- 1. Computer Aided Detection ofPulmonary Nodules in CT ScansWookjin Choi, PhD
2. IntroductionLung cancer is the leading cause of cancer deaths.Most patients diagnosed with lung cancer already have advanced disease40% are stage IV and 30% are IIIThe current five-year survival rate is only 16%Defective nodules are detected at an early stageThe survival rate can be increased(a) male (b) femaleTrends in death rates for selected cancers, United States, 1930-2008  3. Pulmonary Nodule Detection CAD systemThe use of pulmonary nodule detection CAD system can provide an effective solutionCAD system can assist radiologists by increasing efficiency and potentially improving nodule detectionGeneral structure of pulmonary nodule detection system 4. Pulmonary Nodule Detection CAD systemCAD systemsLung segmentationNodule Candidate DetectionFalse Positive ReductionSuzuki et al.(2003)ThresholdingMultiple thresholdingMTANNRubin et al.(2005)ThresholdingSurface normal overlapLantern transform and rule- based classifierDehmeshki et al.(2007)Adaptive thresholdingShape-based GATMRule-based filteringSuarez-Cuenca et al.(2009)Thresholding and 3-D connected component labeling3-D iris filteringMultiple rule-based LDA classifierGolosio et al.(2009)Isosurface-triangulationMultiple thresholdingNeural networkYe et al.(2009)3-D adaptive fuzzy segmentationShape based detectionRule-based filtering and weighted SVM classifierSousa et al.(2010)Region growingStructure extractionSVM classifierMessay et al.(2010)Thresholding and 3-D connected component labelingMultiple thresholding and morphological openingFisher linear discriminant and quadratic classifierRiccardi et al.(2011)Iterative thresholding3-D fast radial filtering and scale space analysisZernike MIP classification based on SVMCascio et al.(2012)Region growingMass-spring modelDouble-threshold cut and neural network 5. Experimental Data SetLung Image Database Consortium (LIDC) database  is applied to evaluate the performance of the proposed method.LIDC database, National Cancer Institute (NCI), United StatesThe LIDC is developing a publicly available database of thoracic computed tomography (CT) scans as a medical imaging research resource to promote the development of computer-aided detection or characterization of pulmonary nodules.The database consists of 84 CT scans (up to 2007) 100-400 Digital Imaging and Communication (DICOM) imagesAn XML data file containing the physician annotations of nodules148 nodulesThe pixel size in the database ranged from 0.5 to 0.76 mmThe reconstruction interval ranged from 1 to 3mm 6. Genetic Programming based Classifier for Detection of Pulmonary nodulesWook-Jin Choi, Tae-Sun Choi, Genetic programming-based feature transform and classification for the automatic detection of pulmonary nodules on computed tomography images, Information Sciences, Vol. 212, pp. 57-78, December 2012, doi: http://dx.doi.org/10.1016/j.ins.2012.05.008Feature spaces for four types of features2-D geometric feature3-D geometric feature2-D intensity-based statistical feature3-D intensity-based statistical featureGenetic programming classifier learningClassification spaceGP based classification expression in tree shape 7. Hierarchical Block-image Analysis for Pulmonary Nodule DetectionWook-Jin Choi, Tae-Sun Choi, Automated Pulmonary Nodule Detection System in Computed Tomography Images: A Hierarchical Block Classification Approach, Entropy, Vol. 15, No. 2, pp. 507-523, February 2013, doi:http://dx.doi.org/10.3390/e15020507ROC curves of the SVM classifiers with respect to three different kernel functions, SVM-r: radial basis function, SVM-p: polynomial function, and SVM-m: Minkowski distance function; (a) p = 0:25 and (b) p = 1.FROC curves of the proposed CAD system with respect to three different kernel parameters of SVM-r classifiers 8. Pulmonary Nodule Detection using Three-dimensional Shape- based Feature DescriptorWook-Jin Choi, Tae-Sun Choi, Automated Pulmonary Nodule Detection based on Three-dimensional Shape-based Feature Descriptor, Computer Methods and Programs in Biomedicine, Vol. 113, No. 1, January 2014, pp. 3754, doi: http://dx.doi.org/10.1016/j.cmpb.2013.08.015Surface saliency weighted surface normal vectorsTwo angular histograms of the surface normal vectorsROC curves of the SVM classifiers with respect to three different kernelfunctions, SVM-r: radial basis function, SVM-p: polynomial function, and SVM-m: Minkowski distance function; (a) p = 0:25 and (b) p = 1.FROC curves of the proposed CAD system with respect to three different dimensions of AHSN featuresFeature optimization with wall detection and elimination algorithm3D shape-based feature descriptor 9. Comparative AnalysisCAD systemsNodule sizeFPs per caseSensitivitySuzuki et al.(2003)8 - 20 mm16.180.3%Rubin et al.(2005)>3 mm376%Dehmeshki et al.(2007)3 - 20 mm14.690%Suarez-Cuenca et al.(2009)4 - 27 mm7.780%Golosio et al.(2009)3 - 30 mm4.079%Ye et al.(2009)3 - 20 mm8.290.2%Sousa et al.(2010)3 - 40.93 mm-84.84%Messay et al.(2010)3-30 mm382.66%Riccardi et al.(2011)>3 mm6.571.%Cascio et al.(2012)3-30 mm6.197.66%Genetic Programming3-30 mm5.4590.9%Hierarchical Block Analysis3-30 mm2.2795.2%Shape-based Feature3-30 mm2.4395.4% 10. ConclusionsAutomated pulmonary nodule detection system is studiedPulmonary nodule detection CAD system is an effective solution for early detection of lung cancerThe proposed systems are based onGenetic programming based classifierFeature transform to classification spaceHierarchical block-image analysisLocally optimized nodule segmentation3-D shape-based feature descriptorShape feature without nodule segmentationThe performance of the proposed CAD systems is evaluated on the LIDC database of NCIThe proposed methods have significantly reduced the false positives in nodule candidates 11. Future workClinically applicable computer aided diagnosis and image guided radiation therapy system for lung cancer (long term goal)Multi-modal imagesClinical and gene informationQuantitative analysis of lung images based on image processing techniquesImproved segmentation, registration, classification, and etc.Lung cancer, COPD and other lung diseasesCT, Dual-energy CT, PET/CT, 4DCT 12. References Rebecca Siegel, Deepa Naishadham, and Ahmedin Jemal, Cancer statistics, 2012, CA: A Cancer Journal for Clinicians, vol. 62, no. 1, pp. 1029, 2012. M. F. McNitt-Gray, S. G. Armato, C. R. Meyer, A. P. Reeves, G. McLennan, R. C. Pais, J. Freymann, M. S. Brown, R. M. Engelmann, P. H. Bland, G. E. Laderach, C. Piker, J. Guo, Z. Towfic, D. P.-Y. Qing, D. F. Yankelevitz, D. R. Aberle, E. J. R. van Beek, H. MacMahon, E. A. Kazerooni, B. Y. Croft, L. P. Clarke, The Lung Image Database Consortium (LIDC) data collection process for nodule detection and annotation, Acad Radiol 14 (2007) 1464 1474. K Suzuki, SG Armato III, F Li, S Sone, and K Doi, Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography, Medical Physics, vol. 30, pp. 1602 1617, 2003. G.D. Rubin, J.K. Lyo, D.S. Paik, A.J. Sherbondy, L.C. Chow, A.N. Leung, R. Mindelzun, P.K. Schraedley-Desmond, S.E. Zinck, D.P. Naidich, et al., Pulmonary Nodules on Multi Detector Row CT Scans: Performance Comparison of Radiologists and Computer-aided Detection, Radiology, vol. 234, no. 1, pp. 274, 2005. Jamshid Dehmeshki, Xujiong Ye, Xinyu Lin, Manlio Valdivieso, and Hamdan Amin, Automated detection of lung nodules in CT images using shape-based genetic algorithm, Computerized Medical Imaging and Graphics, vol. 31, no. 6, pp. 408 417, Sep 2007. J.J. Surez-Cuenca, P.G. Tahoces, M. Souto, M.J. Lado, M. Remy-Jardin, J. Remy, and J. Jos Vidal, Application of the iris filter for automatic detection of pulmonary nodules on computed tomography images, Computers in Biology and Medicine, vol. 39, no. 10, pp. 921 933, 2009. 13. References Bruno Golosio, Giovanni Luca Masala, Alessio Piccioli, Piernicola Oliva, Massimo Carpinelli, Rosella Cataldo, Piergiorgio Cerello, Francesco De Carlo, Fabio Falaschi, Maria Evelina Fantacci, et al., A novel multithreshold method for nodule detection in lung ct, Medical physics, vol. 36, pp. 3607, 2009. X. Ye, X. Lin, J. Dehmeshki, G. Slabaugh, and G. Beddoe, Shape-based computer-aided detection of lung nodules in thoracic CT images, IEEE Transactions on Biomedical Engineering, vol. 56, no. 7, pp. 1810 1820, 2009. Joo Rodrigo Ferreira da Silva Sousa, Aristfanes Correa Silva, Anselmo Cardoso de Paiva, and Rodolfo Acatauass Nunes, Methodology for automatic detection of lung nodules in computerized tomography images., Computer methods and programs in biomedicine, vol. 98, no. 1, pp. 114, Apr. 2010. T. Messay, R.C. Hardie, and S.K. Rogers, A new computationally efficient CAD system for pulmonary nodule detection in CT imagery, Medical Image Analysis, vol. 14, no. 3, pp. 390 406, 2010. A Riccardi, TS Petkov, G Ferri, M Masotti, and R Campanini, Computer-aided detection of lung nodules via 3D fast radial transform, scale space representation, and Zernike MIP classification, Medical Physics, vol. 38, no. 4, pp. 19621971, 2011. D. Cascio, R. Magro, F. Fauci, M. Iacomi, and G. Raso, Automatic detection of lung nodules in ct datasets based on stable 3d mass-pring models, Computers in Biology and Medicine, vol. 42, no. 11, pp. 1098 1109, 2012.