Computer-aided diagnosis system for lung nodules based on computed tomography using shape analysis, a genetic algorithm, and SVM

Abstract Lung cancer is the major cause of death among patients with cancer worldwide. This work is intended to develop a methodology for the diagnosis of lung nodules using images from the Image Database Consortium and Image Database Resource Initiative (LIDC–IDRI). The proposed methodology uses image processing and pattern recognition techniques. To differentiate the patterns of malignant and benign forms, we used a Minkowski functional, distance measures, representation of the vector of points measures, triangulation measures, and Feret diameters. Finally, we applied a genetic algorithm to select the best model and a support vector machine for classification. In the test stage, we applied the proposed methodology to 1405 (394 malignant and 1011 benign) nodules from the LIDC–IDRI database. The proposed methodology shows promising results for diagnosis of malignant and benign forms, achieving accuracy of 93.19 %, sensitivity of 92.75 %, and specificity of 93.33 %. The results are promising and demonstrate a good rate of correct detections using the shape features. Because early detection allows faster therapeutic intervention, and thus a more favorable prognosis for the patient, herein we propose a methodology that contributes to the area.

[1]  J. P. J. de Valk,et al.  Analysis of eye fixations during the diagnostic interpretation of chest radiographs , 2006, Medical and Biological Engineering and Computing.

[2]  Abhir Bhalerao,et al.  Integral geometry descriptors for characterizing emphysema and lung fibrosis in HRCT images , 2008 .

[3]  Jacob D. Furst,et al.  Content-based versus semantic-based retrieval: an LIDC case study , 2009, Medical Imaging.

[4]  Naif Alajlan,et al.  Shape retrieval using triangle-area representation and dynamic space warping , 2007, Pattern Recognit..

[5]  P. Vanathi,et al.  Robust and Automated Lung Nodule Diagnosis from CT Images Based on Fuzzy Systems , 2011, 2011 International Conference on Process Automation, Control and Computing.

[6]  Naif Alajlan,et al.  Multi-object image retrieval based on shape and topology , 2006, Signal Process. Image Commun..

[7]  M D Seemann,et al.  Differentiation of malignant from benign solitary pulmonary lesions using chest radiography, spiral CT and HRCT. , 2000, Lung cancer.

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

[9]  T. Buchert,et al.  Robust Morphological Measures for Large-Scale Structure in the Universe , 1993 .

[10]  J. Hair.  Multivariate data analysis , 1972 .

[11]  Feng Li,et al.  Mass screening for lung cancer with mobile spiral computed tomography scanner , 1998, The Lancet.

[12]  J C Froment,et al.  Primary tumours of the trachea. a clinical, radiological and pathologic evaluation of 12 cases. , 1981, European journal of radiology.

[13]  Xiaolu Yang,et al.  An Improved Median-based Otsu Image Thresholding Algorithm , 2012 .

[14]  Anselmo Cardoso de Paiva,et al.  Lung Nodules Classification in CT Images Using Shannon and Simpson Diversity Indices and SVM , 2012, MLDM.

[15]  Berkman Sahiner,et al.  Computer-aided diagnosis of pulmonary nodules on CT scans: improvement of classification performance with nodule surface features. , 2009, Medical physics.

[16]  Harichandran Khanna Nehemiah,et al.  Computer-aided diagnosis of lung cancer based on analysis of the significant slice of chest computed tomography image , 2012 .

[17]  Elena A. Fedorovskaya,et al.  Digital Image Processing and Analysis , 2010 .

[18]  J. Klein,et al.  The solitary pulmonary nodule. , 2002, Radiologic clinics of North America.

[19]  Hiram Madero Orozco,et al.  Lung nodule classification in frequency domain using support vector machines , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

[20]  E. Davis,et al.  The solitary pulmonary nodule. , 1964, The Medical annals of the District of Columbia.

[21]  Yong Lin,et al.  NF-kappaB in lung cancer, a carcinogenesis mediator and a prevention and therapy target. , 2011, Frontiers in bioscience.

[22]  Georgy Gimel'farb,et al.  3D shape analysis for early diagnosis of malignant lung nodules. , 2011, Information processing in medical imaging : proceedings of the ... conference.

[23]  Jamshid Dehmeshki,et al.  Shape-Based Computer-Aided Detection of Lung Nodules in Thoracic CT Images , 2009, IEEE Transactions on Biomedical Engineering.

[24]  Hans-Jörg Vogel,et al.  Quantifying permafrost patterns using Minkowski densities , 2005 .

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

[26]  D K Owens,et al.  Accuracy of positron emission tomography for diagnosis of pulmonary nodules and mass lesions: a meta-analysis. , 2001, JAMA.

[27]  Dietrich Stoyan,et al.  Morphology of Condensed Matter , 2002 .

[28]  N. Müller,et al.  Fleischner Society: glossary of terms for thoracic imaging. , 2008, Radiology.

[29]  Anselmo Cardoso de Paiva,et al.  Automatic detection of solitary lung nodules using quality threshold clustering, genetic algorithm and diversity index , 2014, Artif. Intell. Medicine.

[30]  Joo Kooi Tan,et al.  Automatic Detection of Lung Nodules in Temporal Subtraction Image by Use of Shape and Density Features , 2009, 2009 Fourth International Conference on Innovative Computing, Information and Control (ICICIC).

[31]  H. Hadwiger.  Vorlesungen über Inhalt, Oberfläche und Isoperimetrie , 1957 .

[32]  Murat Cakiroglu,et al.  Artificial neural network-based classification system for lung nodules on computed tomography scans , 2014, 2014 6th International Conference of Soft Computing and Pattern Recognition (SoCPaR).

[33]  B. Stewart,et al.  World cancer report 2014. , 2014 .

[34]  D. Stoyan,et al.  Morphology of Condensed Matter: Physics And Geometry Of Spatially Complex Systems , 2010 .

[35]  B. Stewart,et al.  World Cancer Report , 2003 .

[36]  D. Ost,et al.  Solitary Pulmonary Nodule , 2005 .

[37]  P. Pattynama,et al.  Receiver operating characteristic (ROC) analysis: basic principles and applications in radiology. , 1998, European journal of radiology.

[38]  Edith M Marom,et al.  Lung cancer imaging. , 2014, Seminars in diagnostic pathology.

[39]  Mary M. Galloway,et al.  Texture analysis using gray level run lengths , 1974 .

[40]  Marie-Françoise Devaux,et al.  COMPUTATION OF MINKOWSKI MEASURES ON 2D AND 3D BINARY IMAGES , 2011 .

[41]  Robert J. Gillies,et al.  Effect of Texture Features in Computer Aided Diagnosis of Pulmonary Nodules in Low-Dose Computed Tomography , 2013, 2013 IEEE International Conference on Systems, Man, and Cybernetics.

[42]  Alexander J. Smola,et al.  Learning with Kernels: support vector machines, regularization, optimization, and beyond , 2001, Adaptive computation and machine learning series.

[43]  Luis A. Santaló,et al.  Integral Geometry and Geometric Probability: Integral Geometry and Geometric Probability , 2004 .

[44]  L. Santaló.  Integral geometry and geometric probability , 1976 .

[45]  F. Laurent,et al.  Management strategy of pulmonary nodule in 2013. , 2013, Diagnostic and interventional imaging.

[46]  J. Remy,et al.  [Management strategy of pulmonary nodules]. , 2002, Journal de radiologie.

[47]  Richard C. Pais,et al.  The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): a completed reference database of lung nodules on CT scans. , 2011, Medical physics.

[48]  Ignacio I Wistuba,et al.  Current concepts on the molecular pathology of non-small cell lung carcinoma. , 2014, Seminars in diagnostic pathology.