Cancer diagnosis by nuclear morphometry using spatial information

• Relationship between majority voting and likelihood ratio test methods are derived.
• Statistical dependency shown between samples in thyroid tissue nuclei.
• A method for set classification that exploits statistical dependencies is derived.
• The method is an alternative to the majority voting approach for classifying sets.
• The efficacy of the method is shown with real data for cancer detection.

Methods for extracting quantitative information regarding nuclear morphology from histopathology images have been long used to aid pathologists in determining the degree of differentiation in numerous malignancies. Most methods currently in use, however, employ the naïve Bayes approach to classify a set of nuclear measurements extracted from one patient. Hence, the statistical dependency between the samples (nuclear measurements) is often not directly taken into account. Here we describe a method that makes use of statistical dependency between samples in thyroid tissue to improve patient classification accuracies with respect to standard naïve Bayes approaches. We report results in two sample diagnostic challenges.