Volumetric analysis framework for accurate segmentation and classification (VAF-ASC) of lung tumor from CT images

Abstract

Lung tumor can be typically stated as the abnormal cell growth in lungs that may cause severe threat to patient health, since lung is a significant organ which comprises associated network of blood veins and lymphatic canals. The earlier detection and classification of lung tumor creates a greater impact on increasing the survival rate of patients. For analysis, the Computed Tomography (CT) lung images are broadly used, since it gives information about the various lung regions. The prediction of tumor contour, position, and volume plays an imperative role in accurate segmentation and classification of tumor cells. This will aid in successful tumor stage detection and treatment phases. With that concern, this paper develops a Volumetric Analysis Framework for Accurate Segmentation and Classification of lung tumors. The volumetric analysis framework comprises the estimation of length, thickness, and height of the detected tumor cell for achieving précised results. Though there are many models for tumor detection from 2D CT inputs, it is very important to develop a method for lung nodule separation from noisy background. For that, this paper connectivity and locality features of the lung image pixels. Moreover, morphological processing techniques are incorporated for removing the additional noises and airways. Tumor segmentation has been accomplished by the k-means clustering approach. Tumor Nodule Metastasis classification based-volumetric analysis is performed for accurate results. The Volumetric Analysis Framework provides better results with respect to factors such as accuracy rate of tumor diagnosis, reduced computation time, and appropriate tumor stage classification.