Parametric data mining and diagnostic rules for digital thermographs in breast cancer

Abstract

In this study, a novel data mining algorithm and parametric analysis protocol were utilized for generating knowledge-based diagnostic rules for infrared thermographs. First, Beier-Neely field morphing and linear affine transformation algorithms were used in geometric standardization for the whole body and partial region respectively. Gray levels of thermal images at same anatomical coordinates in the abnormal regions were then analyzed to determine upper and lower limits for diagnosis. Twenty-five parameters were extracted from each abnormal region for parametric analysis, and decision trees were used to generate the knowledge-based diagnostic rules. A total of 71 and 131 female patients with and without breast cancer respectively were both analyzed in this study. Experimental results indicated that a total of 1750 abnormal regions (703 positive and 1047 negative) were detected. Sixty one positive abnormal regions (61/703=8.6%) from 44 cancer patients (42/71=59.2%) can be found in the abovementioned 14 branches.