Research on <i>in-vivo</i> electron paramagnetic resonance spectrum classification and radiation dose prediction based on machine learning_Journal of Biomedical Engineering

Authors：

XIONG Guangwei ^1,2 , CHEN Bo ^1,2 , MA Lei ^1,3 , JIA Longpeng ^1,2 , CHEN Shunian ¹ , WU Ke ^1,3 , NING Jing ^1,3 ,  ZHU Bin ² ,  GUO Junwang ^1,3

1. Institute of Radiation Medicine, Academy of Military Medical Sciences, Academy of Military Sciences, Beijing 100850, P. R. China;
2. Institute of Smart Manufacturing Systems, Chang'an University, Xi'an 710061, P. R. China;
3. Beijing Key Laboratory of Radiobiology, Beijing 100850, P. R, China;

Corresponding author：

ZHU Bin, Email: 412833157@qq.com; GUO Junwang, Email: guojunwang.thaa@vip.163.com

Keywords：

In-vivo electron paramagnetic resonance; Radiation dose; Spectrum classification; Support vector machine; Genetic algorithm to optimize neural network

DOI：

10.7507/1001-5515.202302015

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

The in-vivo electron paramagnetic resonance (EPR) method can be used for on-site, rapid, and non-invasive detection of radiation dose to casualties after nuclear and radiation emergencies. For in-vivo EPR spectrum analysis, manual labeling of peaks and calculation of signal intensity are often used, which have problems such as large workload and interference by subjective factors. In this study, a method for automatic classification and identification of in-vivo EPR spectra was established using support vector machine (SVM) technology, which can in-batch and automatically identify and screen out invalid spectra due to vibration and dental surface water interference during in-vivo EPR measurements. In this study, a spectrum analysis method based on genetic algorithm optimization neural network (GA-BPNN) was established, which can automatically identify the radiation-induced signals in in-vivo EPR spectra and predict the radiation doses received by the injured. The experimental results showed that the SVM and GA-BPNN spectrum processing methods established in this study could effectively accomplish the automatic spectra classification and radiation dose prediction, and could meet the needs of dose assessment in nuclear emergency. This study explored the application of machine learning methods in EPR spectrum processing, improved the intelligence level of EPR spectrum processing, and would help to enhance the efficiency of mass EPR spectra processing.

Citation： XIONG Guangwei, CHEN Bo, MA Lei, JIA Longpeng, CHEN Shunian, WU Ke, NING Jing, ZHU Bin, GUO Junwang. Research on in-vivo electron paramagnetic resonance spectrum classification and radiation dose prediction based on machine learning. Journal of Biomedical Engineering, 2024, 41(5): 995-1002. doi: 10.7507/1001-5515.202302015 Copy

1.	郭俊旺. 辐射剂量在体测量电子顺磁共振谐振腔研究. 北京: 中国人民解放军军事医学科学院, 2015.
2.	袁清泉, 郭俊旺, 丛建波, 等. 在体剂量检测专用EPR数据采集与控制系统. 波谱学杂志, 2013, 30(3): 354-360.
3.	Bordi F, Fattibene P, Onori S. ESR dose assessment in irradiated chicken legs. Radiation Physics and Chemistry, 1994, 43: 487-491.
4.	Chumak V, Pavlenko J, Sholom S. An approach to the assessment of overall uncertainty of determination of dose using an ESR technique. Applied Radiation and Isotopes, 1996, 47(11-12): 1287-1291.
5.	D’Oca M C, Bartolotta A. Evaluation of the original dose in irradiated dried fruit by EPR spectroscopy. Radiation Measurements, 2011, 46: 813-815.
6.	Zhumadilov K, Ivannikov A, Apsalikov K N, et al. Radiation dose estimation by tooth enamel EPR dosimetry for residents of dolon and bodene. Journal of Radiation Research, 2006, 47(Suppl A): A47-A53.
7.	Parlato A, Calderaro E, Bartolotta A, et al. Application of the ESR spectroscopy to estimate the original dose in irradiated chicken bone. Radiation Physics and Chemistry, 2007, 76: 1466-1469.
8.	Beshir W B. Identification and dose assessment of irradiated cardamom and cloves by EPR spectrometry. Radiation Physics and Chemistry, 2014, 96: 190-194.
9.	Kwona J H, Chung H W, Byun M W. ESR spectroscopy for detecting gamma-irradiated dried vegetables and estimating absorbed doses, Radiation Physics and Chemistry, 2000, 57: 319-324.
10.	Vanhaelewyn G, Callens F, Grun R. EPR spectrum deconvolution and dose assessment of fossil tooth enamel using maximum likelihood common factor analysis. Applied Radiation and Isotopes, 2000, 52: 1317-1326.
11.	Grün R, Ward K. A long-term fading study for ESR intensity measurement and dose evaluation on fossil tooth enamel. Radiation Measurements, 2002, 35: 269-274.
12.	Ivanov D V, Wieser A, Shishkina E A, et al. Effect of spectrum processing procedure on the linearity of EPR dose reconstruction in tooth enamel. Radiation Measurements, 2014, 68: 7-13.
13.	Boyau R J, Duval M, Bodin T. MCDoseE 2. 0 a new markov chain monte carlo program for ESR dose response curve fitting and dose evaluation. Quaternary Geochronology, 2018, 44: 13-22.
14.	Ciesielski B, Kaminska J, Emerich K. Analysis of various modifications in spectra analysis on accuracy of dose reconstructions in EPR dosimetry in tooth enamel. Radiation Measurements, 2011, 46: 783-788.
15.	Zou J, Guo J, Ma L, et al. A normalization method of the volume and geometry of tooth for X-band in vivo EPR dosimetry. Applied Radiation and Isotopes, 2019, 149: 123-129.
16.	邹洁芮. 牙齿剂量电子顺磁共振在体测量方法的实用性研究. 北京: 军事科学院,2019.
17.	Șahiner E, Meriç N, Polymeris G S, et al. Impact of different mechanical pre-treatment to the EPR signals of human fingernails towards studying dose response and fading subjected to UV exposure or beta irradiation. Radiation Measurements, 2015, 82: 40-46.
18.	Zou J, Guo J, Dong G, et al. Effect of the tooth surface water on the accuracy of dose reconstructions in the X-band in vivo EPR dosimetry. Applied Radiation and Isotopes, 2018, 139: 86-90.
19.	Jiao L, Takada J, Endo S, et al. Effects of sunlight exposure on the human tooth enamel ESR spectra used for dose reconstruction. Journal of Radiation Research, 2007, 48(1): 21-29.
20.	Marciniak A, Ciesielski B, Prawdzik-Dampc A. The effect of dose and water treatment on EPR signals in irradiated fingernails. Radiation Protection Dosimetry, 2014, 162(1-2): 6-9.
21.	孙启涛, 罗智孙, 梁好, 等. 基于多尺度特征提取的风机音频信号故障诊断方法研究. 机电工程, 2023, 40(1): 39-46.
22.	丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述. 电子科技大学学报, 2011, 40(1): 2-10.
23.	谢智东, 谭信, 袁昕旺, 等. 基于生成对抗数据增强支持向量机的小样本信号调制识别算法. 电子与信息学报, 2023, 45(6): 2071-2080.
24.	杜海曼, 边婷, 熊鹏, 等. 基于支持向量机多特征融合ST段形态分类. 生物医学工程学杂志, 2022, 39(4): 702-712.
25.	Yang Mingjin, Zhou Wenju, Song Tianxiang. Audio-based fault diagnosis for belt conveyor rollers. Neurocomputing, 2020, 397: 447-456.
26.	崔建敏. 基于支持向量机的供暖系统智能诊断方法研究. 哈尔滨: 哈尔滨工业大学, 2021.
27.	石明, 汪舟, 甘进, 等. 基于GA-BP神经网络的喷丸样品表层硬度预测模型. 表面技术, 2022, 51(1): 332-338,357.
28.	于瑛, 陈笑, 贾晓宇, 等. 基于GA-BP神经网络的逐时总辐射分组模型研究. 太阳能学报, 2022, 43(8): 157-163.
29.	黄体浩, 李俊青, 赵海勇. 遗传算法优化的BP神经网络拷贝数变异检测. 计算机工程与应用, 2022, 58(1): 274-281.
30.	张晓侠, 刘凤坤, 买巍, 等. 基于BP神经网络及其改进算法的织机效率预测. 纺织学报, 2020, 41(8): 121-127.

1. 郭俊旺. 辐射剂量在体测量电子顺磁共振谐振腔研究. 北京: 中国人民解放军军事医学科学院, 2015.
2. 袁清泉, 郭俊旺, 丛建波, 等. 在体剂量检测专用EPR数据采集与控制系统. 波谱学杂志, 2013, 30(3): 354-360.
3. Bordi F, Fattibene P, Onori S. ESR dose assessment in irradiated chicken legs. Radiation Physics and Chemistry, 1994, 43: 487-491.
4. Chumak V, Pavlenko J, Sholom S. An approach to the assessment of overall uncertainty of determination of dose using an ESR technique. Applied Radiation and Isotopes, 1996, 47(11-12): 1287-1291.
5. D’Oca M C, Bartolotta A. Evaluation of the original dose in irradiated dried fruit by EPR spectroscopy. Radiation Measurements, 2011, 46: 813-815.
6. Zhumadilov K, Ivannikov A, Apsalikov K N, et al. Radiation dose estimation by tooth enamel EPR dosimetry for residents of dolon and bodene. Journal of Radiation Research, 2006, 47(Suppl A): A47-A53.
7. Parlato A, Calderaro E, Bartolotta A, et al. Application of the ESR spectroscopy to estimate the original dose in irradiated chicken bone. Radiation Physics and Chemistry, 2007, 76: 1466-1469.
8. Beshir W B. Identification and dose assessment of irradiated cardamom and cloves by EPR spectrometry. Radiation Physics and Chemistry, 2014, 96: 190-194.
9. Kwona J H, Chung H W, Byun M W. ESR spectroscopy for detecting gamma-irradiated dried vegetables and estimating absorbed doses, Radiation Physics and Chemistry, 2000, 57: 319-324.
10. Vanhaelewyn G, Callens F, Grun R. EPR spectrum deconvolution and dose assessment of fossil tooth enamel using maximum likelihood common factor analysis. Applied Radiation and Isotopes, 2000, 52: 1317-1326.
11. Grün R, Ward K. A long-term fading study for ESR intensity measurement and dose evaluation on fossil tooth enamel. Radiation Measurements, 2002, 35: 269-274.
12. Ivanov D V, Wieser A, Shishkina E A, et al. Effect of spectrum processing procedure on the linearity of EPR dose reconstruction in tooth enamel. Radiation Measurements, 2014, 68: 7-13.
13. Boyau R J, Duval M, Bodin T. MCDoseE 2. 0 a new markov chain monte carlo program for ESR dose response curve fitting and dose evaluation. Quaternary Geochronology, 2018, 44: 13-22.
14. Ciesielski B, Kaminska J, Emerich K. Analysis of various modifications in spectra analysis on accuracy of dose reconstructions in EPR dosimetry in tooth enamel. Radiation Measurements, 2011, 46: 783-788.
15. Zou J, Guo J, Ma L, et al. A normalization method of the volume and geometry of tooth for X-band in vivo EPR dosimetry. Applied Radiation and Isotopes, 2019, 149: 123-129.
16. 邹洁芮. 牙齿剂量电子顺磁共振在体测量方法的实用性研究. 北京: 军事科学院,2019.
17. Șahiner E, Meriç N, Polymeris G S, et al. Impact of different mechanical pre-treatment to the EPR signals of human fingernails towards studying dose response and fading subjected to UV exposure or beta irradiation. Radiation Measurements, 2015, 82: 40-46.
18. Zou J, Guo J, Dong G, et al. Effect of the tooth surface water on the accuracy of dose reconstructions in the X-band in vivo EPR dosimetry. Applied Radiation and Isotopes, 2018, 139: 86-90.
19. Jiao L, Takada J, Endo S, et al. Effects of sunlight exposure on the human tooth enamel ESR spectra used for dose reconstruction. Journal of Radiation Research, 2007, 48(1): 21-29.
20. Marciniak A, Ciesielski B, Prawdzik-Dampc A. The effect of dose and water treatment on EPR signals in irradiated fingernails. Radiation Protection Dosimetry, 2014, 162(1-2): 6-9.
21. 孙启涛, 罗智孙, 梁好, 等. 基于多尺度特征提取的风机音频信号故障诊断方法研究. 机电工程, 2023, 40(1): 39-46.
22. 丁世飞, 齐丙娟, 谭红艳. 支持向量机理论与算法研究综述. 电子科技大学学报, 2011, 40(1): 2-10.
23. 谢智东, 谭信, 袁昕旺, 等. 基于生成对抗数据增强支持向量机的小样本信号调制识别算法. 电子与信息学报, 2023, 45(6): 2071-2080.
24. 杜海曼, 边婷, 熊鹏, 等. 基于支持向量机多特征融合ST段形态分类. 生物医学工程学杂志, 2022, 39(4): 702-712.
25. Yang Mingjin, Zhou Wenju, Song Tianxiang. Audio-based fault diagnosis for belt conveyor rollers. Neurocomputing, 2020, 397: 447-456.
26. 崔建敏. 基于支持向量机的供暖系统智能诊断方法研究. 哈尔滨: 哈尔滨工业大学, 2021.
27. 石明, 汪舟, 甘进, 等. 基于GA-BP神经网络的喷丸样品表层硬度预测模型. 表面技术, 2022, 51(1): 332-338,357.
28. 于瑛, 陈笑, 贾晓宇, 等. 基于GA-BP神经网络的逐时总辐射分组模型研究. 太阳能学报, 2022, 43(8): 157-163.
29. 黄体浩, 李俊青, 赵海勇. 遗传算法优化的BP神经网络拷贝数变异检测. 计算机工程与应用, 2022, 58(1): 274-281.
30. 张晓侠, 刘凤坤, 买巍, 等. 基于BP神经网络及其改进算法的织机效率预测. 纺织学报, 2020, 41(8): 121-127.

Previous Article
Research on motion impedance cardiography de-noising method based on two-step spectral ensemble empirical mode decomposition and canonical correlation analysis

Journal of Biomedical Engineering

Research on in-vivo electron paramagnetic resonance spectrum classification and radiation dose prediction based on machine learning

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Format

Content