A Novel Method for Quantitative Analysis of C-Reactive Protein Lateral Flow Immunoassays Images via CMOS Sensor and Recurrent Neural Networks
<bold>Objective:</bold> To design and implement an easy-to-use, Point-of-Care (PoC) lateral flow immunoassays (LFA) reader and data analysis system, which provides a more in-depth quantitative analysis for LFA images than conventional approaches thereby supporting efficient decision maki...
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
IEEE
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/f37ed9ec1ed347629c47b14d33b993e2 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:f37ed9ec1ed347629c47b14d33b993e2 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:f37ed9ec1ed347629c47b14d33b993e22021-12-04T00:00:12ZA Novel Method for Quantitative Analysis of C-Reactive Protein Lateral Flow Immunoassays Images via CMOS Sensor and Recurrent Neural Networks2168-237210.1109/JTEHM.2021.3130494https://doaj.org/article/f37ed9ec1ed347629c47b14d33b993e22021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9625990/https://doaj.org/toc/2168-2372<bold>Objective:</bold> To design and implement an easy-to-use, Point-of-Care (PoC) lateral flow immunoassays (LFA) reader and data analysis system, which provides a more in-depth quantitative analysis for LFA images than conventional approaches thereby supporting efficient decision making for potential early risk assessment of cardiovascular disease (CVD). <bold>Methods and procedures:</bold> A novel end-to-end system was developed including a portable device with CMOS camera integrated with optimized illumination and optics to capture the LFA images produced using high-sensitivity C-Reactive Protein (hsCRP) (concentration level < 5 mg/L). The images were transmitted via WiFi to a back-end server system for image analysis and classification. Unlike common image classification approaches which are based on averaging image intensity from a region-of-interest (ROI), a novel approach was developed which considered the signal along the sample’s flow direction as a time series and, consequently, no need for ROI detection. Long Short-Term Memory (LSTM) networks were deployed for multilevel classification. The features based on Dynamic Time Warping (DTW) and histogram bin counts (HBC) were explored for classification. <bold>Results:</bold> For the classification of hsCRP, the LSTM outperformed the traditional machine learning classifiers with or without DTW and HBC features performed the best (with mean accuracy of 94%) compared to other features. Application of the proposed method to human plasma also suggests that HBC features from LFA time series performed better than the mean from ROI and raw LFA data. <bold>Conclusion:</bold> As a proof of concept, the results demonstrate the capability of the proposed framework for quantitative analysis of LFA images and suggest the potential for early risk assessment of CVD. <bold>Clinical impact:</bold> The hsCRP levels < 5 mg/L were aligned with clinically actionable categories for early risk assessment of CVD. The outcomes demonstrated the real-world applicability of the proposed system for quantitative analysis of LFA images, which is potentially useful for more LFA applications beyond presented in this study.Min JingDonal MclaughlinSara E. McnameeShasidran RajBrian Mac NameeDavid SteeleDewar FinlayJames MclaughlinIEEEarticleLateral flow immunoassays (LFA)CMOS image sensorlong short-term memory (LSTM)dynamic time warpinghigh-sensitivity C-Reactive ProteinComputer applications to medicine. Medical informaticsR858-859.7Medical technologyR855-855.5ENIEEE Journal of Translational Engineering in Health and Medicine, Vol 9, Pp 1-15 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
Lateral flow immunoassays (LFA) CMOS image sensor long short-term memory (LSTM) dynamic time warping high-sensitivity C-Reactive Protein Computer applications to medicine. Medical informatics R858-859.7 Medical technology R855-855.5 |
| spellingShingle |
Lateral flow immunoassays (LFA) CMOS image sensor long short-term memory (LSTM) dynamic time warping high-sensitivity C-Reactive Protein Computer applications to medicine. Medical informatics R858-859.7 Medical technology R855-855.5 Min Jing Donal Mclaughlin Sara E. Mcnamee Shasidran Raj Brian Mac Namee David Steele Dewar Finlay James Mclaughlin A Novel Method for Quantitative Analysis of C-Reactive Protein Lateral Flow Immunoassays Images via CMOS Sensor and Recurrent Neural Networks |
| description |
<bold>Objective:</bold> To design and implement an easy-to-use, Point-of-Care (PoC) lateral flow immunoassays (LFA) reader and data analysis system, which provides a more in-depth quantitative analysis for LFA images than conventional approaches thereby supporting efficient decision making for potential early risk assessment of cardiovascular disease (CVD). <bold>Methods and procedures:</bold> A novel end-to-end system was developed including a portable device with CMOS camera integrated with optimized illumination and optics to capture the LFA images produced using high-sensitivity C-Reactive Protein (hsCRP) (concentration level < 5 mg/L). The images were transmitted via WiFi to a back-end server system for image analysis and classification. Unlike common image classification approaches which are based on averaging image intensity from a region-of-interest (ROI), a novel approach was developed which considered the signal along the sample’s flow direction as a time series and, consequently, no need for ROI detection. Long Short-Term Memory (LSTM) networks were deployed for multilevel classification. The features based on Dynamic Time Warping (DTW) and histogram bin counts (HBC) were explored for classification. <bold>Results:</bold> For the classification of hsCRP, the LSTM outperformed the traditional machine learning classifiers with or without DTW and HBC features performed the best (with mean accuracy of 94%) compared to other features. Application of the proposed method to human plasma also suggests that HBC features from LFA time series performed better than the mean from ROI and raw LFA data. <bold>Conclusion:</bold> As a proof of concept, the results demonstrate the capability of the proposed framework for quantitative analysis of LFA images and suggest the potential for early risk assessment of CVD. <bold>Clinical impact:</bold> The hsCRP levels < 5 mg/L were aligned with clinically actionable categories for early risk assessment of CVD. The outcomes demonstrated the real-world applicability of the proposed system for quantitative analysis of LFA images, which is potentially useful for more LFA applications beyond presented in this study. |
| format |
article |
| author |
Min Jing Donal Mclaughlin Sara E. Mcnamee Shasidran Raj Brian Mac Namee David Steele Dewar Finlay James Mclaughlin |
| author_facet |
Min Jing Donal Mclaughlin Sara E. Mcnamee Shasidran Raj Brian Mac Namee David Steele Dewar Finlay James Mclaughlin |
| author_sort |
Min Jing |
| title |
A Novel Method for Quantitative Analysis of C-Reactive Protein Lateral Flow Immunoassays Images via CMOS Sensor and Recurrent Neural Networks |
| title_short |
A Novel Method for Quantitative Analysis of C-Reactive Protein Lateral Flow Immunoassays Images via CMOS Sensor and Recurrent Neural Networks |
| title_full |
A Novel Method for Quantitative Analysis of C-Reactive Protein Lateral Flow Immunoassays Images via CMOS Sensor and Recurrent Neural Networks |
| title_fullStr |
A Novel Method for Quantitative Analysis of C-Reactive Protein Lateral Flow Immunoassays Images via CMOS Sensor and Recurrent Neural Networks |
| title_full_unstemmed |
A Novel Method for Quantitative Analysis of C-Reactive Protein Lateral Flow Immunoassays Images via CMOS Sensor and Recurrent Neural Networks |
| title_sort |
novel method for quantitative analysis of c-reactive protein lateral flow immunoassays images via cmos sensor and recurrent neural networks |
| publisher |
IEEE |
| publishDate |
2021 |
| url |
https://doaj.org/article/f37ed9ec1ed347629c47b14d33b993e2 |
| work_keys_str_mv |
AT minjing anovelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT donalmclaughlin anovelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT saraemcnamee anovelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT shasidranraj anovelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT brianmacnamee anovelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT davidsteele anovelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT dewarfinlay anovelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT jamesmclaughlin anovelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT minjing novelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT donalmclaughlin novelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT saraemcnamee novelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT shasidranraj novelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT brianmacnamee novelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT davidsteele novelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT dewarfinlay novelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks AT jamesmclaughlin novelmethodforquantitativeanalysisofcreactiveproteinlateralflowimmunoassaysimagesviacmossensorandrecurrentneuralnetworks |
| _version_ |
1718373065612591104 |