Cervical cancer has high morbidity and mortality rates, affecting hundreds of thousands of women worldwide and requiring more accurate screening for early intervention and follow-up treatment. Cytology is the current dominant clinical screening approach, and though it has been used for decades, it has unsatisfactory sensitivity and specificity. In this work, fluorescence lifetime imaging microscopy (FLIM) was used for the imaging of exfoliated cervical cells in which an endogenous coenzyme involved in metabolism, namely, reduced nicotinamide adenine dinucleotide (phosphate) [NAD(P)H], was detected to evaluate the metabolic status of cells. FLIM images from 71 participants were analyzed by the unsupervised machine learning method to build a prediction model for cervical cancer risk. The FLIM method combined with unsupervised machine learning (FLIM-ML) had a sensitivity and specificity of 90.9% and 100%, respectively, significantly higher than those of the cytology approach. One cancer recurrence case was predicted as high-risk several months earlier using this method as compared to using current clinical methods, implying that FLIM-ML may be very helpful for follow-up cancer care. This study illustrates the clinical applicability of FLIM-ML as a detection method for cervical cancer screening and a convenient tool for follow-up cancer care.
Keywords: NAD(P)H; cervical cancer; fluorescence lifetime imaging microscopy; non-invasive screening; unsupervised machine learning.