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

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.

[1]  Lei Zhang,et al.  Sparse representation or collaborative representation: Which helps face recognition? , 2011, 2011 International Conference on Computer Vision.

[2]  Fei Peng,et al.  Semantic Feature Extraction for Brain CT Image Clustering Using Nonnegative Matrix Factorization , 2008, ICMB.

[3]  Yunmei Chen,et al.  An integrated inverse space sparse representation framework for tumor classification , 2018, Pattern Recognit..

[4]  Roberto Prevete,et al.  Computer aided detection of clustered microcalcifications in digitized mammograms using Gabor functions , 2003, 12th International Conference on Image Analysis and Processing, 2003.Proceedings..

[5]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[6]  B. Mercier,et al.  A dual algorithm for the solution of nonlinear variational problems via finite element approximation , 1976 .

[7]  Xin Zhang,et al.  A Computer Aided Diagnosis System in Mammography Using Artificial Neural Networks , 2008, 2008 International Conference on BioMedical Engineering and Informatics.

[8]  Yudy Purnama,et al.  Mammogram Classification using Law's Texture Energy Measure and Neural Networks , 2015 .

[9]  Benjamin Recht,et al.  A Simpler Approach to Matrix Completion , 2009, J. Mach. Learn. Res..

[10]  Yuanjie Zheng,et al.  Breast Cancer Multi-classification from Histopathological Images with Structured Deep Learning Model , 2017, Scientific Reports.

[11]  Gene H. Golub,et al.  Matrix computations , 1983 .

[12]  Patrik O. Hoyer,et al.  Non-negative sparse coding , 2002, Proceedings of the 12th IEEE Workshop on Neural Networks for Signal Processing.

[13]  C J D'Orsi,et al.  Mammography interpretation: the BI-RADS method. , 1997, American family physician.

[14]  Xuelong Li,et al.  Graph Regularized Non-Negative Low-Rank Matrix Factorization for Image Clustering , 2017, IEEE Transactions on Cybernetics.

[15]  James T. Kwok.  Moderating the outputs of support vector machine classifiers , 1999, IEEE Trans. Neural Networks.

[16]  Andrew P. Bradley,et al.  The use of the area under the ROC curve in the evaluation of machine learning algorithms , 1997, Pattern Recognit..

[17]  Sabine Van Huffel,et al.  A Semi-Automated Segmentation Framework for MRI Based Brain Tumor Segmentation Using Regularized Nonnegative Matrix Factorization , 2016, 2016 12th International Conference on Signal-Image Technology & Internet-Based Systems (SITIS).

[18]  Ronghua Shang,et al.  Non-Negative Spectral Learning and Sparse Regression-Based Dual-Graph Regularized Feature Selection , 2018, IEEE Transactions on Cybernetics.

[19]  Essam A. Rashed,et al.  Multiresolution mammogram analysis in multilevel decomposition , 2007, Pattern Recognit. Lett..

[20]  Pierre Moulin,et al.  Complexity-regularized image denoising , 2001, IEEE Trans. Image Process..

[21]  Sezer Kutluk,et al.  Tissue density classification in mammographic images using local features , 2013, 2013 21st Signal Processing and Communications Applications Conference (SIU).

[22]  Aniati Murni Arymurthy,et al.  Association Technique based on Classification for Classifying Microcalcification and Mass in Mammogram , 2013 .

[23]  Aasia Khanum,et al.  Brain Tumor Classification in MRI Scans Using Sparse Representation , 2014, ICISP.

[24]  Sheng Liu,et al.  Multiresolution detection of spiculated lesions in digital mammograms , 2001, IEEE Trans. Image Process..

[25]  Lei Zhang,et al.  Tumor Classification Based on Non-Negative Matrix Factorization Using Gene Expression Data , 2011, IEEE Transactions on NanoBioscience.

[26]  Shuyuan Yang,et al.  Global discriminative-based nonnegative spectral clustering , 2016, Pattern Recognit..

[27]  Hui Wang,et al.  Breast Density Classification Using Local Quinary Patterns with Various Neighbourhood Topologies , 2018, J. Imaging.

[28]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[29]  Yuan Gao,et al.  Improving molecular cancer class discovery through sparse non-negative matrix factorization , 2005 .

[30]  Jian Yang,et al.  Regularized Robust Coding for Face Recognition , 2012, IEEE Transactions on Image Processing.

[31]  Jun Guo,et al.  Extended SRC: Undersampled Face Recognition via Intraclass Variant Dictionary , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Yuanyuan Wang,et al.  Automatic Classification of Intracardiac Tumor and Thrombi in Echocardiography Based on Sparse Representation , 2015, IEEE Journal of Biomedical and Health Informatics.

[33]  Wei Qian,et al.  CAD-Aided Mammogram Training1 , 2005 .

[34]  Nello Cristianini,et al.  Support vector machine classification and validation of cancer tissue samples using microarray expression data , 2000, Bioinform..

[35]  Chih-Jen Lin,et al.  Projected Gradient Methods for Nonnegative Matrix Factorization , 2007, Neural Computation.

[36]  Xiaoming Yuan,et al.  Sparse and low-rank matrix decomposition via alternating direction method , 2013 .

[37]  Gilbert Strang,et al.  The Discrete Cosine Transform , 1999, SIAM Rev..

[38]  Arturo J. Méndez,et al.  Computerized detection of breast masses in digitized mammograms , 2007, Comput. Biol. Medicine.

[39]  E. Elkin,et al.  Decision Curve Analysis: A Novel Method for Evaluating Prediction Models , 2006, Medical decision making : an international journal of the Society for Medical Decision Making.

[40]  Xavier Lladó,et al.  Automatic Diagnosis of Masses by Using Level set Segmentation and Shape Description , 2010, 2010 20th International Conference on Pattern Recognition.

[41]  Allen Y. Yang,et al.  Robust Face Recognition via Sparse Representation , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[42]  Emmanuel J. Candès,et al.  A Singular Value Thresholding Algorithm for Matrix Completion , 2008, SIAM J. Optim..

[43]  Li Tian,et al.  Pseudo-full-space representation based classification for robust face recognition , 2018, Signal Process. Image Commun..

[44]  Christos G. Tsinos,et al.  Distributed Blind Hyperspectral Unmixing via Joint Sparsity and Low-Rank Constrained Non-Negative Matrix Factorization , 2017, IEEE Transactions on Computational Imaging.

[45]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[46]  M. Hestenes.  Multiplier and gradient methods , 1969 .

[47]  H. Sebastian Seung,et al.  Learning the parts of objects by non-negative matrix factorization , 1999, Nature.

[48]  Philip J. Morrow,et al.  Breast Density Classification Using Multiresolution Local Quinary Patterns in Mammograms , 2017, MIUA.

[49]  Ronghua Shang,et al.  A Fast Algorithm for SAR Image Segmentation Based on Key Pixels , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[50]  Stephen P. Boyd,et al.  Distributed Optimization and Statistical Learning via the Alternating Direction Method of Multipliers , 2011, Found. Trends Mach. Learn..