Automated biochemical, morphological, and organizational assessment of precancerous changes from endogenous two-photon fluorescence images.

Abstract

Multi-photon fluorescence microscopy techniques allow for non-invasive interrogation of live samples in their native environment. These methods are particularly appealing for identifying pre-cancers because they are sensitive to the early changes that occur on the microscopic scale and can provide additional information not available using conventional screening techniques.In this study, we developed novel automated approaches, which can be employed for the real-time analysis of two-photon fluorescence images, to non-invasively discriminate between normal and pre-cancerous/HPV-immortalized engineered tissues by concurrently assessing metabolic activity, morphology, organization, and keratin localization. Specifically, we found that the metabolic activity was significantly enhanced and more uniform throughout the depths of the HPV-immortalized epithelia, based on our extraction of the NADH and FAD fluorescence contributions. Furthermore, we were able to separate the keratin contribution from metabolic enzymes to improve the redox estimates and to use the keratin localization as a means to discriminate between tissue types. To assess morphology and organization, Fourier-based, power spectral density (PSD) approaches were employed. The nuclear size distribution throughout the epithelial depths was quantified by evaluating the variance of the corresponding spatial frequencies, which was found to be greater in the normal tissue compared to the HPV-immortalized tissues. The PSD was also used to calculate the Hurst parameter to identify the level of organization in the tissues, assuming a fractal model for the fluorescence intensity fluctuations within a field. We found the range of organization was greater in the normal tissue and closely related to the level of differentiation.A wealth of complementary morphological, biochemical and organizational tissue parameters can be extracted from high resolution images that are acquired based entirely on endogenous sources of contrast. They are promising diagnostic parameters for the non-invasive identification of early cancerous changes and could improve significantly diagnosis and treatment for numerous patients.