Hyperspectral microscopy-based label-free semi-automatic segmentation of eye tissues

Abstract

Fluorescence microscopic imaging of tissues is widely used for pathological diagnosis of diseases and biomedical research purposes. In addition to the exogenous fluorescent signal that is targeted for analysis, some molecules within biological tissues exhibit intrinsic fluorescence referred to as autofluorescence. This tissue optical property interferes with the detection and quantification of the fluorescent signal used to detect and assess biological tissues. To overcome this, hyperspectral imagers with increased spectral and spatial resolution have the capacity to provide greater structural and molecular information. Algorithm-based analysis platforms capable of analyzing large biomedical hyperspectral datasets are unmet needs and can extract useful spectral-spatial information from complex tissues. We present an open-source data analysis approach to exploit the potential of hyperspectral autofluorescence imaging and to extract unbiased and useful spectral-spatial information from the eye. Using an Image Mapping Spectrometer (from 528 nm to 836 nm); mounted on a fluorescence microscope, a non-destructive and label-free approach to evaluate the retina, choroid, and scleral tissues in eye sections is presented. The segmentation of the tissues is based on their respective autofluorescence spectral profiles and are compared using Analysis of Variance (ANOVA) and functional ANOVA. We demonstrate distinctly different autofluorescence spectra for individual eye tissue types. Furthermore, the systematic segmentation method is used to classify tissue types based on their divergent autofluorescence spectra. This study provides the metrics for further construction of spectral profile signatures in eye conditions and diseases. Furthermore, this hyperspectral-based semi-automatic segmentation approach can be expanded for application to other tissues in health and disease.