Computer Aided Detection of
Pulmonary Nodules in CT Scans
Wookjin Choi, PhD
Introduction
Lung cancer is the leading cause of cancer deaths.
Most patients diagnosed with lung cancer already have advanced disease
40% are stage IV and 30% are III
The current five-year survival rate is only 16%
Defective nodules are detected at an early stage
The survival rate can be increased
(a) male (b) female
Trends in death rates for selected cancers, United States, 1930-2008 [1]
Pulmonary Nodule Detection CAD system
The use of pulmonary nodule detection CAD system can
provide an effective solution
CAD system can assist radiologists by increasing efficiency
and potentially improving nodule detection
General structure of pulmonary nodule detection system
Pulmonary Nodule Detection CAD system
CAD systems Lung segmentation Nodule Candidate Detection False Positive Reduction
Suzuki et al.(2003)[3] Thresholding Multiple thresholding MTANN
Rubin et al.(2005)[4] Thresholding Surface normal overlap
Lantern transform and rule-
based classifier
Dehmeshki et al.(2007)[5] Adaptive thresholding Shape-based GATM Rule-based filtering
Suarez-Cuenca et al.(2009)[6] Thresholding and 3-D
connected component
labeling
3-D iris filtering Multiple rule-based LDA
classifier
Golosio et al.(2009)[7] Isosurface-triangulation Multiple thresholding Neural network
Ye et al.(2009)[8] 3-D adaptive fuzzy
segmentation Shape based detection
Rule-based filtering and
weighted SVM classifier
Sousa et al.(2010)[9] Region growing Structure extraction SVM classifier
Messay et al.(2010)[10] Thresholding and 3-D
connected component
labeling
Multiple thresholding and
morphological opening
Fisher linear discriminant and
quadratic classifier
Riccardi et al.(2011)[11] Iterative thresholding
3-D fast radial filtering and
scale space analysis
Zernike MIP classification
based on SVM
Cascio et al.(2012)[12] Region growing Mass-spring model
Double-threshold cut and
neural network
Experimental Data Set
Lung Image Database Consortium (LIDC) database [2] is applied to
evaluate the performance of the proposed method.
LIDC database, National Cancer Institute (NCI), United States
The 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) [2]
100-400 Digital Imaging and Communication (DICOM) images
An XML data file containing the physician annotations of nodules
148 nodules
The pixel size in the database ranged from 0.5 to 0.76 mm
The reconstruction interval ranged from 1 to 3mm
Genetic Programming based Classifier
for Detection of Pulmonary nodules
Wook-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.2012.05.008
Feature spaces for four types of features
2-D geometric feature 3-D geometric feature
2-D intensity-based statistical feature 3-D intensity-based statistical feature
Genetic programming classifier learning
Classification space
GP based classification expression in tree shape
Hierarchical Block-image Analysis for
Pulmonary Nodule Detection
Wook-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/e15020507
ROC 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
θ φ
θ φ
Pulmonary Nodule Detection using Three-dimensional Shape-
based Feature Descriptor
Wook-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. 37–54, doi: http://dx.doi.org/10.1016/j.cmpb.2013.08.015
Surface saliency weighted surface
normal vectors
Two angular histograms of the
surface normal vectors
θ φ
ROC 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 dimensions of AHSN
features
θ φ
θ φ
Feature optimization with wall detection a
nd elimination algorithm
3D shape-based feature descriptor
Comparative Analysis
CAD systems Nodule size FPs per case Sensitivity
Suzuki et al.(2003)[3] 8 - 20 mm 16.1 80.3%
Rubin et al.(2005)[4] >3 mm 3 76%
Dehmeshki et al.(2007)[5] 3 - 20 mm 14.6 90%
Suarez-Cuenca et al.(2009)[6] 4 - 27 mm 7.7 80%
Golosio et al.(2009)[7] 3 - 30 mm 4.0 79%
Ye et al.(2009)[8] 3 - 20 mm 8.2 90.2%
Sousa et al.(2010)[9] 3 - 40.93 mm - 84.84%
Messay et al.(2010)[10] 3-30 mm 3 82.66%
Riccardi et al.(2011)[11] >3 mm 6.5 71.%
Cascio et al.(2012)[12] 3-30 mm 6.1 97.66%
Genetic Programming 3-30 mm 5.45 90.9%
Hierarchical Block Analysis 3-30 mm 2.27 95.2%
Shape-based Feature 3-30 mm 2.43 95.4%
Conclusions
Automated pulmonary nodule detection system is studied
Pulmonary nodule detection CAD system is an effective solution for early detection of lung cancer
The proposed systems are based on
Genetic programming based classifier
• Feature transform to classification space
Hierarchical block-image analysis
• Locally optimized nodule segmentation
3-D shape-based feature descriptor
• Shape feature without nodule segmentation
The performance of the proposed CAD systems is evaluated on the LIDC database of NCI
The proposed methods have significantly reduced the false positives in nodule candidates
Future work
Clinically applicable computer aided diagnosis and image guided radiation therapy system for lung cancer (long term goal)
Multi-modal images
Clinical and gene information
Quantitative analysis of lung images based on image processing techniques
Improved segmentation, registration, classification, and etc.
Lung cancer, COPD and other lung diseases
CT, Dual-energy CT, PET/CT, 4DCT
References
[1] Rebecca Siegel, Deepa Naishadham, and Ahmedin Jemal, “Cancer statistics, 2012,” CA: A
Cancer Journal for Clinicians, vol. 62, no. 1, pp. 10–29, 2012.
[2] 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.
[3] 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.
[4] 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.
[6] 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.
[6] J.J. Suárez-Cuenca, P.G. Tahoces, M. Souto, M.J. Lado, M. Remy-Jardin, J. Remy, and
J. José 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.
References
[7] 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.
[8] 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.
[9] João Rodrigo Ferreira da Silva Sousa, Aristófanes Correa Silva, Anselmo Cardoso
de Paiva, and Rodolfo Acatauassú Nunes, “Methodology for automatic detection of lung nodules
in computerized tomography images.,” Computer methods and programs in biomedicine, vol. 98,
no. 1, pp. 1–14, Apr. 2010.
[10] 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.
[11] 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. 1962–1971, 2011.
[12] 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.