论文信息 - An intelligent lung cancer diagnosis system using cuckoo search optimization and support vector machine classifier

An intelligent lung cancer diagnosis system using cuckoo search optimization and support vector machine classifier

One of the leading causes of cancer death for both men and women is the lung cancer. The best way to improve the patient’s chances for survival is the early detection of potentially cancerous cells. But, the conventional systems fails to segment the cancerous cells of various types namely, well-circumscribed, juxta-pleural, juxta-vascular and pleural-tail at its early stage (i.e., less than 3 mm) that leads to less classification accuracy. It is also noted that none of the existing systems achieved accuracy more than 98%. In this paper, we propose an optimal diagnosis system not only for early detection of lung cancer nodules and also to improve the accuracy in Fog computing environment. The Fog environment is used for storage of the high volume CT scanned images to achieve high privacy, low latency and mobility support. In our approach, for the accurate segmentation of Region of Interest (ROI), the hybrid technique namely Fuzzy C-Means (FCM) and region growing segmentation algorithms are used. Then, the important features of the nodule of interest such as geometric, texture and statistical or intensity features are extracted. From the above extracted features, the optimal features used for the classification of lung cancer are identified using the Cuckoo search optimization algorithm. Finally, the SVM classifier is trained using these optimal features, which in turn helps us to classify the lung cancer as either of type benign or malignant. The accuracy of the proposed system is tested using Early Lung Cancer Action Program (ELCAP) public database CT lung images. The total sensitivity and specificity attained in our system for the above said database are 98.13 and 98.79% respectively. This results in a mean accuracy of 98.51% for training and testing in a sample of 103 nodules occurring in 50 exams. The rate of false positives per exam was 0.109. Also, a high receiver operating characteristic (ROC) of 0.9962 has been achieved.

[1] James C. Bezdek,et al. A comparison of neural network and fuzzy clustering techniques in segmenting magnetic resonance images of the brain , 1992, IEEE Trans. Neural Networks.

[2] Shinichi Tamura,et al. Automated lung segmentation and smoothing techniques for inclusion of juxtapleural nodules and pulmonary vessels on chest CT images , 2014, Biomed. Signal Process. Control..

[3] Catherine Beigelman-Aubry,et al. Management of an incidentally discovered pulmonary nodule , 2007, European Radiology.

[4] O. Miettinen,et al. Survival of Patients with Stage I Lung Cancer Detected on CT Screening , 2008 .

[5] R. Capocaccia,et al. Life expectancy and cancer survival in the EUROCARE-3 cancer registry areas. , 2003, Annals of oncology : official journal of the European Society for Medical Oncology.

[6] E. Hoffman,et al. Assessment of the pulmonary structure-function relationship and clinical outcomes measures: quantitative volumetric CT of the lung. , 1997, Academic radiology.

[7] Nello Cristianini,et al. An introduction to Support Vector Machines , 2000 .

[8] Rashmee Kohad,et al. Diagnosis of Lung Cancer Using Support Vector Machine with Ant Colony Optimization Technique , 2014 .

[9] D. Asir Antony Gnana Singh,et al. Enhancing the Performance of Classifier Using Particle Swarm Optimization (PSO) - based Dimensionality Reduction , 2015 .

[10] Eric A. Hoffman,et al. Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images , 2001, IEEE Transactions on Medical Imaging.

[11] Ezzeddine Zagrouba,et al. Improved Fuzzy-c-means for Noisy Image Segmentation , 2009, SIGMAP.

[12] S. Armato,et al. Computerized detection of pulmonary nodules on CT scans. , 1999, Radiographics : a review publication of the Radiological Society of North America, Inc.

[13] Rahimeh Rouhi,et al. Classification of benign and malignant breast tumors based on hybrid level set segmentation , 2016, Expert Syst. Appl..

[14] Xin-She Yang,et al. Cuckoo Search via Lévy flights , 2009, 2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).

[15] Mohammed Azmi Al-Betar,et al. A survey on applications and variants of the cuckoo search algorithm , 2017, Appl. Soft Comput..

[16] Anselmo Cardoso de Paiva,et al. Automatic detection of small lung nodules in 3D CT data using Gaussian mixture models, Tsallis entropy and SVM , 2014, Eng. Appl. Artif. Intell..

[17] Abbas Z. Kouzani,et al. Random forest based lung nodule classification aided by clustering , 2010, Comput. Medical Imaging Graph..

[18] N. Otsu. A threshold selection method from gray level histograms , 1979 .

[19] C. Kavitha,et al. Classification of Lung Cancer Nodules using SVM Kernels , 2014 .

[20] Chih-Jen Lin,et al. LIBSVM: A library for support vector machines , 2011, TIST.

[21] Ajoy Kumar Ray,et al. Hybrid segmentation, characterization and classification of basal cell nuclei from histopathological images of normal oral mucosa and oral submucous fibrosis , 2012, Expert Syst. Appl..

[22] V. Vapnik. Estimation of Dependences Based on Empirical Data , 2006 .

[23] Chandan Chakraborty,et al. Automated classification of cells in sub-epithelial connective tissue of oral sub-mucous fibrosis - An SVM based approach , 2009, Comput. Biol. Medicine.

[24] Berkman Sahiner,et al. Lung nodule detection on thoracic computed tomography images: preliminary evaluation of a computer-aided diagnosis system. , 2002, Medical physics.