Rapid segmentation and sensitive analysis of CRP with paper-based microfluidic device using machine learning

Ning, Qihong; Zheng, Wei; Xu, Hao; Zhu, Armando; Li, Tangan; Cheng, Yuemeng; Feng, Shaoqing; Wang, Li; Cui, Daxiang; Wang, Kan

doi:10.1007/s00216-022-04039-x

Cited by 21 publications

(9 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The remaining design of the layer (shown in Supplementary Fig. S7 in the ESM for paper-based channels) was patterned by using a chemical capping method 48 to form the desired hydrophilic region. The entire process of sweat flow was as follows: sweat was absorbed through the collection layer, flowed up the vertical channel and the electrode layer through a chromatographic phenomenon, and reacted at the electrode layer.…”

Section: Methodsmentioning

confidence: 99%

Dual-signal readout paper-based wearable biosensor with a 3D origami structure for multiplexed analyte detection in sweat

et al. 2023

Self Cite

View full text Add to dashboard Cite

In this research, we design and implement a small, convenient, and noninvasive paper-based microfluidic sweat sensor that can simultaneously detect multiple key biomarkers in human sweat. The origami structure of the chip includes colorimetric and electrochemical sensing regions. Different colorimetric sensing regions are modified with specific chromogenic reagents to selectively identify glucose, lactate, uric acid, and magnesium ions in sweat, as well as the pH value. The regions of electrochemical sensing detect cortisol in sweat by molecular imprinting. The entire chip is composed of hydrophilically and hydrophobically treated filter paper, and 3D microfluidic channels are constructed by using folding paper. The thread-based channels formed after the hydrophilic and hydrophobic modifications are used to control the rate of sweat flow, which in turn can be used to control the sequence of reactions in the differently developing colored regions to ensure that signals of the best color can be captured simultaneously by the colorimetric sensing regions. Finally, the results of on-body experiments verify the reliability of the proposed sweat sensor and its potential for the noninvasive identification of a variety of sweat biomarkers.

show abstract

Section: Methodsmentioning

confidence: 99%

Dual-signal readout paper-based wearable biosensor with a 3D origami structure for multiplexed analyte detection in sweat

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…In another study, Ning et al reported a rapid segmentation and sensitive analysis of CRP with a paper-based microfluidic device using machine learning. 293 The study involves the fabrication of multi-layer μPADs using the imprinting method for colorimetric detection of C-reactive protein (CRP). The detection-related performance of the μPADs is enhanced by utilizing a machine learning algorithm, specifically, the You Only Look Once (YOLO) model, 294 which is capable of identifying the reaction areas in the μPADs under different lighting conditions and shooting angles of scenes.…”

Section: Smart Wearable Microfluidic Devicesmentioning

confidence: 99%

Recent developments and future perspectives of microfluidics and smart technologies in wearable devices

Apoorva,

Nguyen,

Sreejith

2024

Lab Chip

View full text Add to dashboard Cite

show abstract

“…To address this, a fusion layer was designed to mitigate the effect of this discrepancy on the recognition process. This fusion layer facilitates the nonlinear fitting of network-learned feature information [19][20], enhancing the extraction of image features.…”

Section: B Enhanced Rgiv3 Network Designmentioning

confidence: 99%

Deep Learning-Based Lung Medical Image Recognition

Chai,

Fei,

Wang

et al. 2024

IJIRCST

View full text Add to dashboard Cite

Pulmonary nodules serve as critical indicators for early lung cancer diagnosis, making their detection and classification essential. The prevalent use of transfer learning in recognition algorithms often encounters a significant disparity between source and target datasets, which hampers effective feature extraction from pulmonary nodules and degrades performance. An enhanced neural network model leveraging convolutional neural networks is introduced to address this issue. This model integrates a pre-trained GoogLeNet Inception V3 network with a custom-designed feature fusion layer, improving the network’s ability to extract features. To ascertain the optimal configuration, the models were evaluated based on accuracy in various combinations. The experiments conducted on the LUNA16 pulmonary nodule dataset revealed that the refined network model achieved an accuracy of 88.78% and a sensitivity of 87.18%. This represents an increase of 2.7 and 2.22 percentage points in accuracy and sensitivity, respectively, compared to the GoogLeNet Inception V3 algorithm. Further tests across different dataset proportions also yielded superior outcomes, demonstrating enhanced generalization capabilities. These findings can offer objective benchmarks for clinical diagnosis.

show abstract

Rapid segmentation and sensitive analysis of CRP with paper-based microfluidic device using machine learning

Cited by 21 publications

References 50 publications

Dual-signal readout paper-based wearable biosensor with a 3D origami structure for multiplexed analyte detection in sweat

Dual-signal readout paper-based wearable biosensor with a 3D origami structure for multiplexed analyte detection in sweat

Recent developments and future perspectives of microfluidics and smart technologies in wearable devices

Deep Learning-Based Lung Medical Image Recognition

Contact Info

Product

Resources

About