A Fusion Technique Based on Image - Statistical Analysis for Detection of Throat Cancer Types

The aim of this study is to establish a simple approach to classify the throat tumor type by using statistical analysis techniques without a need for a biopsy or further testing. In this study, around 35 patients were investigated to be classified and to provide appropriate diagnostic for the throat cancer type. MRI images and their properties were processed and converted into number of pixels and intensities that located in the region of interest which covered the area of tumor. This extracted information was employed by traditional statistical methods such as Descriptive Analysis, Box Plots and Testing of Hypothesis to enable reasonable accuracy in differentiation between the tumor types. As a result of this study, it is observed that the using of statistical analysis for the data taken from the MRI images is reliable to diagnose and determine the type of the throat cancer with 95% confidence.