Identification of Graves’ ophthalmology by laser-induced breakdown spectroscopy combined with machine learning method

doi:10.1007/s12200-020-0978-2

Front. Optoelectron.

2021, Vol. 14

Issue (3) : 321-328 https://doi.org/10.1007/s12200-020-0978-2

RESEARCH ARTICLE

Identification of Graves’ ophthalmology by laser-induced breakdown spectroscopy combined with machine learning method

Jingjing LI¹, Feng CHEN¹, Guangqian HUANG², Siyu ZHANG¹, Weiliang WANG¹, Yun TANG¹, Yanwu CHU¹, Jian YAO³, Lianbo GUO¹(

), Fagang JIANG²(

)

¹. Wuhan National Laboratory for Optoelectronics, Huazhong University of Science and Technology, Wuhan 430074, China
². Department of Ophthalmology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, China
³. School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China

Download: PDF(834 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

Diagnosis of the Graves’ ophthalmology remains a significant challenge. We identified between Graves’ ophthalmology tissues and healthy controls by using laser-induced breakdown spectroscopy (LIBS) combined with machine learning method. In this work, the paraffin-embedded samples of the Graves’ ophthalmology were prepared for LIBS spectra acquisition. The metallic elements (Na, K, Al, Ca), non-metallic element (O) and molecular bands ((C-N), (C-O)) were selected for diagnosing Graves’ ophthalmology. The selected spectral lines were inputted into the supervised classification methods including linear discriminant analysis (LDA), support vector machine (SVM), k-nearest neighbor (kNN), and generalized regression neural network (GRNN), respectively. The results showed that the predicted accuracy rates of LDA, SVM, kNN, GRNN were 76.33%, 96.28%, 96.56%, and 96.33%, respectively. The sensitivity of four models were 75.89%, 93.78%, 96.78%, and 96.67%, respectively. The specificity of four models were 76.78%, 98.78%, 96.33%, and 96.00%, respectively. This demonstrated that LIBS assisted with a nonlinear model can be used to identify Graves’ ophthalmopathy with a higher rate of accuracy. The kNN had the best performance by comparing the three nonlinear models. Therefore, LIBS combined with machine learning method can be an effective way to discriminate Graves’ ophthalmology.

Keywords Graves’ ophthalmology laser-induced breakdown spectroscopy (LIBS) linear discriminant analysis (LDA) support vector machine (SVM) k-nearest neighbor (kNN) generalized regression neural network (GRNN)

Corresponding Author(s): Lianbo GUO,Fagang JIANG

Just Accepted Date: 17 March 2020 Online First Date: 14 April 2020 Issue Date: 30 September 2021

Cite this article:

Jingjing LI,Feng CHEN,Guangqian HUANG, et al. Identification of Graves’ ophthalmology by laser-induced breakdown spectroscopy combined with machine learning method[J]. Front. Optoelectron., 2021, 14(3): 321-328.

URL:

https://academic.hep.com.cn/foe/EN/10.1007/s12200-020-0978-2
https://academic.hep.com.cn/foe/EN/Y2021/V14/I3/321

Fig.1 Schematic diagram of the experimental setup

Fig.2 Paraffin-embedded samples.

Fig.3 LIBS spectra of two kinds of samples at different bands. (a) 380–410 nm; (b) 570–780 nm

Tab.1 Analytical lines used as input variables for the classifier

Tab.2 Confusion matrix of the LDA model

Fig.4 Parameter optimization process of the SVM model

Tab.3 Confusion matrix of the SVM model

Fig.5 Parameter optimization process of the kNN model

Tab.4 Confusion matrix of the kNN model

Fig.6 Parameter optimization process of the GRNN model

Tab.5 Confusion matrix of the GRNN model

Fig.7 ROC curves obtained with three nonlinear identification model

Tab.6 Indicators of the nonlinear identification models

1	R S Bahn. Graves’ ophthalmopathy. The New England Journal of Medicine, 2010, 362(8): 726–738 https://doi.org/10.1056/NEJMra0905750 pmid: 20181974
2	P O Phelps, K Williams. Thyroid eye disease for the primary care physician. Disease-a-Month, 2014, 60(6): 292–298 https://doi.org/10.1016/j.disamonth.2014.03.010 pmid: 24906675
3	M Cakir. Euthyroid Graves’ ophthalmopathy with negative autoantibodies. Journal of the National Medical Association, 2005, 97(11): 1547–1549 pmid: 16334503
4	A E Heufelder. Pathogenesis of ophthalmopathy in autoimmune thyroid disease. Reviews in Endocrine & Metabolic Disorders, 2000, 1(1–2): 87–95 https://doi.org/10.1023/A:1010020621687 pmid: 11704996
5	L Guo, X Li, W Xiong, X Zeng, Y Lu. Recent technological progress in Asia from the first Asian Symposium on Laser-induced Breakdown Spectroscopy. Frontiers of Physics, 2016, 11(6): 115208
6	J G R Leandro, F B Gonzaga, J V de Figueiredo Latorraca. Discrimination of wood species using laser-induced breakdown spectroscopy and near-infrared reflectance spectroscopy. Wood Science and Technology, 2019, 53(5): 1079–1091 https://doi.org/10.1007/s00226-019-01119-7
7	M Akhtar, A Jabbar, N Ahmed, S Mahmood, Z A Umar, R Ahmed, M A Baig. Analysis of lead and copper in soil samples by laser-induced breakdown spectroscopy under external magnetic field. Applied Physics B, Lasers and Optics, 2019, 125(6): 110 https://doi.org/10.1007/s00340-019-7225-9
8	F Trichard, V Forquet, N Gilon, C Lienemann, F Baco-Antoniali. Detection and quantification of sulfur in oil products by laser-induced breakdown spectroscopy for on-line analysis. Spectrochimica Acta Part B, Atomic Spectroscopy, 2016, 118: 72–80 https://doi.org/10.1016/j.sab.2016.02.001
9	S Moncayo, J D Rosales, R Izquierdo-Hornillos, J Anzano, J O Caceres. Classification of red wine based on its protected designation of origin (PDO) using Laser-induced Breakdown Spectroscopy (LIBS). Talanta, 2016, 158: 185–191 https://doi.org/10.1016/j.talanta.2016.05.059 pmid: 27343593
10	T Jochum, J U Günther, C Bohling. Material Analysis in Fast Industrial Processes by LIBS: Technical and analytical solutions for inline process monitoring. Photonics Views, 2019, 16(1): 56–59 https://doi.org/10.1002/phvs.201900004
11	L B Guo, Z H Zhu, J M Li, Y Tang, S S Tang, Z Q Hao, X Y Li, Y F Lu, X Y Zeng. Determination of boron with molecular emission using laser-induced breakdown spectroscopy combined with laser-induced radical fluorescence. Optics Express, 2018, 26(3): 2634–2642 https://doi.org/10.1364/OE.26.002634 pmid: 29401800
12	R Yuan, Y Tang, Z Zhu, Z Hao, J Li, H Yu, Y Yu, L Guo, X Zeng, Y Lu. Accuracy improvement of quantitative analysis for major elements in laser-induced breakdown spectroscopy using single-sample calibration. Analytica Chimica Acta, 2019, 1064: 11–16 https://doi.org/10.1016/j.aca.2019.02.056 pmid: 30982508
13	Y W Chu, S S Tang, S X Ma, Y Y Ma, Z Q Hao, Y M Guo, L B Guo, Y F Lu, X Y Zeng. Accuracy and stability improvement for meat species identification using multiplicative scatter correction and laser-induced breakdown spectroscopy. Optics Express, 2018, 26(8): 10119–10127 https://doi.org/10.1364/OE.26.010119 pmid: 29715952
14	X Chen, X Li, X Yu, D Chen, A Liu. Diagnosis of human malignancies using laser-induced breakdown spectroscopy in combination with chemometric methods. Spectrochimica Acta Part B, Atomic Spectroscopy, 2018, 139: 63–69 https://doi.org/10.1016/j.sab.2017.11.016
15	F Ghasemi, P Parvin, J Reif, S Abachi, M R Mohebbifar, M R Razzaghi. Laser induced breakdown spectroscopy for the diagnosis of several malignant tissue samples. Journal of Laser Applications, 2017, 29(4): 042005 https://doi.org/10.2351/1.4989376
16	R Gaudiuso, E Ewusi-Annan, N Melikechi, X Sun, B Liu, L F Campesato, T Merghoub. Using LIBS to diagnose melanoma in biomedical fluids deposited on solid substrates: Limits of direct spectral analysis and capability of machine learning. Spectrochimica Acta Part B, Atomic Spectroscopy, 2018, 146: 106–114 https://doi.org/10.1016/j.chemolab.2016.07.001
17	Y Chu, T Chen, F Chen, Y Tang, S Tang, H Jin, L Guo, Y Lu, X Zeng. Discrimination of nasopharyngeal carcinoma serum using laser-induced breakdown spectroscopy combined with an extreme learning machine and random forest method. Journal of Analytical Atomic Spectrometry, 2018, 33(12): 2083–2088 https://doi.org/10.1039/C8JA00263K
18	R A Fisher. The use of multiple measurements in taxonomic problems. Annals of Eugenics, 1936, 7(2): 179–188 https://doi.org/10.1111/j.1469-1809.1936.tb02137.x
19	Y A Ghassabeh, F Rudzicz, H A Moghaddam. Fast incremental LDA feature extraction. Pattern Recognition, 2015, 48(6): 1999–2012 https://doi.org/10.1016/j.patcog.2014.12.012
20	Y K Zhang, C Q Liu. A novel face recognition method based on linear discriminant analysis. Journal Infrared Millimeter and Waves, 2003, 22(5): 327–330
21	B E Boser, I M Guyon, V N Vapnik. A training algorithm for optimal margin classifiers. In: Proceedings of the 5th annual workshop on Computational learning theory. New York: ACM, 1992, 144–152
22	N Goyal, K Gupta, N Kumar. Multiclass twin support vector machine for plant species identification. Multimedia Tools and Applications, 2019, 78: 27785–27808
23	Y W Chu, F Chen, Y Tang, T Chen, Y X Yu, H L Jin, L B Guo, Y F Lu, X Y Zeng. Diagnosis of nasopharyngeal carcinoma from serum samples using hyperspectral imaging combined with a chemometric method. Optics Express, 2018, 26(22): 28661–28671 https://doi.org/10.1364/OE.26.028661 pmid: 30470039
24	A Kataria, M D Singh. A review of data classification using k-nearest neighbour algorithm. International Journal of Emerging Technology and Advanced Engineering, 2013, 3: 354–360
25	O Dogan, B Oztaysi. Genders prediction from indoor customer paths by Levenshtein-based fuzzy kNN. Expert Systems with Applications, 2019, 136: 42–49 https://doi.org/10.1016/j.eswa.2019.06.029
26	S Jiang, G Pang, M Wu, L Kuang. An improved k-nearest-neighbor algorithm for text categorization. Expert Systems with Applications, 2012, 39(1): 1503–1509 https://doi.org/10.1016/j.eswa.2011.08.040
27	H B Celikoglu. Application of radial basis function and generalized regression neural networks in non-linear utility function specification for travel mode choice modelling. Mathematical and Computer Modelling, 2006, 44(7-8): 640–658 https://doi.org/10.1016/j.mcm.2006.02.002
28	S Han, L Huang, Y Zhou, Z Liu. Mixed chaotic FOA with GRNN to construction of a mutual fund forecasting model. Cognitive Systems Research, 2018, 52: 380–386 https://doi.org/10.1016/j.cogsys.2018.07.006
29	Z Hu, Q Zhao, J Wang. The prediction model of worsted yarn quality based on CNN–GRNN neural network. Neural Computing & Applications, 2019, 31(9): 4551–4562 https://doi.org/10.1007/s00521-018-3723-7
30	H Bendu, B Deepak, S Murugan. Application of GRNN for the prediction of performance and exhaust emissions in HCCI engine using ethanol. Energy Conversion and Management, 2016, 122: 165–173 https://doi.org/10.1016/j.enconman.2016.05.061
31	Y Zhang, J Niu, S. NaA novel nonlinear function fitting model based on FOA and GRNN. Mathematical Problems in Engineering, 2019, 2019: 2697317
32	NIST. NIST Atomic Spectra Database. 2014
33	W Zhu, N Zeng, N. Wang Sensitivity. Specificity, Accuracy, Associated Confidence Interval and ROC Analysis with Practical SAS® Implementations, 2010

Viewed

Full text

Abstract

Cited

Shared

Discussed