Stomach Cancer Diagnosis by Using a Combination of Image Processing Algorithms, Local Binary Pattern Algorithm and Support Vector Machine
Danial Ahmadzadeh, Mohammad Fiuzy, Javad Haddadnia · 2013
Although the amount of stomach cancer has reduced obviously during last decades in western countries, but this illness is still one of the main causes of death in developing countries. In Iran , stomach cancer is one of the most common illness in some areas like northwest and northeast . In this study we aim to suggest a new way for diagnosing this illness. One of the main problems with this illness is that the diagnosis process doesn’t take place at the right time. Nowadays doctors try to diagnose this illness on the basis of their experiences, knowledge, and complicated surveys but all humans have error in their works. Data in this study are selected from 55 subjects (selected randomly). By using image processing and artificial intelligence algorithms like primary preprocessors for increasing the quality and statistical characteristics of image, local binary pattern algorithm for elicit characteristics, image histogram algorithm to elicit impaired characteristics and support vector machine has been used for accurate classification among impaired and suspected subjects and also for accurate diagnosis of impairment. The suggested system by using a combination of mentioned methods was succeed to achieve 91.8% accurate diagnosis. Although available methods are accurate but they are really expensive and time consuming, by comparing this method with those mentioned above are will have a better understanding of its accuracy and usefulness.