Layer-Wise Pre-Training Low-Rank NMF Model for Mammogram-Based Breast Tumor Classification

doi:10.1007/s40305-019-00262-z

Journal of the Operations Research Society of China ›› 2019, Vol. 7 ›› Issue (4): 515-537.doi: 10.1007/s40305-019-00262-z

所属专题： Continuous Optimization

收稿日期:2018-06-18 修回日期:2018-11-03 出版日期:2019-11-30 发布日期:2019-11-28
通讯作者: Xiao-Hui Yang, Wen-Ming Wu, Yun-Mei Chen, Juan Zhang, Dan Long, Li-Jun Yang, Chen-Xi Tian E-mail:xhyanghenu@163.com;wmwu55@163.com;yun@ufl.edu;zhangjuan_496@163.com;legend_long@aliyun.com;yanglijun@henu.edu.cn;tcxhaha@163.com

Layer-Wise Pre-Training Low-Rank NMF Model for Mammogram-Based Breast Tumor Classification

Wen-Ming Wu¹, Xiao-Hui Yang¹, Yun-Mei Chen², Juan Zhang³, Dan Long³, Li-Jun Yang¹, Chen-Xi Tian¹

1 Data Analysis Technology Lab, Institute of Applied Mathematics, School of Mathematics and Statistics, Henan University, Kaifeng 475004, Henan, China;
2 Department of Mathematics, University of Florida, Gainesville, FL 32611, USA;
3 Zhejiang Cancer Hospital, Hangzhou 310022, China

Received:2018-06-18 Revised:2018-11-03 Online:2019-11-30 Published:2019-11-28
Contact: Xiao-Hui Yang, Wen-Ming Wu, Yun-Mei Chen, Juan Zhang, Dan Long, Li-Jun Yang, Chen-Xi Tian E-mail:xhyanghenu@163.com;wmwu55@163.com;yun@ufl.edu;zhangjuan_496@163.com;legend_long@aliyun.com;yanglijun@henu.edu.cn;tcxhaha@163.com
Supported by:
This work was supported in part by the National Natural Science Foundation of China (No. 11701144), National Science Foundation of US (No. DMS1719932), Natural Science Foundation of Henan Province (No. 162300410061) and Project of Emerging Interdisciplinary (No. xxjc20170003).

摘要/Abstract

Abstract: Image-based breast tumor classification is an active and challenging problem. In this paper, a robust breast tumor classification framework is presented based on deep feature representation learning and exploiting available information in existing samples. Feature representation learning of mammograms is fulfilled by a modified nonnegative matrix factorization model called LPML-LRNMF, which is motivated by hierarchical learning and layer-wise pre-training (LP) strategy in deep learning. Low-rank (LR) constraint is integrated into the feature representation learning model by considering the intrinsic characteristics of mammograms. Moreover, the proposed LPML-LRNMF model is optimized via alternating direction method of multipliers and the corresponding convergence is analyzed. For completing classification, an inverse projection sparse representation model is introduced to exploit information embedded in existing samples, especially in test ones. Experiments on the public dataset and actual clinical dataset show that the classification accuracy, specificity and sensitivity achieve the clinical acceptance level.

Key words: Breast tumor classification, Mammogram, LPML-LRNMF, Inverse space sparse representation, ADMM

中图分类号:

68T10

. [J]. Journal of the Operations Research Society of China, 2019, 7(4): 515-537.

Wen-Ming Wu, Xiao-Hui Yang, Yun-Mei Chen, Juan Zhang, Dan Long, Li-Jun Yang, Chen-Xi Tian. Layer-Wise Pre-Training Low-Rank NMF Model for Mammogram-Based Breast Tumor Classification[J]. Journal of the Operations Research Society of China, 2019, 7(4): 515-537.

参考文献

[1] Gao,Y.,Church,P.G.:Improvingmolecularcancerclassdiscoverythroughsparsenon-negativematrix factorization. Bioinformatics 21, 3970-3975(2005)
[2] Lou, P., Qian, W., Romilly, P.:CAD-aided mammogram training. Acad. Radiol. 12, 1039-1048(2005)
[3] Dorsi, C.J., Kopans, D.B.:Mammography interpretation:the BI-RADS method. Am. Fam. Phys. 55, 1548-1550(1997)
[4] Liu, S., Babbs, C.F., Delp, E.J.:Multiresolution detection of spiculated lesions in digital mammograms. IEEE Trans. Image Process. 10, 874-884(2001)
[5] Ebrahim, A.Y.:Detection of breast cancer in mammograms through a new features and decision tree based classification framework. J. Theor. Appl. Inf. Technol. 95, 6256-6267(2017)
[6] Catanzariti, E., Ciminello, M., Prevete, R.:Computer aided detection of clustered microcalcifications in digitized mammograms using Gabor functions. In:International Conference on Image Analysis and Processing, pp. 266-270(2003)
[7] Oliver, A., Torrent, A., Llado, X., Marti, J.:Automatic diagnosis of masses by using level set segmentation and shape description. In:International Conference on Pattern Recognition, pp. 2528-2531(2010)
[8] Rashed, E., Ismail, I., Zaki, S.:Multiresolution mammogram analysis in multilevel decomposition. Pattern Recognit. Lett. 28, 286-292(2007)
[9] Bengio, Y., Courville, A., Vincent, P.:Representation learning:a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35, 1798-1828(2012)
[10] Lecun, Y., Bengio, Y., Hinton, G.:Deep learning. Nature 521, 436(2015)
[11] Han, Z., Wei, B., Zheng, Y., Yin, Y., Li, K., Li, S.:Breast cancer multi-classification from histopathological images with structured deep learning. Sci. Rep. 7, 4172(2017)
[12] Lee, D., Seung, H.:Learning the parts of objects by non-negative matrix factorization. Nature 401, 788-791(1999)
[13] Sauwen, N., Sima, D., Acou, M., Achten, E., Maes, F.:A semi-automated segmentation framework for MRI based brain tumor segmentation using regularized nonnegative matrix factorization. In:International Conference on Signal-Image Technology and Internet-Based Systems, pp. 88-95(2017)
[14] Tsinos, C.G., Rontogiannis, A., Berberidis, K.:Distributed blind hyperspectral unmixing via joint sparsity and low-rank constrained non-negative matrix factorization. IEEE Trans. Comput. Imaging 3, 160-174(2017)
[15] Liu, W., Peng, F., Feng, S., You, J., Chen, Z.:Semantic feature extraction for brain CT image clustering using nonnegative matrix factorization. In:Medical Biometrics, First International Conference, vol. 4901, pp. 41-48(2008)
[16] Zheng, C.H., Ng, T.Y., Zhang, L., Shiu, C.K., Wang, H.Q.:Tumor classification based on non-negative matrix factorization using gene expression data. IEEE Trans. Nanobiosci. 10, 86-93(2011)
[17] Shang, R., Wang, W., Stolkin, R., Jiao, L.:Nonnegative spectral learning and sparse regression-based dual-graph regularized feature selection. IEEE Trans. Cybern. 48, 793-806(2017)
[18] Shang, R., Zhang, Z., Jiao, L., Wang, W., Yang, S.:Global discriminative-based nonnegative spectral clustering. Pattern Recognit. 55, 172-182(2016)
[19] Shang,R.,Yuan,Y.,Jiao,L.,Hou,B.,Esfahani,A.M.G.:AfastalgorithmforSARimagesegmentation based on key pixels. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 99, 1-17(2017)
[20] Li, X., Cui, G., Dong, Y.:Graph regularized non-negative low-rank matrix factorization for image clustering. IEEE Trans. Cybern. 47, 3840-3853(2017)
[21] Yang, X.H., Wu, W., Chen, Y., Li, X., Zhang, J., Long, D., Yang, L.:An integrated inverse space sparse representation framework for tumor classification. Pattern Recognit. 93, 293-311(2019)
[22] Fazel, M.:Matrix rank minimization with applications. Ph.D. dissertation, Stanford University, Stanford, CA, USA (2002)
[23] Recht, B.:A simpler approach to matrix completion. J. Mach. Learn. Res. 12, 3413-3430(2009)
[24] Hestenes, M.:Multiplier and gradient methods. J. Optim. Theory Appl. 4, 303-320(1969)
[25] Yuan, X., Yang, J.:Sparse and low rank matrix decomposition via alternating direction method. Pac. J. Optim. 9, 167-180(2013)
[26] Boyd, S., Parikh, N., Chu, E., Peleato, B., Eckstein, J.:Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3, 1-122(2010)
[27] Gabay, G., Mercier, B.:A dual algorithm for the solution of nonlinear variational problems via finite element approximation. Comput. Math Appl. 2, 17-40(1976)
[28] Zhang, G., Yan, P., Zhao, H., Zhang, X.:A computer aided diagnosis system in mammography using artificial neural networks. In:IEEE International Conference on BioMedical Engineering and Informatics, vol. 2, pp. 823-826(2008)
[29] Varela, C., Tahoces, P., Mendez, A., Souto, M., Vidal, J.:Computerized detection of breast masses in digitized mammograms. Comput. Biol. Med. 37, 214-226(2007)
[30] Cover, T., Hart, P.:Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13, 21-27(1967)
[31] Furey, T., Cristianini, N., Duffy, N., Bednarski, D., Schummer, M., Haussler, D.:Support vector machine classification and validation of cancer tissue samples using microarray expression data. Bioinformatics 16, 906-914(2000)
[32] Wright, J., Yang, A., Ganesh, A., Sastry, S., Ma, Y.:Robust face recognition via sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 31, 210-227(2009)
[33] Nasir, M., Baig, A., Khanum, A.:Brain tumor classification in MRI scans using sparse representation. In:International Conference on Image & Signal Processing, vol. 8509, pp. 629-637(2014)
[34] Guo, Y., Wang, Y., Kong, D., Shu, X.:Automatic classification of intracardiac tumor and thrombi in echocardiography based on sparse representation. IEEE J. Biomed. Health Inform. 19, 601-611(2015)
[35] Zhang, L., Yang, M., Feng, X.:Sparse representation or collaborative representation:which helps face recognition? In:IEEE International Conference on Computer Vision, vol. 2011, pp. 471-478(2012)
[36] Yang, X., Liu, F., Tian, L., Li, H., Jiang, X.Y.:Pseudo-full-space representation based classification for robust face recognition. Signal Process. Image Commun. 60, 64-78(2018)
[37] Lin, J.:Projected gradient methods for nonnegative matrix factorization. Neural Comput. 19, 2756-2779(2007)
[38] Hoyer, P.:Non-negative sparse coding. In:IEEE Workshop on Neural Networks for Signal Processing. pp. 557-565(2004)
[39] Cai, J., Caneds, E., Shen, Z.:A singular value thresholding algorithm for matrix completion. SIAM J. Optim. 20, 1956-1982(2008)
[40] Strang, G.:The discrete cosine transform. SIAM Rev. 41, 135-147(1999)
[41] Bradley, A.P.:The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit. 30, 1145-1159(1997)
[42] Kwok, J.Y.:Moderating the outputs of support vector machine classifiers. IEEE Trans. Neural Netw. 10, 1018-1031(1999)
[43] Vickers, A.J., Elkin, E.:Decision curve analysis:a novel method for evaluating prediction models. Med. Decis. Mak. 26, 565-574(2006)
[44] Yang, M., Zhang, L., Yang, J., Zhang, D.:Regularized robust coding for face recognition. IEEE Trans. Image Process. 22, 1753-1766(2013)
[45] Deng, W., Hu, J., Guo, J.:Extended SRC:undersampled face recognition via intraclass variant dictionary. IEEE Trans. Pattern Anal. Mach. Intell. 34, 1864-1870(2012)
[46] Setiawan, A.S., Wesley, J., Purnama, Y.:Mammogram classification using law's texture energy measure and neural networks. Procedia Comput. Sci. 59, 92-97(2015)
[47] Kutluk, S., Günsel, B.:Tissue density classification in mammographic images using local features. In:Signal Processing and Communications Applications Conference, vol. 32, pp. 1-4(2013)
[48] Rampun, A., Scotney, B., Morrow, P., Wang, H., Winder, J.:Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms. J. Imaging 4, 14(2018)
[49] Herwanto, A.M.A., Arymurthy, A.M.:Association technique based on classification for classifying microcalcification and mass in mammogram. Int. J. Comput. Sci. Issues 10, 252-259(2013)
[50] Golub, G.H., Loan, C.F.V.:Matrix Computations, pp. 242-243. Johns Hopkins University Press, Baltimore (1996)

Layer-Wise Pre-Training Low-Rank NMF Model for Mammogram-Based Breast Tumor Classification

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

本文评价