Can we see epithelium tissue structure below the surface using an optical probe?

This paper answers the question of whether it is possible to detect changes below the surface in epithelium layered structures using a Stochastic Decomposition Method (SDM) that models the scattered light reflected from the layered structure over an area (2-D scan) illuminated by an optical sensor (fibre) emitting light at either one wavelength or with white light. Our technique correlates the differential changes in the reflected tissue texture with the morphological and physical changes that occur in the tissue occurring inside the structure. This work has great potential for detecting changes in mucosal structures and may lead to enhanced endoscopy when the disease is developing to the outside of the mucosal structure and hence becoming hidden during colonoscopy or endoscopic examination. Tests are performed on layered tissue phantoms, and the results obtained show great effectiveness of the model and method in picking up changes in the morphology of the layered tissue phantoms occurring below the surface. We also establish the robustness of the model to changes in viewing depth by testing it on phantoms viewed at different depths. We show that the model is robust to within a 4-mm-deep viewing range.

On-the-fly detection of changes on and below the surface in epithelium mucosal tissue architecture from scattered light.

In this paper we present a technique to raise a flag on the fly when a transition occurs between different mucosal architectures on or below the surface. The segmentation is based on a novel difference metric for detecting an abrupt change in the parameters extracted from a Stochastic Decomposition Method (SDM) that models the scattered light reflected from the mucosal tissue structure over an area (2-D scan) illuminated by an optical sensor (fiber) emitting light at either one wavelength or with white light. This work has the potential to enhance the endoscopist's ability to locate and identify abnormal mucosal architectures in particular when the disease is developing below the surface and hence becoming hidden during colonoscopy or endoscopic examination. It also has also potential in helping deciding as to when and where to take biopsies; steps that should lead to improvement in the diagnostic yield.

Stochastic decomposition method for modeling the scattered signal reflected of mucosal tissues.

The aim of this work is to draw the attention of the biophotonics community to a stochastic decomposition method (SDM) to potentially model 2-D scans of light scattering data from epithelium mucosa tissue. The emphasis in this work is on the proposed model and its theoretical pinning and foundation. Unlike previous works that analyze scattering signal at one spot as a function of wavelength or angle, our method statistically analyzes 2-D scans of light scattering data over an area. This allows for the extraction of texture parameters that correlate with changes in tissue morphology, and physical characteristics such as changes in absorption and scattering characteristics secondary to disease, information that could not be revealed otherwise. The method is tested on simulations, phantom data, and on a limited preliminary in-vitro animal experiment to track mucosal tissue inflammation over time, using the area Az under receiver operating characteristics (ROC) curve as a performance measure. Combination of all the features results in an Az value up to 1 for the simulated data, and Az > 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.

Classification of simulated hyperplastic stages in the breast ducts based on ultrasound RF echo.

Visual inspection of ultrasound is diagnostically limited for characterizing breast tissue, in particular when it comes to visually detecting hyperplasia that forms in the ducts at its early formation (at submillimeter resolution) stages. It can, of course, be seen using biopsies. But this will not be done unless the areas have been flagged using noninvasive modalities. The aim of this paper is to draw to the attention of the medical community (albeit through simulations) that the continuous wavelet transform decomposition (CWTD) that was proven in vivo for tissue characterization before has the potential to flag out simulated hyperplasia data at submillimeter resolutions. And it might be an excellent candidate for detecting in vivo hyperplastic changes in the breast. To the best of our knowledge, this is the first attempt at studying the potential of detecting cell growth in breast ducts using ultrasound. The stochastic decomposition model (the CWTD) of the RF echo with its coherent and diffuse components, yields image parameters that correlate closely with the structural parameters of the (simulated) hyperplastic stages of the breast tissue. The discrimination power of the various parameters is studied under a host of conditions, such as varying resolution, depth, and coherent to diffuse energy ratio (CDR) values using a point-scatterer model simulator that mimics epithelium hyperplastic growth in the breast ducts. These are shown to be useful for detecting the various types of simulated hyperplastic data. Careful analysis shows that three parameters, in particular the number of coherent scatterers, the Rayleigh scattering degree, and the energy of the diffuse scatterers, are most sensitive to variations in the hyperplastic simulated data. And they show very high ability to discriminate between various stages of simulated hyperplasia, even in cases of low resolution and low CDR values. Using the area under the receiver operating characteristics (ROC) curve (A(z)) as the performance metric, values of A(z) > 0.942 are obtained when discriminating between stages for resolution 0.948 for different duct densities.

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.

Classification of the stages of hyperplasia in breast ducts by analyzing different depths and segmentation of ultrasound breast scans into ductal areas.

In this paper, we study in depth the potential of detection of epithelium hyperplastic growth in the breast ducts leading to early breast cancer detection. Towards that end, we use a stochastic decomposition algorithm of the RF echo into its coherent and diffuse components that yields image parameters related to the structural parameters of the hyperplastic stages of the breast tissue. Previously, we proved that the two parameters, in particular the number of coherent scatterers and the Rayleigh scattering degree show very high ability to discriminate between various stages of hyperplasia even in cases of low resolution and low SNR values. In this paper, the discrimination power of the other parameters is studied further considering different depths using a point scatterer model simulator that mimics epithelium hyperplastic growth in the breast ducts. Significant improvement is obtained in the performance with the newly adopted method considering depth. Values of Az up to 0.974 are obtained when discriminating between pairs of stages using the parameter residual error variance. In addition, this paper presents a fast nonparametric segmentation procedure to locate the ducts illustrated using phantom data. The performance of the segmentation procedure is obtained as Az>0.948 for various regions of breast scans.