zhpsЖурнал прикладной спектроскопииZhurnal Prikladnoii Spektroskopii0514-7506B. I. Stepanov Institute of Physics of the National Academy of Scienceszhps-1771Research ArticleАННОТАЦИИ АНГЛОЯЗЫЧНЫХ СТАТЕЙABSTRACTS ENGLISH-LANGUAGE ARTICLESCочетание лазерно-искровой эмиссионной спектроскопии с машинным обучением для выявления рака легкихLASER-INDUCED BREAKDOWN SPECTROSCOPY COMBINED WITH MACHINE LEARNING FOR THE IDENTIFICATION OF LUNG CANCER TUMORSLiH.LiHan

Чанчунь

Changchun

SunH.SunHaoran

Чанчунь

Changchun

GaoX.GaoXun

Чанчунь

Changchun

lasercust@163.comКолледж электронных технологий ЧанчуняSchool of Optoelectronic Science, Changchun College of Electronic TechnologyТехнологический университет ЧанчуняSchool of Mechanical and Electrical Engineering, Changchun University of TechnologyУниверситет науки и технологий ЧанчуняSchool of Physics, Changchun University of Science and Technology202507022025921132132Copyright © Li H., Sun H., Gao X., 20252025Li H., Sun H., Gao X.Li H., Sun H., Gao X.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://zhps.ejournal.by/jour/article/view/1771

Лазерно-искровая эмиссионная спектроскопия (LIBS) в сочетании с машинным обучением использована для дифференциации образцов раковых опухолей легких и нормальных тканей. Образцы плазмы собирали с помощью лазерной абляции при 1064 нм для получения характерных спектров образцов опухолей легких и нормальных тканей. Для диагностики злокачественных новообразований выбраны 12 линий C, Mg, Ca, C-N, Na и K. Для установления модели дискриминации опухолей и нормальных тканей использованы модели PCA, SVM, KNN, Decision Tree и Bagged Tree. Для оценки модели дискриминации использован метод 10-кратной перекрестной проверки. Лучшие результаты показала интегрированная обучающая модель Bagged Tree с общей точностью 98.9%, чувствительностью и специфичностью 98.6 и 99.3% и площадью под кривой (AUC) 0.982. Предположено, что LIBS можно использовать как быстрый и точный способ идентификации опухолей легких человека. 

The diagnosis of lung cancer has always been a challenging clinical issue. In this work, we use laserinduced breakdown spectroscopy (LIBS) combined with machine learning to differentiate samples of lung cancer tumors from those of normal tissues. Sample plasma was collected by laser ablation at 1064 nm to obtain the characteristic spectra of lung tumor and normal tissue samples. Twelve lines of C, Mg, Ca, C-N, Na, and K were selected for the diagnosis of malignancy. Principal component analysis (PCA), support vector machine (SVM), k-nearest neighbors (KNN), Decision Tree, and Bagged Tree were used to establish the discrimination model for tumors and normal tissue. A 10-fold cross-validation method was used to evaluate the discrimination model. The results showed that the integrated learning Bagged Tree model performed best, with an overall accuracy of 98.9%, sensitivity and specificity of 98.6 and 99.3%, respectively, and an area under the curve (AUC) of 0.982. This study suggests that LIBS can be used as a fast and accurate means of identifying human lung tumors. 

лазерно-искровая эмиссионная спектроскопиямашинное обучениедискриминационная модельрак легкихдиагностикаlaser-induced breakdown spectroscopymachine learningdiscrimination modellung cancer tumorsdiagnosisThis research is financially supported by the Natural Science Foundation of Jilin province (No. 20220101035JC).ReferencesD. W. Yang, Y. Liu, C. B. Bai, X. D. Wang, C. A. Powell, Cancer Lett., 468, 82–87 (2020).D. W. Yang, Y. Liu, C. B. Bai, X. D. Wang, C. A. Powell, Cancer Lett., 468, 82–87 (2020).D. R. Lewis, D. P. Check, N. E. Caporaso, W. D. Travis, S. S. Devesa, Cancer, 120, No. 18, 2883–2892 (2015).D. R. Lewis, D. P. Check, N. E. Caporaso, W. D. Travis, S. S. Devesa, Cancer, 120, No. 18, 2883–2892 (2015).F. R. Zhu, R. Ding, R. Q. Lei, H. Cheng, J. Liu, C. W. Shen, et al., Respiratory Medicine, 146, 57–65 (2019).F. R. Zhu, R. Ding, R. Q. Lei, H. Cheng, J. Liu, C. W. Shen, et al., Respiratory Medicine, 146, 57–65 (2019).S. H. Moolgavkar, T. R. Holford, D. T. Levy, C. Y. Kong, M. Foy, L. Clarke, et al., J. Nat. Cancer Institute, 104, No. 7, 541–548 (2012).S. H. Moolgavkar, T. R. Holford, D. T. Levy, C. Y. Kong, M. Foy, L. Clarke, et al., J. Nat. Cancer Institute, 104, No. 7, 541–548 (2012).W. Q. Chen, R. S. Zheng, H. M. Zeng, S. W. Zhang, Thoracic Cancer, 6, No. 2, 209–215 (2015).W. Q. Chen, R. S. Zheng, H. M. Zeng, S. W. Zhang, Thoracic Cancer, 6, No. 2, 209–215 (2015).F. Bray, J. Ferlay, I. Soerjomataram, R. L. Siegel, L. A. Torre, A. Jemal, Cancer J. Clin., 68, No. 6, 394–424 (2018).F. Bray, J. Ferlay, I. Soerjomataram, R. L. Siegel, L. A. Torre, A. Jemal, Cancer J. Clin., 68, No. 6, 394–424 (2018).L. Filograna, J. Lenkowicz, F. Cellini, N. Dinapoli, S. Manfrida, N. Magarelli, et al., Radiologia Medica, 124, No. 1, 50–57 (2018).L. Filograna, J. Lenkowicz, F. Cellini, N. Dinapoli, S. Manfrida, N. Magarelli, et al., Radiologia Medica, 124, No. 1, 50–57 (2018).W. D. Travis, N. Rekhtman, Seminars in Respiratory & Critical Care Medicine, 32, No. 1, 22–31 (2011).W. D. Travis, N. Rekhtman, Seminars in Respiratory & Critical Care Medicine, 32, No. 1, 22–31 (2011).A. Jabbar, Z. Y. Hou, J. C. Liu, R. Ahmed, S. Mahmood, Z. Wang, Spectrochim. Acta, B: At. Spectrosc., 157, 84–90 (2019).A. Jabbar, Z. Y. Hou, J. C. Liu, R. Ahmed, S. Mahmood, Z. Wang, Spectrochim. Acta, B: At. Spectrosc., 157, 84–90 (2019).G. Kim, J. Kwak, K. R. Kim, H. Lee, K. W. Kim, H. Yang, et al., J. Hazard. Mater., 263, No. 2, 754–760 (2013).G. Kim, J. Kwak, K. R. Kim, H. Lee, K. W. Kim, H. Yang, et al., J. Hazard. Mater., 263, No. 2, 754–760 (2013).S. Niu, L. J. Zheng, A. Q. Khan, G. Feng, H. P. Zeng, Talanta, 179, No. 1, 312–317 (2018).S. Niu, L. J. Zheng, A. Q. Khan, G. Feng, H. P. Zeng, Talanta, 179, No. 1, 312–317 (2018).G. Bilge, H. M. Velioglu, B. Sezer, K. E. Eseller, I. H. Boyaci, Meat Sci., 119, No. 9, 118–122 (2016).G. Bilge, H. M. Velioglu, B. Sezer, K. E. Eseller, I. H. Boyaci, Meat Sci., 119, No. 9, 118–122 (2016).C. A. Munson, F. C. De Lucia Jr., T. Piehler, K. L. McNesby, A. W. Miziolek, Spectrochim. Acta, B: At. Spectrosc., 60, No. 7, 1217–1224 (2005).C. A. Munson, F. C. De Lucia Jr., T. Piehler, K. L. McNesby, A. W. Miziolek, Spectrochim. Acta, B: At. Spectrosc., 60, No. 7, 1217–1224 (2005).V. K. Singh, V. Kumar, J. Sharma, Lasers in Medical Science, 30, No. 6, 1763–1778 (2015).V. K. Singh, V. Kumar, J. Sharma, Lasers in Medical Science, 30, No. 6, 1763–1778 (2015).R. Kanawade, F. Mehari, C. Knipfer, M. Rohde, K. T. Gerk, M. Schmidt, et al., Spectrochim. Acta, B: At. Spectrosc., 87, 175–181 (2013).R. Kanawade, F. Mehari, C. Knipfer, M. Rohde, K. T. Gerk, M. Schmidt, et al., Spectrochim. Acta, B: At. Spectrosc., 87, 175–181 (2013).A. Kumar, F. Y. Yueh, J. P. Singh, S. Burgess, Appl. Opt., 43, No. 28, 5399 (2004).A. Kumar, F. Y. Yueh, J. P. Singh, S. Burgess, Appl. Opt., 43, No. 28, 5399 (2004).A. El-Hussein, A. K. Kassem, H. Ismail, M. A. Harith, Talanta, 82, No. 2, 495–501 (2010).A. El-Hussein, A. K. Kassem, H. Ismail, M. A. Harith, Talanta, 82, No. 2, 495–501 (2010).Y. W. Chu, T. Chen, F. Chen, Y. Tang, S. S. Tang, H. L. Jin, et al., J. Analyt. At. Spectrometry, 33, No. 12, 2083–2088 (2018).Y. W. Chu, T. Chen, F. Chen, Y. Tang, S. S. Tang, H. L. Jin, et al., J. Analyt. At. Spectrometry, 33, No. 12, 2083–2088 (2018).Y. Y. Liu, S. Y. Zhao, X. Gao, S. Y. Fu, C. Song, Y. P. Dou, S. Z. Song, C. Y. Qi, J. Q. Lin, RSC Adv., 12, 34520 (2022).Y. Y. Liu, S. Y. Zhao, X. Gao, S. Y. Fu, C. Song, Y. P. Dou, S. Z. Song, C. Y. Qi, J. Q. Lin, RSC Adv., 12, 34520 (2022).P. Petousis, S. X. Han, D. Aberle, A. T. Bui Alex, Artificial Intelligence in Medicine, 72, No. 9, 42–55 (2016).P. Petousis, S. X. Han, D. Aberle, A. T. Bui Alex, Artificial Intelligence in Medicine, 72, No. 9, 42–55 (2016).H. Asri, H. Mousannif, H. A. Moatassime, T. Noel, Proc. Comp. Sci., 83, 1064–1069 (2016).H. Asri, H. Mousannif, H. A. Moatassime, T. Noel, Proc. Comp. Sci., 83, 1064–1069 (2016).S. Palmqvist, P. S. Insela, H. Zetterberg, K. Blennow, B. Brixg, E. Stomrud, et al., Alzhmer’s & Dementia, 15, No. 2 (2019).S. Palmqvist, P. S. Insela, H. Zetterberg, K. Blennow, B. Brixg, E. Stomrud, et al., Alzhmer’s & Dementia, 15, No. 2 (2019).

The authors declare that there are no conflicts of interest present.