Current Medical Imaging Reviews      Usama Ijaz Bajwa 1,* , Abdullah Ali Shah 2 , Muhammad Waqas Anwar 1 , Ghulam Gilanie 1 and Asma Ejaz Bajwa 3 1 Department of Computer Science, COMSATS Institute of Information Technology, Lahore, Pakistan; 2 Asad Tech House (Private) Limited, Islamabad, Pakistan; 3 Pathology Department, Shalamar Medical and Dental College, Lahore, Pakistan A R T I C L E H I S T O R Y Received: June 13, 2016 Revised: May 31, 2017 Accepted: June 04, 2017 DOI: 10.2174/1573405613666170614083951 Abstract: Backgroud: Lung cancer is the most common cancer in terms of both incidence and mortality. Where medical science is playing its role to overcome this deadly disease, new ad- vancements’s and research areis also going on in computer science especially in the domain of im- age processing to support doctors and radiologists to tackle it. Developments are going on in image processing and CAD evaluation for applications that include cancer screening, diagnosis, and im- age-guided intervention, and treatment. Methods: The most efficient way to stop the cancer is to detect and diagnose it at an early stage. Most of the existing CAD systems monitor the growth of lung nodules over a period of time, which is not possible at the early stage of lung cancer. In case of lung cancer treatment in Pakistan, even if the cancer is at later stages, there are no such archives in which the history of patient is main- tained. So in that case, it becomes extremely important to develop such system which detects lung cancer at its early stage without depending on the requirement of patient history. Secondly, major- ity of the CAD systems require training prior to use and after the training, they still cannot’t pro- duce satisfactory results. And the last point is most of the scanners comes with built-in software and most of the scanners do notesn’t support third party software’s. Results: In this study, a CAD system is proposed for the detection of malignant nodules through traditional image processing techniques fused with the techniques used by radiologists. The system goes through three main phases; pre-processing, segmentation and 3D reconstruction. In the first phase, pre-processing techniques weare used to remove unwanted information and enhance the im- age for further processing. During the second phase, the nodule wais detected and localized and in the last phase, 3D reconstruction of the nodule is performed for better visualization that supports the radiologist and the surgeon/doctor. At By the end of the study, we have discussed the perform- ance of our CAD system on LIDC dataset. Discussion: This dataset consists of 1018 cases from which we randomly selected 340 cases and compared the results of our methodology using four different scenarios against studies which have used Artificial Neural Networks (ANN) and Support Vector Machine (SVM). Conclusion: The methodology used in this study, clearly outperforms in two out of the four scenar- ios when compared to ANN and SVM. Keywords: Lung cancer detection, CT slices, computer aided detection, malignant lung nodules, LIDC dataset, SVM. 1. INTRODUCTION Cancer, also known as malignant tumor, is a group of diseases in which the growth and spreading of abnormal cells cannot be controlled and can invade or extend to other areas of the body, resulting in death [1, 2]. In developed countries, the disease which is leading cause of death is can- cer and in developing countries, it is the second leading *Address correspondenc to this author at the Department of Computer Sci- ence, COMSATS Institute of Information Technology, Lahore, Pakistan; E-mails: usamabajwa@ciitlahore.edu.pk, usama@usamaijaz.com cause of mortalities exceeded only by heart diseases [2]. If we divide cancer into sites (according to body parts) and check the statistics, lung cancer is the most common cancer in terms of both the occurrence and mortality [2]. The lead- ing cause of lung cancer is smoking and it is believed that 90% of lung cancer cases and deaths are caused by it. Other risk factors are Second Hand Smoke (SHS), asbestos expo- sure, cancer causing agents, radon, family history and air pollution [3]. As we know, tobacco is the main contributor to lung cancer. Unfortunately, Pakistan is one of the countries where tobacco epidemic has been established recently and 1875-6603/18 $58.00+.00 ©2018 Bentham Science Publishers Send Orders for Reprints to reprints@benthamscience.ae 422 Current Medical Imaging Reviews, 2018, 14, 422-429 RESEARCH ARTICLE Computer-Aided Detection (CADe) System for Detection of Malignant Lung Nodules in CT Slices - a Key for Early Lung Cancer Detection