Skip to main content

Image processing and machine learning techniques to automate diagnosis of Lugol's iodine cervigrams for a low-cost point-of-care digital colposcope

Publication ,  Conference
Asiedu, MN; Simhal, A; Lam, CT; Mueller, J; Chaudhary, U; Schmitt, JW; Sapiro, G; Ramanujam, N
Published in: Progress in Biomedical Optics and Imaging - Proceedings of SPIE
January 1, 2018

The world health organization recommends visual inspection with acetic acid (VIA) and/or Lugol's Iodine (VILI) for cervical cancer screening in low-resource settings. Human interpretation of diagnostic indicators for visual inspection is qualitative, subjective, and has high inter-observer discordance, which could lead both to adverse outcomes for the patient and unnecessary follow-ups. In this work, we a simple method for automatic feature extraction and classification for Lugol's Iodine cervigrams acquired with a low-cost, miniature, digital colposcope. Algorithms to preprocess expert physician-labelled cervigrams and to extract simple but powerful color-based features are introduced. The features are used to train a support vector machine model to classify cervigrams based on expert physician labels. The selected framework achieved a sensitivity, specificity, and accuracy of 89.2%, 66.7% and 80.6% with majority diagnosis of the expert physicians in discriminating cervical intraepithelial neoplasia (CIN +) relative to normal tissues. The proposed classifier also achieved an area under the curve of 84 when trained with majority diagnosis of the expert physicians. The results suggest that utilizing simple color-based features may enable unbiased automation of VILI cervigrams, opening the door to a full system of low-cost data acquisition complemented with automatic interpretation.

Duke Scholars

Published In

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

DOI

ISSN

1605-7422

ISBN

9781510614550

Publication Date

January 1, 2018

Volume

10485
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Asiedu, M. N., Simhal, A., Lam, C. T., Mueller, J., Chaudhary, U., Schmitt, J. W., … Ramanujam, N. (2018). Image processing and machine learning techniques to automate diagnosis of Lugol's iodine cervigrams for a low-cost point-of-care digital colposcope. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 10485). https://doi.org/10.1117/12.2282792
Asiedu, M. N., A. Simhal, C. T. Lam, J. Mueller, U. Chaudhary, J. W. Schmitt, G. Sapiro, and N. Ramanujam. “Image processing and machine learning techniques to automate diagnosis of Lugol's iodine cervigrams for a low-cost point-of-care digital colposcope.” In Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol. 10485, 2018. https://doi.org/10.1117/12.2282792.
Asiedu MN, Simhal A, Lam CT, Mueller J, Chaudhary U, Schmitt JW, et al. Image processing and machine learning techniques to automate diagnosis of Lugol's iodine cervigrams for a low-cost point-of-care digital colposcope. In: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2018.
Asiedu, M. N., et al. “Image processing and machine learning techniques to automate diagnosis of Lugol's iodine cervigrams for a low-cost point-of-care digital colposcope.” Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10485, 2018. Scopus, doi:10.1117/12.2282792.
Asiedu MN, Simhal A, Lam CT, Mueller J, Chaudhary U, Schmitt JW, Sapiro G, Ramanujam N. Image processing and machine learning techniques to automate diagnosis of Lugol's iodine cervigrams for a low-cost point-of-care digital colposcope. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2018.

Published In

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

DOI

ISSN

1605-7422

ISBN

9781510614550

Publication Date

January 1, 2018

Volume

10485