Reliable Feature Selection for Automated Angle Closure Glaucoma Mechanism Detection

详细信息    查看全文

• 作者：S. Issac Niwas (1)
  Weisi Lin (1)
  Xiaolong Bai (2) (3)
  Chee Keong Kwoh (1)
  Chelvin C. Sng (5)
  M. Cecilia Aquino (4)
  P. T. K. Chew (5)
  
  1. School of Computer Engineering ; Nanyang Technological University (NTU) ; Singapore ; 639798 ; Singapore
  2. The State Key Laboratory of Fluid Power Transmission and Control ; Zhejiang University ; Hangzhou ; 310027 ; People鈥檚 Republic of China
  3. School of Electrical and Electronics Engineering ; Nanyang Technological University (NTU) ; Singapore ; 639798 ; Singapore
  5. Department of Ophthalmology ; Yong Loo Lin School of Medicine ; National University of Singapore (NUS) ; Singapore ; 119228 ; Singapore
  4. Eye Surgery Centre ; National University Health System (NUHS) ; Singapore ; 119228 ; Singapore
  
• 关键词：Angle ; closure glaucoma ; Feature selection ; Rank combination method ; Adaboost classifier ; Machine learning
• 刊名：Journal of Medical Systems
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：39
• 期：3
• 全文大小：1,789 KB
• 参考文献：1. Quigley, H. A., and Broman, A. T., 鈥淭he number of people with glaucoma worldwide in 2010 and 2020鈥? / Br. J. Ophthalmol. 90(3):262鈥?67, 2006. CrossRef
  2. Lowe, R. F., 鈥淎etiology of the anatomical basis for primary angle-closure glaucoma. Biometrical comparisons between normal eyes and eyes with primary angle-closure glaucoma鈥? / Br. J. Ophthalmol. 54(3):161鈥?69, 1970. CrossRef
  3. Acharya, U. R., Dua, S., Du, X., Sree, S. V., and Chua, C. K., 鈥淎utomated diagnosis of glaucoma using texture and higher order spectra features鈥? / IEEE Trans. Inf. Technol. Biomed. 15(3):449鈥?55, 2011. CrossRef
  4. Garc铆a G. S., Galilea E. H., 鈥淯sing artificial neural networks to identify glaucoma stages,鈥? In: / The Mystery of Glaucoma, Intech Publishers, 331鈥?52, 2011.
  5. Pachiyappan, A., Das, U. N., Murthy, T. V. S. P., and Tatavarti, R., 鈥淎utomated diagnosis of diabetic retinopathy and glaucoma using Fundus and OCT images鈥? / Lipids Health Dis. 11(73):1鈥?0, 2012.
  6. Mookiah, M. R. K., Acharya, U. R., Lim, C. M., Petznick, A., and Suri, J. S., 鈥淒ata mining technique for automated diagnosis of glaucoma using higher order spectra and wavelet energy features鈥? / Knowl.-Based Syst. 33:73鈥?2, 2012. CrossRef
  7. Krishnan, M. M. R., 鈥淎utomated glaucoma detection using hybrid feature extraction in retinal fundus images鈥? / J. Mech. Med. Biol. 13(1):1鈥?1, 2013. CrossRef
  8. Nayak, J., Acharya, U. R., Bhat, P. S., Shetty, N., and Lim, T.-C., 鈥淎utomated diagnosis of glaucoma using digital fundus images鈥? / J. Med. Syst. 33:337鈥?46, 2009. CrossRef
  9. Tham, Y. C., Li, X., Wong, T. Y., Quigley, H. A., Aung, T., and Cheng, C. Y., 鈥淕lobal prevalence of glaucoma and projections of glaucoma burden through 2040: A systematic review and meta-analysis鈥? / Ophthalmology 121(11):2081鈥?090, 2014. CrossRef
  10. How, A. C., Baskaran, M., Kumar, R. S., He, M., Foster, P. J., Lavanya, R., Wong, H. T., Chew, P. T. K., Friedman, D. S., and Aung, T., 鈥淐hanges in anterior segment morphology after laser peripheral iridotomy: an anterior segment optical coherence tomography study鈥? / Ophthalmology 119(7):1383鈥?387, 2012. CrossRef
  11. Shabana, N., Aquino, M. C., See, J., Tan, A. M., Nolan, W. P., Hitchings, R., Young, S. M., Loon, S. C., Sng, C. C., Wong, W., and Chew, P. T. K., 鈥淨uantitative evaluation of anterior chamber parameters using anterior segment optical coherence tomography in primary angle closure mechanisms鈥? / Clin. Experiment. Ophthalmol. 40:792鈥?01, 2012. CrossRef
  12. Coyne A, Shovlin J, 鈥淎S-OCT Technology: Analyzing the Anterior Segment鈥? / Review of Optometry, 2012. [Online]. Available: http://www.revoptom.com/continuing_education/tabviewtest/lessonid/108148/.
  13. Han, J.-H., Kang, J. U., and Song, C. G., 鈥淧olarization sensitive subcutaneous and muscular imaging based on common path optical coherence tomography using near infrared source鈥? / J. Med. Syst. 35:521鈥?26, 2011. CrossRef
  14. Acharya, U. R., Yun, W. L., Ng, E. Y., Yu, W., and Suri, J. S., 鈥淚maging system of human eye: A review鈥? / J. Med. Syst. 32(4):301鈥?15, 2008. CrossRef
  15. Nongpiur, M. E., Ku, J. Y., and Aung, T., 鈥淎ngle closure glaucoma: a mechanistic review鈥? / Curr. Opin. Ophthalmol. 22(2):96鈥?01, 2011. CrossRef
  16. Ng, W. T., and Morgan, W., 鈥淢echanisms and treatment of primary angle closure: a review鈥? / Clin. Experiment. Ophthalmol. 40(4):e218鈥揺228, 2012. CrossRef
  17. Leung, K., Chan, W. M., Ko, C. Y., Chui, S. I., Woo, J., Tsang, M. K., and Tse, R. K., 鈥淰isualization of anterior chamber angle dynamics using optical coherence tomography鈥? / Ophthalmology 112:980鈥?84, 2005. CrossRef
  18. Sng, C. C., Aquino, M. C., Liao, J., Ang, M., Zheng, C., Loon, S. C., and Chew, P. T. K., 鈥淧retreatment anterior segment imaging during acute primary angle closure: insights into angle closure mechanisms in the acute phase鈥? / Ophthalmology 121(1):119鈥?25, 2014. CrossRef
  19. Wirawan, A., Kwoh, C. K., Chew, P. T. K., Aquino, M. C. D., Seng, C. L., See, J., Zheng, C., and Lin, W., 鈥淔eature selection for computer-aided angle closure glaucoma mechanism detection鈥? / J. Med. Imaging Health Informat. 2(4):438鈥?44, 2012. CrossRef
  20. Saeys Y, Abeel T, Peer YV, 鈥淩obust feature selection using ensemble feature selection techniques鈥? In: Proc. 25th European Conference on Machine Learning and Knowledge Discovery in Databases, Part II, Springer-Verlag, Berlin, Heidelberg, 313鈥?25, 2008.
  21. Peng, H., Long, F., and Ding, C., 鈥淔eature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy鈥? / IEEE Trans. Pattern Anal. Mach. Intell. 27(8):1226鈥?238, 2005. CrossRef
  22. 艦en B, Peker M, 脟avu艧o臒lu A, 脟elebi FV, 鈥淎 comparative study on classification of sleep stage based on EEG signals using feature selection and classification algorithms鈥? / J. Med. Syst. 38, no. 18, 2014. (DOI: 10.1007/s10916-014-0018-0 ).
  23. He, X., Cai, D., and Niyogi, P., / 鈥淟aplacian score for feature selection鈥? in Advances in Neural Information Processing System, vol. 17. MIT Press, Cambridge, 2005.
  24. Liu H, Setiono R, 鈥淐hi2: Feature selection and discretization of numeric attributes鈥? In: Proc. 7th IEEE Int. Conf. Tools with Artificial Intelligence, 388鈥?91, 1995.
  25. Duda, R. O., Hart, P. E., and Stork, D. G., / 鈥淧attern classification鈥?/em>. Wiley, New York, 2001.
  26. Zhao, Z., Morstatter, F., Sharma, S., Alelyani, S., Anand, A., and Liu, H., / 鈥淎dvancing feature selection research: ASU Feature selection repository鈥?/em>. TR-10-007, School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, Tempe, 2007.
  27. Cawley G, Talbot N, Girolami M, 鈥淪parse multinomial logistic regression via Bayesian L1 regularisation鈥? In: / Advances in Neural Information Processing Systems 19:209鈥?16, 2007.
  28. Li, Y. J., Hsu, D. F., and Chung, S. M., 鈥淐ombination of multiple feature selection methods for text categorization by using combinatorial fusion analysis and rank-score characteristic鈥? / Int. J. Artif. Intell. Tools 22(2):1350001鈥?350025, 2013. CrossRef
  29. Freund, Y., and Schapire, R. E., 鈥淎 Decision-Theoretic generalization of on-line learning鈥? / J. Comput. Syst. Sci. 55:119鈥?39, 1997. CrossRef
  30. Yoo, I., Alafaireet, P., Marinov, M., Keila, P.-H., Gopidi, R., Chang, J.-F., and Hua, L., 鈥淒ata mining in healthcare and biomedicine: A survey of the literature鈥? / J. Med. Syst. 36(4):2431鈥?448, 2012. CrossRef
  31. Ozcift, A., and Gulten, A., 鈥淎 robust multi-class feature selection strategy based on rotation forest ensemble algorithm for diagnosis of Erythemato-Squamous diseases鈥? / J. Med. Syst. 36:941鈥?49, 2012. CrossRef
  
• 刊物类别：Mathematics and Statistics
• 刊物主题：Statistics
  Statistics for Life Sciences, Medicine and Health Sciences
  Health Informatics and Administration
  
• 出版者：Springer Netherlands
• ISSN：1573-689X

文摘

Glaucoma is an eye disease where a loss of vision occurs as a result of progressive optic nerve damage usually associates with high intraocular pressure. A subtype of glaucoma called primary angle-closure glaucoma (PACG) has been observed to be the result of one or more mechanisms such as Pupil block, Plateau iris, Peripheral iris roll, and Lens in the anterior segment of the eye. Reliable features in anterior segment images are important for determining the specific mechanisms involved in PACG. In this paper, first the discriminant features are selected by several feature selection algorithms in the context of PACG detection based on anterior segment optical coherence tomography (AS-OCT) images, and then a novel criteria is proposed to further select more reliable features. Our approach is based on selecting the top-ranked features in each algorithm and its rank combination for selection of the best features. Compared with the features selected by the individual feature selection methods, the features selected by our method achieves the best performance in terms of the accuracy of classification of the four PACG mechanisms by using AdaBoost classifier.