Smart Colonography for Distributed Medical Databases with Group Kernel Feature Analysis
Article No.: 58, Pages 1 - 24
Abstract
Computer-Aided Detection (CAD) of polyps in Computed Tomographic (CT) colonography is currently very limited since a single database at each hospital/institution doesn't provide sufficient data for training the CAD system's classification algorithm. To address this limitation, we propose to use multiple databases, (e.g., big data studies) to create multiple institution-wide databases using distributed computing technologies, which we call smart colonography. Smart colonography may be built by a larger colonography database networked through the participation of multiple institutions via distributed computing. The motivation herein is to create a distributed database that increases the detection accuracy of CAD diagnosis by covering many true-positive cases. Colonography data analysis is mutually accessible to increase the availability of resources so that the knowledge of radiologists is enhanced. In this article, we propose a scalable and efficient algorithm called Group Kernel Feature Analysis (GKFA), which can be applied to multiple cancer databases so that the overall performance of CAD is improved. The key idea behind the proposed GKFA method is to allow the feature space to be updated as the training proceeds with more data being fed from other institutions into the algorithm. Experimental results show that GKFA achieves very good classification accuracy.
References
[1]
American Cancer Society. 2014. Cancer Facts & Figures 2014. American Cancer Society.
[2]
M. Awad, Y. Motai, J. Näppi, and H. Yoshida. 2010. A clinical decision support framework for incremental polyps classification in virtual colonoscopy. Algorithms 3, 1--20.
[3]
C. L. Cai, J. G. Lee, M. E. Zalis, and H. Yoshida. 2011. Mosaic decomposition: An electronic cleansing method for inhomogeneously tagged regions in noncathartic CT colonography. IEEE Transactions on Medical Imaging 30 (2011), 559--570.
[4]
T. T. Chang, J. Feng, H. W. Liu, and H. Ip. 2008. Clustered microcalcification detection based on a multiple kernel support vector machine with grouped features. In Proceedings of the 19th International Conference on Pattern Recognition. 8, 1--4.
[5]
X. W. Chen. 2003. Gene selection for cancer classification using bootstrapped genetic algorithms and support vector machines. In Proceedings of the IEEE International Computational Systems, Bioinformatics Conference. 504--505.
[6]
T. J. Chin and D. Suter. 2007. Incremental kernel principal component analysis. IEEE Transactions on Image Processing 16, 6, 1662--1674.
[7]
N. Cristianini, J. Kandola, A. Elisseeff, and Shawe-Taylor, J. 2001. On kernel target alignment. In Proceedings of the Neural Information Processing Systems. 367--373.
[8]
T. Fawcett. 2006. An introduction to ROC analysis. Pattern Recognition Letters 27, 8, 861--874.
[9]
H. Fröhlich, O. Chapelle, and B. Scholkopf. 2003. Feature selection for support vector machines by means of genetic algorithm. In Proceedings of the 15th IEEE International Conference on Tools with Artificial Intelligence. 142--148.
[10]
L. Hoegaerts, L. De Lathauwer, I. Goethals, J. A. K. Suykens, J. Vandewalle, and B. De Moor. 2007. Efficiently updating and tracking the dominant kernel principal components. Neural Networks 20, 2, 220--229.
[11]
C. Hu, Y. Chang, R. Feris, and M. Turk. 2004. Manifold based analysis of facial expression. In Proceedings of the Computer Vision and Pattern Recognition Workshop. 27, 81--85.
[12]
L. Jayawardhana, Y. Motai, and A. Docef. 2009. Computer-aided detection of polyps in CT colonography: On-line versus off-line accelerated kernel feature analysis. Special Issue on Processing and Analysis of High-Dimensional Masses of Image and Signal Data, Signal Processing 1--12.
[13]
X. Jiang, R. Snapp, Y. Motai, and X. Zhu. 2006. Accelerated kernel feature analysis In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 109--116.
[14]
A. Khan, J. A. Doucette, and R. Cohen. 2013. Validation of an ontological medical decision support system for patient treatment using a repository of patient data: Insights into the value of machine learning. ACM Transactions on Intelligent Systems Technology 4, 4, Article 68 (September 2013).
[15]
B. J. Kim and I. K. Kim. 2004. Incremental nonlinear PCA for classification. In Proceedings in Knowledge Discovery in Databases. 3202, 291--300.
[16]
B. J. Kim, J. Y. Shim, C. H. Hwang, I. K. Kim, and J. H. Song. 2003. Incremental feature extraction based on empirical kernel map. Foundations of Intelligent Systems. 2871, 440--444.
[17]
Y. Kim. 2007. Incremental principal component analysis for image processing. Optics Letters 32, 1, 32--34.
[18]
J. Kivinen, A. J. Smola, and R. C. Williamson. 2004. Online learning with kernels. IEEE Transactions on Signal Processing 52, 8, 2165--2176.
[19]
B. Levin, D. A. Lieberman, B. McFarland, K. S. Andrews, D. Brooks, J. Bond, C. Dash, F. M. Giardiello, S. Glick, D. Johnson, C. D. Johnson, T. R. Levin, P. J. Pickhardt, D. K. Rex, R. A. Smith, A. Thorson, and S. J. Winawer. 2008. Screening and surveillance for the early detection of colorectal cancer and adenomatous polyps, 2008: A joint guideline from the American Cancer Society, the US Multi-Society Task Force on Colorectal Cancer and the American College of Radiology. CA: A Cancer Journal for Clinicians 58, 130--160.
[20]
Y. M. Li. 2004. On incremental and robust subspace learning. Pattern Recognition 37, 7, 1509--1518.
[21]
Y. Motai and H. Yoshida. 2013. Principal composite kernel feature analysis: Data-dependent kernel approach. IEEE Transactions on Knowledge and Data Engineering 25, 8, 1863--1875.
[22]
J. Näppi and H. Yoshida. 2002. Automated detection of polyps in CT colonography: Evaluation of volumetric features for reduction of false positives. Academic Radiology 9, 386--397.
[23]
J. Näppi and H. Yoshida. 2003. Feature guided analysis for reduction of false positives in CAD of polyps for CT colonography. Medical Physics 30, 1592--1601.
[24]
J. Näppi and H. Yoshida. 2007. Fully automated three-dimensional detection of polyps in fecal-tagging CT colonography. Academy of Radiology 14 (March 2007), 287--300.
[25]
S. Ozawa, S. Pang, and N. Kasabov. 2008. Incremental learning of chunk data for online pattern classification systems. IEEE Transactions on Neural Networks 19, 6, 1061--1074.
[26]
C. Park and S. B. Cho. 2003. Genetic search for optimal ensemble of feature-classifier pairs in DNA gene expression profiles. In Proceedings of the International Joint Conference on Neural Networks. 3, 1702--1707.
[27]
P. J. Pickhardt, J. R. Choi, I. Hwang, J. A. Butler, M. L. Puckett, H. A. Hildebrandt, R. K. Wong, P. A. Nugent, P. A. Mysliwiec, and W. R. Schindler. 2003. Computed tomographic virtual colonoscopy to screen for colorectal neoplasia in asymptomatic adults. New England Journal of Medicine 349 (December 4, 2003), 2191--2200.
[28]
D. Regge and S. Halligan. 2013. CAD: How it works, how to use it, performance. European Journal of Radiology 82, 1171--1176.
[29]
D. Regge, C. Laudi, G. Galatola, Della P. Monica, L. Bonelli, G. Angelelli, R. Asnaghi, B. Barbaro, C. Bartolozzi, D. Bielen, L. Boni, C. Borghi, P. Bruzzi, M. C. Cassinis, M. Galia, T. M. Gallo, A. Grasso, C. Hassan, A. Laghi, M. C. Martina, E. Neri, C. Senore, G. Simonetti, S. Venturini, and G. Gandini. 2009. Diagnostic accuracy of computed tomographic colonography for the detection of advanced neoplasia in individuals at increased risk of colorectal cancer. Journal of the American Medical Association 301, 23, 2453--2461.
[30]
D. C. Rockey. 2010. Computed tomographic colonography: Ready for prime time? Gastroenterology Clinics of North America 39, 901--909.
[31]
D. C. Rockey, E. Paulson, D. Niedzwiecki, W. Davis, H. B. Bosworth, L. Sanders, J. Yee, J. Henderson, P. Hatten, S. Burdick, A. Sanyal, D. T. Rubin, M. Sterling, G. Akerkar, M. S. Bhutani, K. Binmoeller, J. Garvie, E. J. Bini, K. McQuaid, W. L. Foster, W. M. Thompson, A. Dachmanm, and R. Halvorsen. 2005. Analysis of air contrast barium enema, computed tomographic colonography, and colonoscopy: Prospective comparison. Lancet 365 (January 22, 2005), 305--311.
[32]
F. A. Sadjadi. 2008. Polarimetric radar target classification using support vector machines. Optical Engineering 47, 4.
[33]
B. Schölkopf and A. J. Smola. 2002. Learning with kernels: support vector machines, regularization, optimization, and beyond. Adaptive Computation and Machine Learning. MIT Press.
[34]
D. G. Stork and E. Yom-Tov. 2004. Computer Manual in MATLAB to Accompany Pattern Classification, 2nd ed. New York: John Wiley & Sons.
[35]
V. Taimouri, L. Xin, L. Zhaoqiang, L. Chang, P. Darshan, and H. Jing. 2011. Colon segmentation for prepless virtual colonoscopy. IEEE Transactions on Information Technology Biomedicine 15 (2011), 709--715.
[36]
V. F. van Ravesteijn, C. van Wijk, F. M. Vos, R. Truyen, J. F. Peters, J. Stoker, and L. J. van Vliet. 2010. Computer-aided detection of polyps in ct colonography using logistic regression. IEEE Transactions on Medical Imaging 29 (January 2010), 120--131.
[37]
H. Xiong, Y. Zhang, and X. W. Chen. 2007. Data-dependent kernel machines for microarray data classification. IEEE/ACM Transactions on Computational Biology and Bioinformatics 4, 4.
[38]
J. H. Yao, M. Miller, M. Franaszek, and R. M. Summers. 2004. Colonic polyp segmentation in CT colonography-based on fuzzy clustering and deformable models. IEEE Transactions on Medical Imaging 23, 1344--1356.
[39]
J. Yee, D. H. Kim, M. P. Rosen, T. Lalani, L. R. Carucci, B. D. Cash, B. W. Feig, K. J. Fowler, D. S. Katz, M. P. Smith, and V. Yaghmai. 2014. ACR appropriateness criteria: Colorectal cancer screening. Journal of the American College of Radiologists 11, 543--551.
[40]
H. Yoshida and A. H. Dachman. 2005. CAD techniques, challenges and controversies in computed tomographic colonography. Abdominal Imaging 30, 26--41.
[41]
H. Yoshida and J. Nappi. 2001. Three-dimensional computer-aided diagnosis scheme for detection of colonic polyps. IEEE Transactions on Medical Imaging 20 (December 2001), 1261--1274.
[42]
H. Yoshida and J. Näppi. 2007. CAD in CT colonography without and with fecal tagging: Progress and challenges. Computerized Medical Imaging and Graphics 31, 267--284.
[43]
H. Yoshida, Y. Masutani, P. MacEneaney, D. Rubin, and A. H. Dachman. 2002. Computerized detection of colonic polyps at CT colonography on the basis of volumetric features: Pilot study. Radiology 222, 327--336.
[44]
H. Yoshida, Y. Wu, and W. Cai. 2012. Scalable, high-performance 3D image computing platform: System architecture and application to virtual colonoscopy. In Proceedings of the IEEE Engineering and Medical Biology Society. 3994--3997.
[45]
H. T. Zhao, P. C. Yuen, and J. T. Kwok. 2006. A novel incremental principal component analysis and its application for face recognition. IEEE Transactions on Systems, Man, and Cybernetics, Part B 36, 4, 873--886.
[46]
W. Zheng, C. Zou, and L. Zhao. 2005. An improved algorithm for kernel principal component analysis. Neural Processing Letters 49--56.
Index Terms
- Smart Colonography for Distributed Medical Databases with Group Kernel Feature Analysis
Recommendations
Computer-aided detection for ultra-low-dose CT colonography
MICCAI'12: Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applicationsTo screen large populations for colorectal cancer, it may be necessary to reduce the radiation dose of computed tomographic colonography (CTC) examinations. We compared the accuracy of computer-aided detection (CAD) in standard-dose (SD) CTC with that ...
Application of CT acquisition parameters as features in computer-aided detection for CT colonography
MICCAI'12: Proceedings of the 4th international conference on Abdominal Imaging: computational and clinical applicationsStudies have indicated that the acquisition parameters of computed tomography (CT) scans can have significant effect on the accuracy of computer-aided detection (CAD) in CT colonography. We investigated whether these parameters can be used as external ...
Centerline registration of prone and supine CT colonography scans based on correlation optimized warping and anatomical landmarks
ISBI'09: Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to MacroIn this paper, we propose an automated method for colon registration from supine and prone scans. We formulate the colon registration problem as time series matching along the centerline of the colon. Four anatomical salient points on the colon are ...
Comments
Information & Contributors
Information
Published In
August 2015
419 pages
Copyright © 2015 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 27 July 2015
Accepted: 01 September 2014
Revised: 01 July 2014
Received: 01 March 2014
Published in TIST Volume 6, Issue 4
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed
Funding Sources
- Presidential Research Incentive Program at VCU
- Center for Clinical and Translational Research Endowment Fund of Virginia Commonwealth University (VCU)
- the American Cancer Society through the Massey Cancer Center
- National Science Foundation
- the National Center for Advancing Translational Sciences
- National Institutes of Health
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 161Total Downloads
- Downloads (Last 12 months)1
- Downloads (Last 6 weeks)0
Reflects downloads up to 10 Nov 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in