A new computationally efficient CAD system for pulmonary nodule detection in CT imagery

Early detection of lung nodules is extremely important for the diagnosis and clinical management of lung cancer. In this paper, a novel computer aided detection (CAD) system for the detection of pulmonary nodules in thoracic computed tomography (CT) imagery is presented. The paper describes the architecture of the CAD system and assesses its performance on a publicly available database to serve as a benchmark for future research efforts. Training and tuning of all modules in our CAD system is done using a separate and independent dataset provided courtesy of the University of Texas Medical Branch (UTMB). The publicly available testing dataset is that created by the Lung Image Database Consortium (LIDC). The LIDC data used here is comprised of 84 CT scans containing 143 nodules ranging from 3 to 30mm in effective size that are manually segmented at least by one of the four radiologists. The CAD system uses a fully automated lung segmentation algorithm to define the boundaries of the lung regions. It combines intensity thresholding with morphological processing to detect and segment nodule candidates simultaneously. A set of 245 features is computed for each segmented nodule candidate. A sequential forward selection process is used to determine the optimum subset of features for two distinct classifiers, a Fisher Linear Discriminant (FLD) classifier and a quadratic classifier. A performance comparison between the two classifiers is presented, and based on this, the FLD classifier is selected for the CAD system. With an average of 517.5 nodule candidates per case/scan (517.5+/-72.9), the proposed front-end detector/segmentor is able to detect 92.8% of all the nodules in the LIDC/testing dataset (based on merged ground truth). The mean overlap between the nodule regions delineated by three or more radiologists and the ones segmented by the proposed segmentation algorithm is approximately 63%. Overall, with a specificity of 3 false positives (FPs) per case/patient on average, the CAD system is able to correctly identify 80.4% of the nodules (115/143) using 40 selected features. A 7-fold cross-validation performance analysis using the LIDC database only shows CAD sensitivity of 82.66% with an average of 3 FPs per CT scan/case.

[1]  H. Yoshida,et al.  Automated detection of polyps with CT colonography: evaluation of volumetric features for reduction of false-positive findings. , 2002, Academic radiology.

[2]  P. Cooperberg,et al.  Computer-aided detection in screening CT for pulmonary nodules. , 2006, AJR. American journal of roentgenology.

[3]  Maximilian Reiser,et al.  Clinical evaluation of a computer-aided diagnosis (CAD) prototype for the detection of pulmonary embolism. , 2007, Academic radiology.

[4]  Geoffrey McLennan,et al.  The Lung Image Database Consortium (LIDC): an evaluation of radiologist variability in the identification of lung nodules on CT scans. , 2007, Academic radiology.

[5]  Robin N. Strickland.  Image-Processing Techniques for Tumor Detection , 2007 .

[6]  Anthony J. Sherbondy,et al.  Pulmonary nodules on multi-detector row CT scans: performance comparison of radiologists and computer-aided detection. , 2005, Radiology.

[7]  Thomas Bülow,et al.  Comparative performance analysis for computer aided lung nodule detection and segmentation on ultra-low-dose vs. standard-dose CT , 2006, SPIE Medical Imaging.

[8]  O. Miettinen,et al.  Early Lung Cancer Action Project: overall design and findings from baseline screening , 1999, The Lancet.

[9]  K. Doi,et al.  Computer-aided diagnostic scheme for the detection of lung nodules on chest radiographs: localized search method based on anatomical classification. , 2006, Medical physics.

[10]  Zaid J. Towfic,et al.  The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation , 2007, SPIE Medical Imaging.

[11]  Russell C. Hardie,et al.  Performance analysis of a new computer aided detection system for identifying lung nodules on chest radiographs , 2008, Medical Image Anal..

[12]  J M Tanner,et al.  Growth of Radiologically Determined Heart Diameter, Lung Width, and Lung Length from 5-19 Years, with Standards for Clinical Use , 1972, Archives of disease in childhood.

[13]  E. Hoffman,et al.  Lung image database consortium: developing a resource for the medical imaging research community. , 2004, Radiology.

[14]  Ilaria Gori,et al.  An automated system for lung nodule detection in low-dose computed tomography , 2007, SPIE Medical Imaging.

[15]  R. Fisher.  THE USE OF MULTIPLE MEASUREMENTS IN TAXONOMIC PROBLEMS , 1936 .

[16]  T. W. Anderson.  R. A. Fisher and multivariate analysis , 1996 .

[17]  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.

[18]  Bram van Ginneken,et al.  A computer-aided diagnosis system for detection of lung nodules in chest radiographs with an evaluation on a public database , 2006, Medical Image Anal..

[19]  R. A. Maxion,et al.  Proper Use of ROC Curves in Intrusion/Anomaly Detection , 2004 .

[20]  G. McLachlan.  Discriminant Analysis and Statistical Pattern Recognition , 1992 .

[21]  William E. Higgins,et al.  Paradigm for shape-based image analysis , 1998 .

[22]  Bram van Ginneken,et al.  Multi-scale Nodule Detection in Chest Radiographs , 2003, MICCAI.

[23]  R. Engelmann,et al.  Segmentation of pulmonary nodules in three-dimensional CT images by use of a spiral-scanning technique. , 2007, Medical physics.

[24]  Milan Sonka,et al.  Knowledge-based segmentation of intrathoracic airways from multidimensional high-resolution CT images , 1994, Medical Imaging.

[25]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

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

[27]  Robert M. Nishikawa,et al.  A study on several Machine-learning methods for classification of Malignant and benign clustered microcalcifications , 2005, IEEE Transactions on Medical Imaging.

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

[29]  Berkman Sahiner,et al.  Classification of malignant and benign masses based on hybrid ART2LDA approach , 1999, IEEE Transactions on Medical Imaging.

[30]  Berkman Sahiner,et al.  Effect of CAD on radiologists' detection of lung nodules on thoracic CT scans: observer performance study , 2007, SPIE Medical Imaging.

[31]  Hiroshi Fujita,et al.  Automated detection of pulmonary nodules in helical CT images based on an improved template-matching technique , 2001, IEEE Transactions on Medical Imaging.

[32]  A. Wetter,et al.  Automated detection of lung nodules in multidetector CT: influence of different reconstruction protocols on performance of a software prototype. , 2006, RoFo : Fortschritte auf dem Gebiete der Rontgenstrahlen und der Nuklearmedizin.

[33]  Athanasios Papoulis,et al.  Probability, Random Variables and Stochastic Processes , 1965 .

[34]  Marco Das,et al.  Small pulmonary nodules: effect of two computer-aided detection systems on radiologist performance. , 2006, Radiology.

[35]  S. Armato,et al.  Automated detection of lung nodules in CT scans: preliminary results. , 2001, Medical physics.

[36]  Ilaria Gori,et al.  Comparing and combining algorithms for computer-aided detection of pulmonary nodules in computed tomography scans: The ANODE09 study , 2010, Medical Image Anal..

[37]  Y. Kawata,et al.  Computer-aided diagnosis for pulmonary nodules based on helical CT images , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[38]  E. V. van Beek,et al.  The Lung Image Database Consortium (LIDC): a comparison of different size metrics for pulmonary nodule measurements. , 2007, Academic radiology.

[39]  Rafael Wiemker,et al.  Performance analysis for computer-aided lung nodule detection on LIDC data , 2007, SPIE Medical Imaging.

[40]  David G. Stork,et al.  Pattern Classification , 1973 .

[41]  Avinash C. Kak,et al.  PCA versus LDA , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[42]  Jean Serra,et al.  Image Analysis and Mathematical Morphology , 1983 .

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

[44]  Michael F. McNitt-Gray,et al.  Method for segmenting chest CT image data using an anatomical model: preliminary results , 1997, IEEE Transactions on Medical Imaging.

[45]  David Gur,et al.  Automated lung segmentation in X-ray computed tomography: development and evaluation of a heuristic threshold-based scheme. , 2003, Academic radiology.

[46]  J. Rodgers,et al.  Linearly Independent, Orthogonal, and Uncorrelated Variables , 1984 .

[47]  Shoji Kido,et al.  Automatic segmentation of pulmonary nodules on CT images by use of NCI lung image database consortium , 2006, SPIE Medical Imaging.