A novel lung tumor detection technique using Fast Greedy Snake algorithm.

Lung tumors are a type of growth in the lung which can be categorized as Non – Small cell lung cancer and Small cell lung cancer depending on the size of the cell as observed under a microscope. Non – Small cell lung cancer is more commonly found in people than the Small cell lung cancer. Tumors that are detected at an earlier stage have more chances of getting treated at a faster period of time, however if left undetected and undiagnosed for so long, it might lead to various impediments. As a fact, the traditional methods used for diagnosing is time consuming and have chances of errors. Thus a non – invasive method of diagnosing has been studied and discussed. In the proposed study, PET-CT images have been collected from databases and used in the Fast Greedy Snake algorithm. The aim and objectives of study is to segment tumor region in the lung images using Fast Greedy Snakes Algorithm (FGSA), to extract the GLCM features from the region segmented and to perform classification. As a result of the study, the proposed Fast Greedy Snake Algorithm provides an accurate segmentation in the lung images. Some Statistical features like mean, kurtosis, correlation, Entropy, Skewness and standard deviation have been studied and compared between the normal and abnormal images; and the results have been recorded. Thus a most precise and fast programmed method has been implemented to segment the lung tumor images using Fast Greedy snakes algorithm. [ABSTRACT FROM AUTHOR]