Suspicious volumetric tumor (SVT) segmentation of a CT-image (CTi) and analysing changes in the volume of tumor is a significantly challenging task for the identification of lung cancer. In this regard, we design a two-step suspicious volumetric tumor segmentation (SVTS) approach based on an adaptive multiple resolution contour (AMRC) models for effective SVT segmentation. First, the high-intensity-pixels edge centroid of SVT (HECS) method is designed to identify the SVT location in CTi, and these outcomes are subsequently conceding threshold values to fix the level set method (LSM). Second, HECS outcomes are recognised using particle swarm optimisation (PSO) which is harmonised twin support vector machines (TSVM) to achieve segmentation accuracy. An open-source tumor cancer imaging archive (TCIA) dataset, 529 abnormal tissues (ATs) of the lung from the lung image database consortium (LIDC), are conceded to assess the performance of the SVT segmentation approach. The average segmentation accuracy of NLTC, TCIA, and LIDC datasets are 73.19%, 76.21% and 75.89%, respectively, compared with standard benchmark approaches. Subsequently, our framework efficiently classified the normal and abnormal CTi based on the SVT segmentation accuracy rate.