Skin lesion feature vectors classification in models of a Riemannian manifold
详细信息 查看全文
- 作者：Nikolay Metodiev Sirakov ; Ye-Lin Ou…
- 关键词：Feature vectors ; Riemannian manifold ; Support vector machines ; Classification ; Intervals of confidence ; 62H35 ; 68U10 ; 68P10
- 刊名：Annals of Mathematics and Artificial Intelligence
- 出版年：2015
- 出版时间：October 2015
- 年：2015
- 卷：75
- 期：1-2
- 页码：217-229
- 全文大小：863 KB
- 参考文献：1.Mete, M., Ou, Y.-L., Sirakov, N. M.: Skin Lesion Feature Vector Space With A Metric To Model Geometric Structures Of Malignancy, R.P. Barneva, V. Brimkov, J. Aggarval(Eds.): IWCIA 2012, LNCS 7655, Springer Verlag, pp. 285-297 (2012)
2.Nachbar, F., Stolz, W., Merkle, T., et al.: The ABCD rule of dermatoscopy: High prospective value in the diagnosis of doubtful melanocytic skin lesions. J.. Am. Acad. Dermatol. 30 (4), 551鈥?59 (1994)CrossRef
3.Argenziano, G., Fabbrocini, G., Carli, P., De Giorgi, V., Sammarco, E., Delfino, M.: Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions. Comparison of ABCD rule of dermatoscopy and a new 7-point checklist based on pattern analysis. Arch. Dermatol 134, 1563鈥?570 (1998)CrossRef
4.American Cancer Society: Cancer Facts & Figures 2010, http://鈥媤ww.鈥媍ancer.鈥媜rg/鈥?/span> . Accessed July, 26 (2010)
5.Argenziano, G., Soyer, H.P., De Giorgi, V., et al.: Interactive atlas of dermoscopy. Milan. EDRA Medical Pub, Italy (2000)
6.Sirakov, N.M., Ushkala, K.: An integral active contour model for convex hull and bound- ary extraction. In: Bebis, G. et al. (Eds), LNCS, Vol. 5876, Springer, pp. 1031-1040 (2009)
7.Silveira, M., Marques, J.S.: :Level set segmentation of dermoscopy images, 5th IEEE ISBI: From Nano to Macro, Paris, 14-17 May 2008, pp. 173 - 176, (2008). doi:10.鈥?109/鈥婭SBI.鈥?008.鈥?540960
8.Zhou, H., Schaefer, Celebi, M.E., Lin, F.: : Gradient vector flow with mean shift for skin lesion segmentation. Comp. Med. Imaging Graphics 35 (I.2), 121鈥?27 (2011)CrossRef
9.Sadeghi, M., Razmara, M., Atkins, M.S., Lee, T.K.: :A novel method for detection of pigment network in dermoscopic images using graphs. Comput. Med. Imaging Graphics 35 (2), 137鈥?43 (2011)CrossRef
10.Xie, F., Bovik, A.: :Automatic segmentation of dermoscopy images using self-generating neural networks seeded by genetic algorithm. Journal of Pattern Recognition 46 (3), 1012鈥?019 (2013)CrossRef
11.Maglogiannis, I.: Doukas, G.N.:Overview of Advanced Computer Vision Systems for Skin Lesions Characterization, IEEE Tran. on Information Technology in Biomedicine, V. 13, NO. 5. SEPTEMBER (2009)
12.Gilmore, S., Hofmann-Wellenhof, R., Soyer, P. H.: A support vector machine for decision support in melanoma recognition. Exp Dermatol 830-5 (2010), 19 (2010)
13.Alcon, J.F, Ciuhu, C., Kate, W., Heinrich, A., Uzunbajakava, N., Krekels, G., Siem, D., Haan, G.: :Automatic Imaging System With Decision Support for Inspection of Pigmented Skin Lesions and Melanoma Diagnosis. IEEE J. Sel. Top Signal Proc. 3 (1) (2009)
14.Mete, M., Sirakov, N.M.: Application of active contour and density based models for lesion detection in dermoscopy images. In: BMC Bioinformatics 2010, 11(Suppl 6):S23 (2010). doi:10.1186/1471-2105-11-S6-S23
15.Mete, M., Sirakov, N.M.: Dermoscopic diagnosis of melanoma in a 4D feature space constructed by active contour extracted features. Journal of Medical Imaging and Graphics 2012 (36), 572鈥?79 (2012)CrossRef
16.Nara, C.: : Active contour on the exact solution of the active convex hull model working with noise, Master Degree Thesis, Texas A and M Univ. Commer 07, 01 (2011)
17.Mulchrone, K., Choudhury, K.: Fitting an ellipse to an arbitrary shape: implications for strain analysis. J. Struct Geol. 26 (1), 143鈥?53 (2004)CrossRef
18.O鈥橬eill, B.: Semi-Riemannian geometry with applications to relativity. Academic Press, New York (1983)MATH
19.Petersen, P.: Riemannian geometry, Vol. 171. Springer-Verlag, New York (1998)CrossRef
20.Scholkopf, B., Smola, A.J., Williamson, R. C., Bartlett, P. L.: New Support Vector Algorithms. Neural Comput. 12, 1207鈥?245 (2000)CrossRef
21.Sirakov, N.M., Mete, M., Nara, S.C.: Automatic boundary detection and symmetry calculation in dermoscopy images of skin lesions, IEEE ICIP2011, Brussels, pp. 1637-1640 (2011)
22.Thieu, Q.T., Luong, M., Rocchisani, J.M., Vienne, E.: A convex active contour region-based model for image segmentation. Proc. CAIP鈥?1, Part I, LNCS, Vol. 6854, Springer-Verlag Berlin, Heidelberg, pp. 135-143 (2011)
23.Vapnik, V.: The Nature of Statistical Learning Theory. Springer, New York (1995)MATH CrossRef
24.Chang, C.C., Lin, C.-J.: LIBSVM: a library for support vector machines, Vol. 2 (2011). http://鈥媤ww.鈥媍sie.鈥媙tu.鈥媏du.鈥媡w/鈥媬cjlin/鈥媗ibsvm
25.Devore, J., Berk, K.: Modern mathematical statistics with applications. International Student Edition ed. Belmont, CA: Thomson Higher Education (2007)
26.Blackledge, J.M., Dubovitskiy, D.A.: Object Detection and Classification with Applications to Skin Cancer Screening. ISAST Tran. Intiligent Syst. 1 (2) (2008) - 作者单位：Nikolay Metodiev Sirakov (1)
Ye-Lin Ou (2)
Mutlu Mete (3)
1. Department of Mathematics, Department of Computer Science, Texas A & M University-Commerce, Commerce, Texas, USA
2. Department of Mathematics, Texas A & M University-Commerce, Commerce, Texas, USA
3. Department of Computer Science, Texas A & M University-Commerce, Commerce, Texas, USA - 刊物类别：Computer Science
- 刊物主题：Artificial Intelligence and Robotics
Mathematics
Computer Science, general
Complexity - 出版者：Springer Netherlands
- ISSN：1573-7470
文摘
This study is a continuation of a work published by Mete, Ou, and Sirakov (2012), where a model of a 4D manifold of feature vectors was developed. The present paper introduces an improved metric in the 4D manifold first and then extends both the size of the sample space and the dimension (to 6D) of the manifold model in which the sample space lies. As a result, we not only overcame the issue of one single vector representing multiple skin lesions, which occurred in the work of Mete, Ou, and Sirakov (2012), but also improved the accuracy of classification. Furthermore, a statistical evaluation of our support vector machine (SVM) classification method was performed. The intervals of confidence were calculated for the mean of classification of a large sample set in the 6D model. Comparison results of classification with our SVM in 4D and 6D models using 10-fold cross-validation are given at the end of the paper. It is found that the 6D model improves the classification results of the previous study suggesting that two newly introduced features contributed to the increase of the classification accuracy. Keywords Feature vectors Riemannian manifold Support vector machines Classification Intervals of confidence