Discrimination of nasopharyngeal carcinoma serum using laser-induced breakdown spectroscopy combined with an extreme learning machine and random forest method

Yanwu Chu, Tong Chen, Feng Chen, Yun Tang, Shisong Tang, Honglin Jin, Lianbo Guo, Yong Feng Lu, Xiaoyan Zeng

Research output: Contribution to journalArticle

Abstract

The early diagnosis of malignant solid tumours remains a challenge. Here, we propose an efficient way to discriminate between nasopharyngeal carcinoma (NPC) serum and healthy control serum by using laser-induced breakdown spectroscopy (LIBS). Serum was dripped onto a boric acid substrate for LIBS spectrum acquisition. The focus elements (Na, K, Zn, Mg, etc.) were selected for diagnosing NPC using LIBS. With the random forest (RF), characteristic spectral lines were selected based on the variable importance. The spectral lines with variable importance greater than the average were selected. The selected spectral lines are the input of the extreme learning machine (ELM) classifier. Using the RF combined with the ELM classifier, the accuracy rate, sensitivity, and specificity of NPC serum and healthy controls reached 98.330%, 99.0222% and 97.751%, respectively. This demonstrates that LIBS combined with a RF-ELM model can be used to identify NPC with a high rate of accuracy.

Original languageEnglish (US)
Pages (from-to)2083-2088
Number of pages6
JournalJournal of Analytical Atomic Spectrometry
Volume33
Issue number12
DOIs
StatePublished - Dec 2018

Fingerprint

Laser induced breakdown spectroscopy
Learning systems
Classifiers
Tumors
Substrates

ASJC Scopus subject areas

  • Analytical Chemistry
  • Spectroscopy

Cite this

Discrimination of nasopharyngeal carcinoma serum using laser-induced breakdown spectroscopy combined with an extreme learning machine and random forest method. / Chu, Yanwu; Chen, Tong; Chen, Feng; Tang, Yun; Tang, Shisong; Jin, Honglin; Guo, Lianbo; Lu, Yong Feng; Zeng, Xiaoyan.

In: Journal of Analytical Atomic Spectrometry, Vol. 33, No. 12, 12.2018, p. 2083-2088.

Research output: Contribution to journalArticle

Chu, Yanwu ; Chen, Tong ; Chen, Feng ; Tang, Yun ; Tang, Shisong ; Jin, Honglin ; Guo, Lianbo ; Lu, Yong Feng ; Zeng, Xiaoyan. / Discrimination of nasopharyngeal carcinoma serum using laser-induced breakdown spectroscopy combined with an extreme learning machine and random forest method. In: Journal of Analytical Atomic Spectrometry. 2018 ; Vol. 33, No. 12. pp. 2083-2088.
@article{e524e5ea7e1e4c7c81997d091cc382dc,
title = "Discrimination of nasopharyngeal carcinoma serum using laser-induced breakdown spectroscopy combined with an extreme learning machine and random forest method",
abstract = "The early diagnosis of malignant solid tumours remains a challenge. Here, we propose an efficient way to discriminate between nasopharyngeal carcinoma (NPC) serum and healthy control serum by using laser-induced breakdown spectroscopy (LIBS). Serum was dripped onto a boric acid substrate for LIBS spectrum acquisition. The focus elements (Na, K, Zn, Mg, etc.) were selected for diagnosing NPC using LIBS. With the random forest (RF), characteristic spectral lines were selected based on the variable importance. The spectral lines with variable importance greater than the average were selected. The selected spectral lines are the input of the extreme learning machine (ELM) classifier. Using the RF combined with the ELM classifier, the accuracy rate, sensitivity, and specificity of NPC serum and healthy controls reached 98.330{\%}, 99.0222{\%} and 97.751{\%}, respectively. This demonstrates that LIBS combined with a RF-ELM model can be used to identify NPC with a high rate of accuracy.",
author = "Yanwu Chu and Tong Chen and Feng Chen and Yun Tang and Shisong Tang and Honglin Jin and Lianbo Guo and Lu, {Yong Feng} and Xiaoyan Zeng",
year = "2018",
month = "12",
doi = "10.1039/c8ja00263k",
language = "English (US)",
volume = "33",
pages = "2083--2088",
journal = "Journal of Analytical Atomic Spectrometry",
issn = "0267-9477",
publisher = "Royal Society of Chemistry",
number = "12",

}

TY - JOUR

T1 - Discrimination of nasopharyngeal carcinoma serum using laser-induced breakdown spectroscopy combined with an extreme learning machine and random forest method

AU - Chu, Yanwu

AU - Chen, Tong

AU - Chen, Feng

AU - Tang, Yun

AU - Tang, Shisong

AU - Jin, Honglin

AU - Guo, Lianbo

AU - Lu, Yong Feng

AU - Zeng, Xiaoyan

PY - 2018/12

Y1 - 2018/12

N2 - The early diagnosis of malignant solid tumours remains a challenge. Here, we propose an efficient way to discriminate between nasopharyngeal carcinoma (NPC) serum and healthy control serum by using laser-induced breakdown spectroscopy (LIBS). Serum was dripped onto a boric acid substrate for LIBS spectrum acquisition. The focus elements (Na, K, Zn, Mg, etc.) were selected for diagnosing NPC using LIBS. With the random forest (RF), characteristic spectral lines were selected based on the variable importance. The spectral lines with variable importance greater than the average were selected. The selected spectral lines are the input of the extreme learning machine (ELM) classifier. Using the RF combined with the ELM classifier, the accuracy rate, sensitivity, and specificity of NPC serum and healthy controls reached 98.330%, 99.0222% and 97.751%, respectively. This demonstrates that LIBS combined with a RF-ELM model can be used to identify NPC with a high rate of accuracy.

AB - The early diagnosis of malignant solid tumours remains a challenge. Here, we propose an efficient way to discriminate between nasopharyngeal carcinoma (NPC) serum and healthy control serum by using laser-induced breakdown spectroscopy (LIBS). Serum was dripped onto a boric acid substrate for LIBS spectrum acquisition. The focus elements (Na, K, Zn, Mg, etc.) were selected for diagnosing NPC using LIBS. With the random forest (RF), characteristic spectral lines were selected based on the variable importance. The spectral lines with variable importance greater than the average were selected. The selected spectral lines are the input of the extreme learning machine (ELM) classifier. Using the RF combined with the ELM classifier, the accuracy rate, sensitivity, and specificity of NPC serum and healthy controls reached 98.330%, 99.0222% and 97.751%, respectively. This demonstrates that LIBS combined with a RF-ELM model can be used to identify NPC with a high rate of accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85057529712&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057529712&partnerID=8YFLogxK

U2 - 10.1039/c8ja00263k

DO - 10.1039/c8ja00263k

M3 - Article

AN - SCOPUS:85057529712

VL - 33

SP - 2083

EP - 2088

JO - Journal of Analytical Atomic Spectrometry

JF - Journal of Analytical Atomic Spectrometry

SN - 0267-9477

IS - 12

ER -