RESEARCH ARTICLE Lung computed axial tomography image segmentation using possibilistic fuzzy C-means approach for computer aided diagnosis system Tharcis Paulraj 1 | Kezi Selva Vijila Chelliah 1 | Sundar Chinnasamy 2 1 Department of Electronics and Communication Engineering, Christian College of Engineering & Technology, Dindigul, Tamilnadu, India 2 Department of Computer Science and Engineering, Christian College of Engineering & Technology, Dindigul, Tamilnadu, India Correspondence Sundar Chinnasamy, Department of Computer Science and Engineering, Christian College of Engineering & Technology, Dindigul, Tamilnadu, India. Email: sundarc007@yahoo.com Abstract Soft computing is an associate rising field that plays a crucial half in the area of engineering and science. One of the most significant applications of soft computing is image segmentation. It focuses on an exploiting tolerance of imprecision and uncertainty. Segmentation supported soft computing remains a difficult task within the medical field. Medical images are habitually used in the segmentation process to extract the meaningful portions and to know and clarify the condition of the par- ticular patient. In this article, we implement an efficient possibilistic fuzzy C-means (PFCM) approach to segment the lung portion in the computed tomography (CT) image and the result shows that it improves the segmentation accuracy upto 98.5012% and results are compared with existing segmenting approaches like fuzzy possibilistic C-means method, fuzzy bitplane method and so forth. Also, the PFCM approach increases the diagnostic accuracy of the computer aided diagnosis system using CT images. The radiologist may utilize this computer aided diagnosis system results as a second opinion of their diagnosed results. KEYWORDS computed tomography, computer-aided diagnosis system, fuzzy possibilistic C-means method, possibilistic fuzzy C-means method 1 | INTRODUCTION Medical imaging segmentation is a vital assignment of know-how and analysis of image. Within the subject of clin- ical imaging, segmentation is a necessary extraordinary half of part of getting meaningful portions of the images. In advance, the length segmentation will be carried out manually and it has a few meaningless enveloped elements of Images. Segmenting lung images automatically needs the help of algo- rithms which may be resolved by a way of logical calculations and provide efficiently segmented quantities. Gomathi and Thangaraj 1 explained that the lung computed tomography (CT) images are efficaciously utilized for analysis cause as it has been efficaciously inspected the chest diseases, lung, most cancers, pneumonia, tuberculosis and pulmonary emphysema. The extraordinary growth of lung tissues goes to make lung severe, causing most cancers loss of life of an individual. Chin-Wei and Rajeswari 2 defined most rarely used soft Computing techniques, which are particle swarm optimiza- tion and simulated annealing techniques. Some of the regu- larly used computing processes are fuzzy-based approaches, neural network-based techniques and genetic algorithm- based methods. Usually, computing approaches are for seg- mentation and classification of medical abnormalities. In this article, we explain the soft computing-based segmentation approach to enhance the accuracy of image segmentation and the simulation results has been presented and compared with the existing segmentation approaches. Received: 11 August 2018 Revised: 3 May 2019 Accepted: 8 May 2019 DOI: 10.1002/ima.22340 Int J Imaging Syst Technol. 2019;1–8. wileyonlinelibrary.com/journal/ima © 2019 Wiley Periodicals, Inc. 1