Detection of cervical cancer from evoked tissue fluorescence  images using 2- and 3-way methods

Barry M. Wise; Jeremy M. Shaver

doi:10.1117/12.2516584

Translator Disclaimer

27 February 2019 Detection of cervical cancer from evoked tissue fluorescence images using 2- and 3-way methods

Barry M. Wise, Jeremy M. Shaver

Author Affiliations +

Proceedings Volume 10872, Optical Fibers and Sensors for Medical Diagnostics and Treatment Applications XIX; 1087210 (2019) https://doi.org/10.1117/12.2516584
Event: SPIE BiOS, 2019, San Francisco, California, United States

Abstract

In-vivo examinations of cervical tissue were performed using Evoked Tissue Fluorescence (ETF) as part of a clinical trial. These examinations were performed in conjunction with conventional colposcopy, along with of biopsies of suspect cancerous or pre-cancerous tissue. The ETF data consisted of 22 images of the cervix taken at combinations of 3 excitation wavelengths and 9 emission wavelengths. The ultimate goal was to use these images to accurately classify tissue between normal states (normal squamous and normal columnar) and pre-cancerous and cancerous states (squamous metaplasia, and high and low Squamous Intraepithelial Lesion, HSIL and LSIL). Several chemometric methods were applied to the data for the purpose of preprocessing (e.g. image alignment), eliminating patient to patient variability (e.g. GLS and specialized centering), classification of tissues (hierarchical PLS-DA) and elucidating the underlying signatures of the tissues and background components (PARAFAC).

Citation Download Citation

Barry M. Wise and Jeremy M. Shaver "Detection of cervical cancer from evoked tissue fluorescence images using 2- and 3-way methods ", Proc. SPIE 10872, Optical Fibers and Sensors for Medical Diagnostics and Treatment Applications XIX, 1087210 (27 February 2019); https://doi.org/10.1117/12.2516584

ACCESS THE FULL ARTICLE