Adaptive spectral window sizes for extraction of diagnostic features from optical spectra.

We present an approach to adaptively adjust the spectral window sizes for optical spectra feature extraction. Previous studies extracted features from spectral windows of a fixed width. In our algorithm, piecewise linear regression is used to adaptively adjust the window sizes to find the maximum window size with reasonable linear fit with the spectrum.

Reducing variability in the output of pattern classifiers using histogram shaping.

Purpose: The authors present a novel technique based on histogram shaping to reduce the variability in the output and (sensitivity, specificity) pairs of pattern classifiers with identical ROC curves, but differently distributed outputs.

Methods: The authors identify different sources of variability in the output of linear pattern classifiers with identical ROC curves, which also result in classifiers with differently distributed outputs. They theoretically develop a novel technique based on the matching of the histograms of these differently distributed pattern classifier outputs to reduce the variability in their (sensitivity, specificity) pairs at fixed decision thresholds, and to reduce the variability in their actual output values.

Indexes for three-class classification performance assessment--an empirical comparison.

Assessment of classifier performance is critical for fair comparison of methods, including considering alternative models or parameters during system design. The assessment must not only provide meaningful data on the classifier efficacy, but it must do so in a concise and clear manner. For two-class classification problems, receiver operating characteristic analysis provides a clear and concise assessment methodology for reporting performance and comparing competing systems.

Effect of normalization methods on biomarker identification utilizing mass spectrometry.

In biomarker identification using mass spectrometry, normalization makes it possible to compare mass spectra obtained from different samples. However, the relative influence of different normalization methods is an unexplored topic. In this study, we compared the most widely used normalization methods in a systemic manner to investigate impact of normalization.

Comparison of linear and non-linear classifiers for oral cancer screening by optical spectroscopy.

We compared the use of linear discriminant analysis and an artificial neural network for classifying optical spectral measurements of oral sites. Consistent with studies of optical spectroscopy for diagnosis of other forms of cancer, our results suggest that a non-linear classifier may be warranted. Our study also demonstrated that the classifiers were better able to distinguish between sites that were more histopathologically distinct.

Probing local tissue changes in the oral cavity for early detection of cancer using oblique polarized reflectance spectroscopy: a pilot clinical trial.

We report the results of an oral cavity pilot clinical trial to detect early precancer and cancer using a fiber optic probe with obliquely oriented collection fibers that preferentially probe local tissue morphology and heterogeneity using oblique polarized reflectance spectroscopy (OPRS). We extract epithelial cell nuclear sizes and 10 spectral features. These features are analyzed independently and in combination to assess the best metrics for separation of diagnostic classes.