Lung Cancer Detection Using Fuzzy Auto-Seed Cluster Means Morphological Segmentation and SVM Classifier

2016 ◽  
Vol 40 (7) ◽  
Author(s):  
T. Manikandan ◽  
N. Bharathi

Lung Cancer is a disease of irregular cells multiplying and growing into a tumour. It’s hard to believe, but lung cancer is the primary cause of cancer deaths among both women and men. Every year more people die of lung cancer than of colon, prostate and Breast cancers. Some important facts of lung cancer are Excluding Skin cancer, lung cancer is the second most common cancer in both women and men. Statistics from Indian Council of Medical Research (ICMR) recommend that lung cancer is fast turning into a plague in India. It is a high mortality cancer due to poor access to affordable health care and diagnosis at late stage. At the time of diagnosis only 15 percent of the cases of lung cancer are curable. Due to the nature of the disease patients with lung cancer present themselves for diagnosis at a much later stage than other cancers. Globally lung cancer accounts for 8.4% percent of all cancers in women and 14.5% in men. For lung cancer Smoking is the single largest contributor. Other causes are exposure to carcinogenic toxins like radon, asbestos, radiation and air pollutants. Exposure to women to smoke from the burning of charcoal for cooking is also a cause of lung cancer. About 20 percent we can reduce the risk of lung cancer by doing physical activities and exercise is known to improve lung function. In recent times, image processing measures are frequently used in a number of medical areas for enlargement of the image in preceding recognition and managing periods, where the instant aspect is really important to determine the abnormality problems in objective figures, mainly in a variety of malignancy tumours such as lung cancer, breast cancer etc


Image classification is one of the major issues of image pre-processing approach. To resolve this issue a large number of classification approaches has been developed. In this work, a novel SVM-FA (support vector machine optimized with firefly approach) classifier is developed for detecting the lung cancer on the basis of the CT images. Lung cancer is considered one of the most critical and vital. Thus the early analysis of such kind of disease is required. For this purpose, the study implements the image pre-processing (filtration and segmentation) techniques to the input CT scan images. Then the SVM classifier, optimized with firefly approach is applied to the pre-processed data. The target of the work is to enhance the accuracy in the final prediction or output. For evaluating the proficiency level of the proposed SVM-FA approach, a comparison analysis is also performed in this work. The comparison is done among proposed work, traditional work and SVM classifier. On the basis of the obtained facts and figures, the proposed work is found to be effective and efficient in terms of the accuracy (96%) and specificity (83.333%) respectively


Lung cancer is the foremost cause of cancer-related deaths world-wide [1]. It affects 100,000 Americans of the smoking population every year of all age groups, particularly those above 50 years of the smoking population [2]. In India, 51,000 lung cancer deaths were reported in 2012, which include 41,000 men and 10,000 women [3]. It is the leading cause of cancer deaths in men; however, in women, it ranked ninth among all cancerous deaths [4]. It is possible to detect the lung cancer at a very early stage, providing a much higher chance of survival for the patients.


Sign in / Sign up

Export Citation Format

Share Document