A Combination of Shape and Texture Features for Classification of Pulmonary Nodules in Lung CT Images

Classification of malignant and benign pulmonary nodules is important for further treatment plan. The present work focuses on the classification of benign and malignant pulmonary nodules using support vector machine. The pulmonary nodules are segmented using a semi-automated technique, which requires only a seed point from the end user. Several shape-based, margin-based, and texture-based features are computed to represent the pulmonary nodules. A set of relevant features is determined for the efficient representation of nodules in the feature space. The proposed classification scheme is validated on a data set of 891 nodules of Lung Image Database Consortium and Image Database Resource Initiative public database. The proposed classification scheme is evaluated for three configurations such as configuration 1 (composite rank of malignancy “1” and “2” as benign and “4” and “5” as malignant), configuration 2 (composite rank of malignancy “1”,“2”, and “3” as benign and “4” and “5” as malignant), and configuration 3 (composite rank of malignancy “1” and “2” as benign and “3”,“4” and “5” as malignant). The performance of the classification is evaluated in terms of area (Az) under the receiver operating characteristic curve. The Az achieved by the proposed method for configuration-1, configuration-2, and configuration-3 are 0.9505, 0.8822, and 0.8488, respectively. The proposed method outperforms the most recent technique, which depends on the manual segmentation of pulmonary nodules by a trained radiologist.

[1]  M. McNitt-Gray,et al.  A pattern classification approach to characterizing solitary pulmonary nodules imaged on high resolution CT: preliminary results. , 1999, Medical physics.

[2]  M. L. Dewal,et al.  A Fast Region-Based Active Contour Model for Boundary Detection of Echocardiographic Images , 2012, Journal of Digital Imaging.

[3]  J. Austin,et al.  Glossary of terms for CT of the lungs: recommendations of the Nomenclature Committee of the Fleischner Society. , 1996, Radiology.

[4]  Niranjan Khandelwal,et al.  Differential geometry-based techniques for characterization of boundary roughness of pulmonary nodules in CT images , 2015, International Journal of Computer Assisted Radiology and Surgery.

[5]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[6]  Ayman El-Baz,et al.  A novel shape-based diagnostic approach for early diagnosis of lung nodules , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[7]  Marcos Salganicoff,et al.  Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models , 2011, Medical Image Anal..

[8]  Lubomir M. Hadjiiski,et al.  Computer-aided diagnosis of pulmonary nodules on CT scans: segmentation and classification using 3D active contours. , 2006, Medical physics.

[9]  S. Iwano,et al.  Computer-aided diagnosis: a shape classification of pulmonary nodules imaged by high-resolution CT. , 2005, Computerized Medical Imaging and Graphics.

[10]  S. Swensen,et al.  Screening for lung cancer with low-dose spiral computed tomography. , 2000, American journal of respiratory and critical care medicine.

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

[12]  Arunabha S. Roy,et al.  Automated lung nodule classification following automated nodule detection on CT: a serial approach. , 2003, Medical physics.

[13]  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.

[14]  Kunio Doi,et al.  Computer-aided diagnostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificial neural network , 2005, IEEE Transactions on Medical Imaging.

[15]  Punam K. Saha,et al.  Measurements of digitized objects with fuzzy borders in 2D and 3D , 2005, Image Vis. Comput..

[16]  K. Doi,et al.  Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. , 2002, AJR. American journal of roentgenology.

[17]  W. Heindel,et al.  Screening for early lung cancer with low-dose spiral CT: prevalence in 817 asymptomatic smokers. , 2002, Radiology.

[18]  Heiner Stuckenschmidt,et al.  RockIt: Exploiting Parallelism and Symmetry for MAP Inference in Statistical Relational Models , 2013, AAAI.

[19]  Heinz-Otto Peitgen,et al.  Morphological segmentation and partial volume analysis for volumetry of solid pulmonary lesions in thoracic CT scans , 2006, IEEE Transactions on Medical Imaging.

[20]  Sudipta Mukhopadhyay,et al.  A Segmentation Framework of Pulmonary Nodules in Lung CT Images , 2016, Journal of Digital Imaging.

[21]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[22]  Paula Martins,et al.  Algorithm Versus Physicians Variability Evaluation in the Cardiac Chambers Extraction , 2012, IEEE Transactions on Information Technology in Biomedicine.

[23]  Niranjan Khandelwal,et al.  Erratum to: A Segmentation Framework of Pulmonary Nodules in Lung CT Images , 2015, Journal of Digital Imaging.

[24]  Ashis Kumar Dhara,et al.  Performance metrics for image contrast , 2011, 2011 International Conference on Image Information Processing.

[25]  Jacob D. Furst,et al.  Learning lung nodule similarity using a genetic algorithm , 2012, Medical Imaging.

[26]  K. Doi,et al.  Radiologists' performance for differentiating benign from malignant lung nodules on high-resolution CT using computer-estimated likelihood of malignancy. , 2004, AJR. American journal of roentgenology.

[27]  Hong Zhao,et al.  Texture Feature Analysis for Computer-Aided Diagnosis on Pulmonary Nodules , 2015, Journal of Digital Imaging.

[28]  Jacob D. Furst,et al.  A model for the relationship between semantic and content based similarity using LIDC , 2010, Medical Imaging.

[29]  Cordelia Schmid,et al.  Human Detection Using Oriented Histograms of Flow and Appearance , 2006, ECCV.

[30]  Rangaraj M. Rangayyan,et al.  Measures of acutance and shape for classification of breast tumors , 1997, IEEE Transactions on Medical Imaging.

[31]  松木 裕一.  Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT : Evaluation with receiver operating characteristic analysis , 2003 .