Boosted Tree Classifier for in Vivo Identification of Early Cervical Cancer using Multispectral Digital Colposcopy

Nilgoon Zarei, Dennis Cox, Pierre Lane, Scott Cantor, Neely Atkinson, Jose-Miguel Yamal, Leonid Fradkin, Daniel Serachitopol, Sylvia Lam, Dirk Niekerk, Dianne Miller, Jessica McAlpine, Kayla Castaneda, Felipe Castaneda, Michele Follen, Calum MacAulay

2017

Abstract

Background: Cervical cancer develops over several years; screening and early diagnosis have decreased the incidence and mortality threefold over the last fifty years. Opportunities for the application of imaging and automation in the screening process exist in settings where resources are limited. Methods: Patients with high-grade squamous intraepithelial lesions (SIL) underwent imaging with a Multispectral Digital Colposcopy (MDC) prior to have a loop excision of the cervix. The image taken with white light was annotated by a clinician. The excised specimen was mapped by the study histopathologist blinded to the MDC data. This map was used to define areas of high grade in the excised tissue. Eleven reviewers mapped the histopathologic data into the MDC images. The reviewers’ maps were analyzed and areas of agreement were calculated. We compared the result of a boosted tree classifier with a previously developed ensemble classifier. Results: Using a boosted tree classifier we obtained a sensitivity of 95%, a specificity of 96%, and an accuracy of 96% on the training sets. When we applied the classifier to a test set, we obtained a sensitivity of 82%, a specificity of 81%, and an accuracy of 81%. The boosted tree classifier performed better than the previously developed ensemble classifier. Conclusion: Here we presented promising results which show that a boosted tree analysis on MDC images is a method that could be used as an adjunct to colposcopy and would result in greater diagnostic accuracy compared to existing methods.

References

  1. World Cancer Research, http://www.wcrf.org/int/cancerfacts-figures/data-specific-cancers/cervical-cancerstatistics (13 September 2016).
  2. Nordstrom, et al., 2001 "Identification of cervical intraepithelial neoplasia (CIN) using UV excited fluorescence and diffuse reflectance tissue spectroscopy." Lasers in Surgery and Medicine 29.2 118-127.
  3. Chang, et al., 2002, "Optimal excitation wavelengths for discrimination of cervical neoplasia." IEEE Transactions on Biomedical Engineering 49.10, 1102- 1111.
  4. Benavides, et al., 2003, "Multispectral digital colposcopy for in vivo detection of cervical cancer." Optics Express 11.10, 1223-1236.
  5. Park, et al., 2005, "Multispectral digital microscopy for in
Download


Paper Citation


in Harvard Style

Zarei N., Cox D., Lane P., Cantor S., Atkinson N., Yamal J., Fradkin L., Serachitopol D., Lam S., Niekerk D., Miller D., McAlpine J., Castaneda K., Castaneda F., Follen M. and MacAulay C. (2017). Boosted Tree Classifier for in Vivo Identification of Early Cervical Cancer using Multispectral Digital Colposcopy . In Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: BIOIMAGING, (BIOSTEC 2017) ISBN 978-989-758-215-8, pages 85-91. DOI: 10.5220/0006148900850091


in Bibtex Style

@conference{bioimaging17,
author={Nilgoon Zarei and Dennis Cox and Pierre Lane and Scott Cantor and Neely Atkinson and Jose-Miguel Yamal and Leonid Fradkin and Daniel Serachitopol and Sylvia Lam and Dirk Niekerk and Dianne Miller and Jessica McAlpine and Kayla Castaneda and Felipe Castaneda and Michele Follen and Calum MacAulay},
title={Boosted Tree Classifier for in Vivo Identification of Early Cervical Cancer using Multispectral Digital Colposcopy},
booktitle={Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: BIOIMAGING, (BIOSTEC 2017)},
year={2017},
pages={85-91},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006148900850091},
isbn={978-989-758-215-8},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 10th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: BIOIMAGING, (BIOSTEC 2017)
TI - Boosted Tree Classifier for in Vivo Identification of Early Cervical Cancer using Multispectral Digital Colposcopy
SN - 978-989-758-215-8
AU - Zarei N.
AU - Cox D.
AU - Lane P.
AU - Cantor S.
AU - Atkinson N.
AU - Yamal J.
AU - Fradkin L.
AU - Serachitopol D.
AU - Lam S.
AU - Niekerk D.
AU - Miller D.
AU - McAlpine J.
AU - Castaneda K.
AU - Castaneda F.
AU - Follen M.
AU - MacAulay C.
PY - 2017
SP - 85
EP - 91
DO - 10.5220/0006148900850091