcnamee enhancingsensitivityofpointofcarethyroiddiagnosisviacomputationalanalysisoflateralflowassayimagesusingnoveltexturalfeaturesandhybridaimodels
AT dewarfinlay enhancingsensitivityofpointofcarethyroiddiagnosisviacomputationalanalysisoflateralflowassayimagesusingnoveltexturalfeaturesandhybridaimodels
AT kokyewng enhancingsensitivityofpointofcarethyroiddiagnosisviacomputationalanalysisoflateralflowassayimagesusingnoveltexturalfeaturesandhybridaimodels
AT jamesmclaughlin enhancingsensitivityofpointofcarethyroiddiagnosisviacomputationalanalysisoflateralflowassayimagesusingnoveltexturalfeaturesandhybridaimodels