Stochastic decomposition method for detection of epithelium dysplasia and inflammation using white light spectroscopy imaging.

In this paper, we present a stochastic decomposition method (SDM) that allows the detection of dysplasia in epithelial tissue using white-light spectroscopy imaging. The main goal is to extract the data from the decomposition which will lead to the construction of a feature parameter space corresponding to changes in the tissue morphology related to formation of dysplasia and inflammation. These parameters include the number and mean energy of coherent scatterers; deviation from Rayleigh scattering; residual error variance of the diffuse component; and normalized correlation coefficient. The tests are performed on tissue-mimicking phantom data and tissue data collected from mouse colon in vitro. The obtained results demonstrate effectiveness of the method in differentiating between tissue structures with different cell morphologies. The results are shown by fusing all the estimated parameter set together and also using each parameter separately. Combination of all the features results in an Az value higher than 0.927 for the phantom data. For the tissue data, the best performances for differentiation between pairs of various levels of inflammation are 0.859, 0.983, and 0.999.