Abstract
The study considers the application of artificial neural networks to solve the inverse problem of fluorescence (FL) spectroscopy for monitoring the elimination of carbon nanocomplexes’ components from the body – the problem of determining the concentrations of carbon dots (CD) and the anticancer drug doxorubicin (Dox) excreted from the body with urine. The problem was solved in three ways using three sets of FL spectroscopy data: spectral data obtained by exciting FL of urine together with CD and Dox with radiation of 405 nm, 532 nm wavelength as well as spectra obtained by combining these data. Multilayer perceptrons (MLP) were applied to the obtained spectral data, which enabled the determination of the concentrations of CD and Dox in urine. To increase the accuracy of monitoring the excretion of CD and Dox with urine, principal component analysis and autoencoders were additionally used. The conducted studies showed that the best results of solving this problem are provided by the application of a MLP to spectral data compressed using an autoencoder. This approach allows us to determine the concentration of CD in urine with MAE of 39 ng/mL (3.3% of the upper limit of the concentration range) and the concentration of Dox with MAE of 27 ng/mL (2.8% of the upper limit of the concentration range). The proposed approach shows results comparable with analogues, however it lacks several significant drawbacks such as rigid fixation of the CD concentration in the suspension, and it can be used for simultaneous rapid monitoring of a number of substances.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS1060992X23010046/MediaObjects/12005_2023_5164_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS1060992X23010046/MediaObjects/12005_2023_5164_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS1060992X23010046/MediaObjects/12005_2023_5164_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS1060992X23010046/MediaObjects/12005_2023_5164_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS1060992X23010046/MediaObjects/12005_2023_5164_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS1060992X23010046/MediaObjects/12005_2023_5164_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS1060992X23010046/MediaObjects/12005_2023_5164_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.3103%2FS1060992X23010046/MediaObjects/12005_2023_5164_Fig8_HTML.png)
REFERENCES
B.G.M. Vandenginste, D.L. Massart, L.M.C. Buydens, S. De Jong, P.J. Lewi, and J. Smeyers-Verbeke, Handbook of chemometrics and qualimetrics (Elsevier, Amsterdam, 1998).
Y. LeCun, Y. Bengio, and G. Hinton, Deep learning, Nature 521 (7553), 436–444 (2015).
Å. Rinnan, F. Van Den Berg, and S.B. Engelsen, Review of the most common pre-processing techniques for near-infrared spectra, Trac-Trend Anal. Chem. 28 (10), 1201–1222 (2009).
S. Burikov, S. Dolenko, T. Dolenko, S. Patsaeva, and V. Yuzhakov, Decomposition of water Raman stretching band with a combination of optimization methods, Mol. Phys. 108 (6), 739-747 (2010).
O. Devos, L. Duponchel, Parallel genetic algorithm co-optimization of spectral pre-processing and wavelength selection for PLS regression, Chemometr. Intell. Lab. 107 (1), 50–58 (2011).
C.M. Valensise, A. Giuseppi, F. Vernuccio, A. De la Cadena, G. Cerullo, and D. Polli, Removing non-resonant background from CARS spectra via deep learning, APL Photonics 5 (6), 061305 (2020).
I. Isaev, E. Obornev, I. Obornev, E. Rodionov, M. Shimelevich, V. Shirokiy, and S. Dolenko, Using Domain Knowledge for Feature Selection in Neural Network Solution of the Inverse Problem of Magnetotelluric Sounding, Adv. Intell. Syst. Cybern. 310, 115–126 (2020).
A. Efitorov, S. Dolenko, T. Dolenko, K. Laptinskiy, and S. Burikov, Use of Wavelet Neural Networks to Solve Inverse Problems in Spectroscopy of Multi-component Solutions, Stud. Comp. Intell. 856, 285–294 (2020).
E. Guevara, J.C. Torres-Galván, M.G. Ramírez-Elías, C. Luevano-Contreras, and F.J. González, Use of Raman spectroscopy to screen diabetes mellitus with machine learning tools, Biomed. Opt. Express. 9 (10), 4998–5010 (2018).
S. Khan, R. Ullah, A. Khan, R. Ashraf, H. Ali, M. Bilal, and M. Saleem, Analysis of hepatitis B virus infection in blood sera using Raman spectroscopy and machine learning, Photodiagn. Photodyn. 23, 89–93 (2018).
E. Rodriguez-Diaz, D. Manolakos, H. Christman, M.A. Bonning, J.K. Geisse, O.M. A’Amar, and I.J. Bigio, Optical spectroscopy as a method for skin cancer risk assessment, Photochem. Photobiol. 95 (6), 1441–1445 (2019).
J. Xue, Y. Pu, J. Smith, X.Gao, C. Wang, and B. Wu, Identifying metastatic ability of prostate cancer cell lines using native fluorescence spectroscopy and machine learning methods, Sci. Rep. 11 (1), 2282 (2021).
X. Wang, Z. Wang, J. Weng, C. Wen, H. Chen, and X. Wang, A new effective machine learning framework for sepsis diagnosis, IEEE Access 6, 48300–48310 (2018).
I. Olaetxea, A. Valero, E. Lopez, H. Lafuente, A. Izeta, I. Jaunarena, and A. Seifert, Machine Learning-Assisted Raman Spectroscopy for pH and Lactate Sensing in Body Fluids, Anal. Chem. 92 (20), 13888–13895 (2020).
X. Jintao, Y. Liming, L. Yufei, L. Chunyan, and C. Han, Noninvasive and fast measurement of blood glucose in vivo by near infrared (NIR), Spectrochim. Acta A 179, 250-254 (2017).
Z. Li, H. Zhang, B.T. Nguyen, S. Luo, P.Y. Liu, J. Zou, and A.Q. Liu, Smart ring resonator–based sensor for multicomponent chemical analysis via machine learning, Photonics Res. 9 (2), B38–B44 (2021).
T.A. Dolenko, S.A. Burikov, A.M. Vervald, I.I. Vlasov, S.A. Dolenko, K.A. Laptinskiy, J.M. Rosenholm, and O.A. Shenderova, Use of neural network algorithms for optical imaging of fluorescent biomarkers based on carbon nanoparticles, J. Biomed. Opt. 19 (11), 117007 (2014).
K.A. Laptinskiy, S.A. Burikov, S.A. Dolenko, A.O. Efitorov, O.E. Sarmanova, O.A. Shenderova, I.I. Vlasov, and T.A. Dolenko, Monitoring of nanodiamonds in human urine using artificial neural networks, Phys. Status Solidi A 213 (10), 2614–2622 (2016).
O.E. Sarmanova, S.A. Burikov, S.A. Dolenko, I.V. Isaev, K.A. Laptinskiy, N. Prabhakar, D. SenKaraman, J.M. Rosenholm, O.A. Shenderova, and T.A. Dolenko, A method for optical imaging and monitoring of the excretion of fluorescent nanocomposites from the body using artificial neural networks, Nanomed.-Nanotechnol. 14 (4), 1371–1380 (2018).
X. Gao and B. Wu, Breast cancer diagnosis using fluorescence spectroscopy with dual-wavelength excitation and machine learning, Proc. SPIE 10873, 108731F (2019).
Z. Xu, Z. Wang, M. Liu, B. Yan, X. Ren, and Z. Gao, Machine learning assisted dual-channel carbon quantum dots-based fluorescence sensor array for detection of tetracyclines, Spectrochim. Acta A 232, 118147 (2020).
D. Bank, N. Koenigstein, and R. Giryes, “Autoencoders,” arXiv preprint arXiv:2003.05991, (2020).
O.E. Sarmanova, K.A. Laptinskiy, M.Y. Khmeleva, S.A. Burikov, S.A. Dolenko, A.E. Tomskaya, and T.A. Dolenko, “Development of the fluorescent carbon nanosensor for pH and temperature of liquid media with artificial neural networks,” Spectrochim. Acta A 258, 119861 (2021). https://doi.org/10.1016/j.saa.2021.119861
S.K. Kumar, On weight initialization in deep neural networks, arXiv preprint arXiv:1704.08863, (2017).
D.P. Kingma and J. Ba, Adam: A Method for Stochastic Optimization, arXiv preprint arXiv:1412.6980, (2014).
A. Géron, Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems (O’Reilly Media, Sebastopol, 2019).
S.M. Lundberg and S.I. Lee, A unified approach to interpreting model predictions, in 31st Conf. Neural Inform. Process. Syst. (Long Beach, 2017) pp. 4768–4777.
B. Wang, S. Wang, Y. Wang, Y. Lv, H. Wu, X. Ma, and M. Tan, Highly fluorescent carbon dots for visible sensing of doxorubicin release based on efficient nanosurface energy transfer, Biotechnol. Lett. 38 (1), 191–201 (2016).
I.V. Gerdova, S.A. Dolenko, T.A. Dolenko, I.V. Churina, and V.V. Fadeev, New opportunity solutions to inverse problems in laser spectroscopy involving artificial neural networks, Izv. Akad. Nauk. Fiz. 66 (8), 1116–1124 (2002).
R. Jia, D. Dao, B. Wang, F.A. Hubis, N. Hynes, N.M. Gürel, and C.J. Spanos, Towards efficient data valuation based on the shapley value, in 22nd Intern. Conf. Artif. Intell. Stati. PMLR (2019) pp. 1167–1176.
I. Isaev, O. Sarmanova, S. Burikov, T. Dolenko, K. Laptinskiy, and S. Dolenko, Feature Selection in Neural Network Solution of Inverse Problem Based on Integration of Optical Spectroscopic Methods, Stud. Comp. Intell. 925, 234–241 (2021).
M. Yang, Y. Yan, E. Liu, X. Hu, H. Hao, and J. Fan, Polyethyleneimine-functionalized carbon dots as a fluorescent probe for doxorubicin hydrochloride by an inner filter effect, Opti. Mater. 112, 110743 (2021).
ACKNOWLEDGMENTS
This research was performed according to the Development program of the Interdisciplinary Scientific and Educational School of Lomonosov Moscow State University “Photonic and Quantum technologies. Digital medicine” (O.E. Sarmanova). The authors are grateful to A. Tomskaya for providing carbon dots.
Funding
The work was supported by the Russian Science Foundation, project no. 22-12-00138, https://rscf.ru/project/22-12-00138/ (T.A.Dolenko, S.A.Burikov, K.A.Laptinskiy—planning and conducting an experiment, processing and analyzing the results). The contribution of O.E.Sarmanova (programming and training of neural networks) was supported by the Foundation for the Advancement of Theoretical Physics and Mathematics “BASIS”, project no. 19-2-6-6-1.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
About this article
Cite this article
Sarmanova, O.E., Kudryashov, A.D., Laptinskiy, K.A. et al. Applications of Fluorescence Spectroscopy and Machine Learning Methods for Monitoring of Elimination of Carbon Nanoagents from the Body. Opt. Mem. Neural Networks 32, 20–33 (2023). https://doi.org/10.3103/S1060992X23010046
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S1060992X23010046