Deep learning assisted quantitative detection of cardiac troponin I in hierarchical dendritic copper-nickel nanostructure lateral flow immunoassay

被引:0
|
作者
Zhang, Shenglan [1 ,2 ,3 ]
Chen, Liqiang [1 ,2 ]
Tan, Yuxin [3 ]
Wu, Shaojie [1 ,2 ]
Guo, Pengxin [1 ,2 ]
Jiang, Xincheng [1 ,2 ]
Pan, Hongcheng [3 ]
机构
[1] Guilin Univ Technol, Educ Dept Guangxi Zhuang Autonomous Reg, Key Lab Adv Mfg & Automat Technol, Guilin 541006, Peoples R China
[2] Guilin Univ Technol, Coll Mech & Control Engn, Guilin 541006, Peoples R China
[3] Guilin Univ Technol, Coll Environm Sci & Engn, Guilin 541006, Peoples R China
基金
中国国家自然科学基金;
关键词
CARCINOEMBRYONIC ANTIGEN; FLUORESCENCE; RECOGNITION; COLOR;
D O I
10.1039/d4ay01187b
中图分类号
O65 [分析化学];
学科分类号
070302 ; 081704 ;
摘要
The rising demand for point-of-care testing (POCT) in disease diagnosis has made LFIA sensors based on dendritic metal thin film (HD-nanometal) and background fluorescence technology essential for rapid and accurate disease marker detection, thanks to their integrated design, high sensitivity, and cost-effectiveness. However, their unique 3D nanostructures cause significant fluorescence variation, challenging traditional image processing methods in segmenting weak fluorescence regions. This paper develops a deep learning method to efficiently segment target regions in HD-nanometal LFIA sensor images, improving quantitative detection accuracy. We propose an improved UNet++ network with attention and residual modules, accurately segmenting varying fluorescence intensities, especially weak ones. We evaluated the method using IoU and Dice coefficients, comparing it with UNet, Deeplabv3, and UNet++. We used an HD-nanoCu-Ni LFIA sensor for cardiac troponin I (cTnI) as a case study to validate the method's practicality. The proposed method achieved a 96.3% IoU, outperforming other networks. The R2 between characteristic quantity and cTnI concentration reached 0.994, confirming the method's accuracy and reliability. This enhances POCT accuracy and provides a reference for future fluorescence immunochromatography expansion. This paper proposes a deep learning-based method using an improved UNet++ network with attention and residual modules to enhance quantitative detection accuracy in HD-nanoMetal LFIA sensor images.
引用
收藏
页码:6715 / 6725
页数:11
相关论文
共 29 条
  • [21] Deep Learning-Enhanced Chemiluminescence Vertical Flow Assay for High-Sensitivity Cardiac Troponin I Testing
    Han, Gyeo-Re
    Goncharov, Artem
    Eryilmaz, Merve
    Ye, Shun
    Joung, Hyou-Arm
    Ghosh, Rajesh
    Ngo, Emily
    Tomoeda, Aoi
    Lee, Yena
    Ngo, Kevin
    Melton, Elizabeth
    Garner, Omai B.
    Di Carlo, Dino
    Ozcan, Aydogan
    SMALL, 2025,
  • [22] Flower-shaped magnetic fluorescent nanoparticles based lateral flow biosensor for highly sensitive detection of cardiac troponin I
    Liu, Guan
    Chen, Mingrui
    Wang, Jiulin
    Cui, Xinyuan
    Wang, Kan
    Yang, Ziyang
    Gao, Ang
    Zhang, Amin
    Zhang, Qian
    Shen, Yulan
    Gao, Guo
    Cui, Daxiang
    SENSORS AND ACTUATORS B-CHEMICAL, 2024, 414
  • [23] Quantitative lateral flow immunoassay for rapid detection of procollagen type I N-terminal propeptide in the monitoring of osteoporosis treatment
    Chen, Chung-An
    Chiu, Ping-Yeh
    Huang, Tse-Hao
    Ho, Natalie Yi-Ju
    Kao, Fu-Cheng
    Tsai, Tsung-Ting
    ANALYTICA CHIMICA ACTA, 2023, 1239
  • [24] Time-resolved fluorescence resonance energy transfer-based lateral flow immunoassay using a raspberry-type europium particle and a single membrane for the detection of cardiac troponin I
    Lee, Kyung Won
    Kim, Ka Ram
    Chun, Hyeong Jin
    Jeong, Kwan Young
    Hong, Dong-Ki
    Lee, Kook-Nyung
    Yoon, Hyun C.
    BIOSENSORS & BIOELECTRONICS, 2020, 163
  • [25] Development and optimization of surface-enhancement Raman scattering-based lateral flow immunoassays for the ultrasensitive detection of cardiac troponin I
    Song, Eunyeong
    Kim, Insu
    Jeon, Changsu
    Pyun, Sunghyun
    MICROCHEMICAL JOURNAL, 2023, 193
  • [26] One-pot synthesis of AuPt@FexOy nanoparticles with excellent peroxidase-like activity for development of ultrasensitive colorimetric lateral flow immunoassay of cardiac troponin I
    Wang, Haodong
    Yao, Chaoqun
    Fan, Jiwen
    He, Yuquan
    Wang, Zhenxin
    BIOSENSORS & BIOELECTRONICS, 2023, 237
  • [27] Ru(bpy)32+-Loaded Mesoporous Silica Nanoparticles as Electrochemiluminescent Probes of a Lateral Flow Immunosensor for Highly Sensitive and Quantitative Detection of Troponin I
    Hong, Donggu
    Jo, Eun-Jung
    Kim, Kihyeun
    Song, Mun-Beom
    Kim, Min-Gon
    SMALL, 2020, 16 (44)
  • [28] Electrochemiluminescence Lateral Flow Immunoassay Using Ruthenium(II) Complex-Loaded Dendritic Mesoporous Silica Nanospheres for Highly Sensitive and Quantitative Detection of SARS-CoV-2 Nucleocapsid Protein
    Fu, Wenxuan
    Wang, Xuexue
    Ying, Xudong
    Sun, Tao
    Wang, Yafeng
    Wang, Jing
    Su, Bin
    ADVANCED FUNCTIONAL MATERIALS, 2024,
  • [29] Combining Ultralong Organic Phosphorescent Nanoparticle-Based Lateral Flow Strip Assay With Deep Learning: A Quantitative Detection Method for Creatine Kinase MB
    Wu, Yi
    Zhang, Yiming
    Yi, Weijing
    Fu, Yusheng
    Ren, Chunhui
    Guo, Jinhong
    Guo, Jiuchuan
    IEEE SENSORS JOURNAL, 2024, 24 (24) : 41787 - 41796