Novel quantitative analysis of autofluorescence images for oral cancer screening

Tze-Ta Huang, Jehn-Shun Huang, Yen Yun Wang, Ken-Chung Chen, Dung-Yau Wang, Yi Chun Chen, Che Wei Wu, Leong Perng Chan, Yi Chu Lin, Yu Hsun Kao, Shoko Nioka, Shyng Shiou F. Yuan, Pau-Choo Chung

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Objectives VELscope® was developed to inspect oral mucosa autofluorescence. However, its accuracy is heavily dependent on the examining physician's experience. This study was aimed toward the development of a novel quantitative analysis of autofluorescence images for oral cancer screening. Materials and methods Patients with either oral cancer or precancerous lesions and a control group with normal oral mucosa were enrolled in this study. White light images and VELscope® autofluorescence images of the lesions were taken with a digital camera. The lesion in the image was chosen as the region of interest (ROI). The average intensity and heterogeneity of the ROI were calculated. A quadratic discriminant analysis (QDA) was utilized to compute boundaries based on sensitivity and specificity. Results 47 oral cancer lesions, 54 precancerous lesions, and 39 normal oral mucosae controls were analyzed. A boundary of specificity of 0.923 and a sensitivity of 0.979 between the oral cancer lesions and normal oral mucosae were validated. The oral cancer and precancerous lesions could also be differentiated from normal oral mucosae with a specificity of 0.923 and a sensitivity of 0.970. Conclusion The novel quantitative analysis of the intensity and heterogeneity of VELscope® autofluorescence images used in this study in combination with a QDA classifier can be used to differentiate oral cancer and precancerous lesions from normal oral mucosae.

Original languageEnglish
Pages (from-to)20-26
Number of pages7
JournalOral Oncology
Volume68
DOIs
Publication statusPublished - 2017 May 1

Fingerprint

Mouth Neoplasms
Mouth Mucosa
Early Detection of Cancer
Discriminant Analysis
Physicians
Light
Sensitivity and Specificity
Control Groups

All Science Journal Classification (ASJC) codes

  • Oral Surgery
  • Oncology
  • Cancer Research

Cite this

Huang, Tze-Ta ; Huang, Jehn-Shun ; Wang, Yen Yun ; Chen, Ken-Chung ; Wang, Dung-Yau ; Chen, Yi Chun ; Wu, Che Wei ; Chan, Leong Perng ; Lin, Yi Chu ; Kao, Yu Hsun ; Nioka, Shoko ; Yuan, Shyng Shiou F. ; Chung, Pau-Choo. / Novel quantitative analysis of autofluorescence images for oral cancer screening. In: Oral Oncology. 2017 ; Vol. 68. pp. 20-26.
@article{3dcc7d7d6be2407fba1e99b32c440f5d,
title = "Novel quantitative analysis of autofluorescence images for oral cancer screening",
abstract = "Objectives VELscope{\circledR} was developed to inspect oral mucosa autofluorescence. However, its accuracy is heavily dependent on the examining physician's experience. This study was aimed toward the development of a novel quantitative analysis of autofluorescence images for oral cancer screening. Materials and methods Patients with either oral cancer or precancerous lesions and a control group with normal oral mucosa were enrolled in this study. White light images and VELscope{\circledR} autofluorescence images of the lesions were taken with a digital camera. The lesion in the image was chosen as the region of interest (ROI). The average intensity and heterogeneity of the ROI were calculated. A quadratic discriminant analysis (QDA) was utilized to compute boundaries based on sensitivity and specificity. Results 47 oral cancer lesions, 54 precancerous lesions, and 39 normal oral mucosae controls were analyzed. A boundary of specificity of 0.923 and a sensitivity of 0.979 between the oral cancer lesions and normal oral mucosae were validated. The oral cancer and precancerous lesions could also be differentiated from normal oral mucosae with a specificity of 0.923 and a sensitivity of 0.970. Conclusion The novel quantitative analysis of the intensity and heterogeneity of VELscope{\circledR} autofluorescence images used in this study in combination with a QDA classifier can be used to differentiate oral cancer and precancerous lesions from normal oral mucosae.",
author = "Tze-Ta Huang and Jehn-Shun Huang and Wang, {Yen Yun} and Ken-Chung Chen and Dung-Yau Wang and Chen, {Yi Chun} and Wu, {Che Wei} and Chan, {Leong Perng} and Lin, {Yi Chu} and Kao, {Yu Hsun} and Shoko Nioka and Yuan, {Shyng Shiou F.} and Pau-Choo Chung",
year = "2017",
month = "5",
day = "1",
doi = "10.1016/j.oraloncology.2017.03.003",
language = "English",
volume = "68",
pages = "20--26",
journal = "Oral Oncology",
issn = "1368-8375",
publisher = "Elsevier Limited",

}

Novel quantitative analysis of autofluorescence images for oral cancer screening. / Huang, Tze-Ta; Huang, Jehn-Shun; Wang, Yen Yun; Chen, Ken-Chung; Wang, Dung-Yau; Chen, Yi Chun; Wu, Che Wei; Chan, Leong Perng; Lin, Yi Chu; Kao, Yu Hsun; Nioka, Shoko; Yuan, Shyng Shiou F.; Chung, Pau-Choo.

In: Oral Oncology, Vol. 68, 01.05.2017, p. 20-26.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Novel quantitative analysis of autofluorescence images for oral cancer screening

AU - Huang, Tze-Ta

AU - Huang, Jehn-Shun

AU - Wang, Yen Yun

AU - Chen, Ken-Chung

AU - Wang, Dung-Yau

AU - Chen, Yi Chun

AU - Wu, Che Wei

AU - Chan, Leong Perng

AU - Lin, Yi Chu

AU - Kao, Yu Hsun

AU - Nioka, Shoko

AU - Yuan, Shyng Shiou F.

AU - Chung, Pau-Choo

PY - 2017/5/1

Y1 - 2017/5/1

N2 - Objectives VELscope® was developed to inspect oral mucosa autofluorescence. However, its accuracy is heavily dependent on the examining physician's experience. This study was aimed toward the development of a novel quantitative analysis of autofluorescence images for oral cancer screening. Materials and methods Patients with either oral cancer or precancerous lesions and a control group with normal oral mucosa were enrolled in this study. White light images and VELscope® autofluorescence images of the lesions were taken with a digital camera. The lesion in the image was chosen as the region of interest (ROI). The average intensity and heterogeneity of the ROI were calculated. A quadratic discriminant analysis (QDA) was utilized to compute boundaries based on sensitivity and specificity. Results 47 oral cancer lesions, 54 precancerous lesions, and 39 normal oral mucosae controls were analyzed. A boundary of specificity of 0.923 and a sensitivity of 0.979 between the oral cancer lesions and normal oral mucosae were validated. The oral cancer and precancerous lesions could also be differentiated from normal oral mucosae with a specificity of 0.923 and a sensitivity of 0.970. Conclusion The novel quantitative analysis of the intensity and heterogeneity of VELscope® autofluorescence images used in this study in combination with a QDA classifier can be used to differentiate oral cancer and precancerous lesions from normal oral mucosae.

AB - Objectives VELscope® was developed to inspect oral mucosa autofluorescence. However, its accuracy is heavily dependent on the examining physician's experience. This study was aimed toward the development of a novel quantitative analysis of autofluorescence images for oral cancer screening. Materials and methods Patients with either oral cancer or precancerous lesions and a control group with normal oral mucosa were enrolled in this study. White light images and VELscope® autofluorescence images of the lesions were taken with a digital camera. The lesion in the image was chosen as the region of interest (ROI). The average intensity and heterogeneity of the ROI were calculated. A quadratic discriminant analysis (QDA) was utilized to compute boundaries based on sensitivity and specificity. Results 47 oral cancer lesions, 54 precancerous lesions, and 39 normal oral mucosae controls were analyzed. A boundary of specificity of 0.923 and a sensitivity of 0.979 between the oral cancer lesions and normal oral mucosae were validated. The oral cancer and precancerous lesions could also be differentiated from normal oral mucosae with a specificity of 0.923 and a sensitivity of 0.970. Conclusion The novel quantitative analysis of the intensity and heterogeneity of VELscope® autofluorescence images used in this study in combination with a QDA classifier can be used to differentiate oral cancer and precancerous lesions from normal oral mucosae.

UR - http://www.scopus.com/inward/record.url?scp=85015071020&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015071020&partnerID=8YFLogxK

U2 - 10.1016/j.oraloncology.2017.03.003

DO - 10.1016/j.oraloncology.2017.03.003

M3 - Article

VL - 68

SP - 20

EP - 26

JO - Oral Oncology

JF - Oral Oncology

SN - 1368-8375

ER -