ICTACT Journal on Soft Computing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Deep Learning Feature Extraction with Ensemble Spectral Cluster and Gaussian Mixture for Malicious Tumor Detection


Affiliations
1 Department of Computer Science, Government Arts College, Udumalpet, India
2 Department of Computer Science, Government Arts College, Coimbatore, India
     

   Subscribe/Renew Journal


Different clustering algorithms produce distinct sub-divisions as they apply disparate partition on the data. Hence, no single clustering algorithm is said to be optimal and therefore resulting in different partitions. To utilize the complementary nature of different partitions, ensemble clustering is used. The work in this paper focuses on producing ensembles through several clustering algorithms that perform feature extraction using deep learning and malicious tumor detection through ensemble cluster. In this study, to improve the performance and reduce the complexity involved in the malicious tumor detection process, Deep Learning Feature Extraction (DLFE) technique is presented. Furthermore, to improve the quality of results obtained, ensemble clusters namely, Normalized Spectral Cluster and Gaussian Mixture technique has been applied to the extracted features. The experimental results of the proposed technique have been evaluated and validated for performance and quality analysis on three datasets based on accuracy, sensitivity, specificity. The experimental results achieved 85.28% accuracy, 70.43% specificity, and 97.19% sensitivity, demonstrating the effectiveness of the proposed technique for identifying normal and abnormal tissues from various test images. The simulation results prove the significance in terms of quality parameters and accuracy in comparison to the state-of-the-art techniques.

Keywords

Clustering Algorithm, Deep Learning, Feature Extraction, Normalized Spectral Cluster, Gaussian Mixture.
Subscription Login to verify subscription
User
Notifications
Font Size

  • Eyad Elyan and Mohamed Medhat Gaber, “A fine-Grained Random Forests using Class Decomposition: An Application to Medical Diagnosis”, Neural Computing and Applications, Vol. 27, No. 8, pp. 2279-2288, 2015.

  • Zhiwen Yu, Hongsheng Chen Jane You, Hau-San Wong, Jiming Liu, Le Li and Guoqiang Han, “Double Selection based Semi-Supervised Clustering Ensemble for Tumor Clustering from Gene Expression Profiles”, IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 11, No. 4, pp. 1113-1119, 2014.

  • Smita Prava Mishra, Debahuti Mishra and Srikanta Patnaik, “An Integrated Robust Semi-Supervised Framework for Improving Cluster Reliability using Ensemble Method for Heterogeneous Datasets”, Karbala International Journal of Modern Science, Vol. 1, No. 4, pp. 200-211, 2015.

  • Bartosz Krawczyk, Michal Wozniak and Boguslaw Cyganek, “Clustering-based Ensembles for One-Class Classification”, Information Sciences, Vol. 264, pp. 182-195, 2014.

  • Zhiwen Yu, Hantao Chen, Jane You Jiming Liu, Hau-San Wong and Guoqiang Han, “Adaptive Fuzzy Consensus Clustering Framework for Clustering Analysis of Cancer Data”, IEEE/ACM Transactions on Computational Biology and Bioinformatics, Vol. 12, No. 4, pp. 1123-1129, 2015.

  • Yannik Siegert, Xiaoyi Jiang, Volker Krieg and Sebastian Bartholomaus, “Classification-Based Record Linkage with Pseudonymized Data for Epidemiological Cancer Registries”, IEEE Transactions on Multimedia, Vol. 18, No. 10, pp. 224-237, 2016.

  • Xianxue Yu, Guoxian Yu and Jun Wang, “Clustering Cancer Gene Expression Data by Projective Clustering Ensemble”, PLOS ONE, Vol. 12, No. 2, pp. 1-21, 2017.

  • Ran Qi, Dengyuan Wu, Li Sheng, Donald Henson, Arnold Schwartz, Eric Xu, Kai Xing and Dechang Chen, “On an Ensemble Algorithm for Clustering Cancer Patient Data”, BMC System Biology, Vol. 7, No. 4, pp. 1-9, 2013.

  • Filippo Maria Bianchi, Lorenzo Livi and Cesare Alippi, “Investigating Echo-State Networks Dynamics by Means of Recurrence Analysis”, IEEE Transactions on Neural Networks and Learning Systems, Vol. 29, No. 2, pp. 81-85, 2016.

  • Filippo Maria Bianchi, Enrico Maiorino, Lorenzo Livi, Antonello Rizzi and Alireza Sadeghian, “An Agent-based Algorithm Exploiting Multiple Local Dissimilarities for Clusters Mining and Knowledge Discovery”, Soft Computing, Vol. 21, No. 5, pp. 1347-1369, 2015.

  • Filippo Maria Bianchi, Lorenzo Livi and Antonello Rizzi, “Two Density-based k-means Initialization Algorithms for Non-Metric Data Clustering”, Pattern Analysis and Applications, Vol. 19, No. 3, pp. 745-763, 2015.

  • Asmaa M. Mahmoud, Lamiaa M.E. Bakrawy and Neveen I. Ghali, “Link Prediction in Social Networks based on Spectral Clustering using k-Medoids and Landmark”, International Journal of Computer Applications, Vol. 168, No. 7, pp. 1-8, 2017.

  • Bushra Mughal, Muhammad Sharif and Nazeer Muhammad, “Bi-Model Processing for Early Detection of Breast Tumor in CAD System”, The European Physical Journal Plus, Vol. 16, No. 4, pp. 132-136, 2017.

  • Nilesh Bhaskarrao Bahadure, Arun Kumar Ray and Har Pal Thethi, “Image Analysis for MRI Based Brain Tumor Detection and Feature Extraction using Biologically Inspired BWT and SVM”, International Journal of Biomedical Imaging, Vol. 2017, pp. 1-12, 2017.

  • Zhiwen Yu, Xianjun Zhu, Hau-San Wong, Jane You, Jun Zhang and Guoqiang Han, “Distribution-Based Cluster Structure Selection”, IEEE Transactions on Cybernetics, Vol. 47, No. 11, pp. 3554-3567, 2016.

  • Anirban Mukhopadhyay, Sanghamitra Bandyopadhyay and Ujjwal Maulik, “Multi-Class Clustering of Cancer Subtypes through SVM Based Ensemble of Pareto-Optimal Solutions for Gene Marker Identification”, PLOS ONE, Vol. 5, No. 11, pp. 1-7, 2010.

  • Mohammad Raihanul Islam, Md. Mustafizur Rahman, Asif Salekin and Ahmed Shayer Andalib, “A Novel Approach for Generating Clustered Based Ensemble of Classifiers”, International Journal of Machine Learning and Computing, Vol. 3, No. 1, pp. 137-141, 2013.

  • Andreas Geyer-Schulz and Michael Ovelgonne, “The Randomized Greedy Modularity Clustering Algorithm and the Core Groups Graph Clustering Scheme”, German-Japanese Interchange of Data Analysis Results, 2014.

  • Natthakan Iam-On, Tossapon Boongoen and Simon Garrett, “LCE: A Link-Based Cluster Ensemble method for Improved Gene Expression Data Analysis”, Bioinformatics, Vol. 26, No. 12, pp. 1513-1519, 2010.

  • P. Tamayo, D. Slonim, J. Mesirov, Q. Zhu, S. Kitareewan, E. Dmitrovsky, E.S. Lander and T.R. Golub, “Interpreting Patterns of Gene Expression with Self-Organizing Maps: Methods and Application to Hematopoietic Differentiation”, Proceedings of the National Academy of Sciences, Vol. 96, No. 6, pp. 2907-2912, 1999.

  • A. Bhattacharjee, W.G. Richards and J. Staunton, “Classification of Human Lung Carcinomas by mRNA Expression Profiling Reveals Distinct Adenocarcinomas Sub-Classes”, Proceedings of the National Academy of Sciences, Vol. 98, No. 24, pp. 13790-13795, 2001.


Abstract Views: 222

PDF Views: 2




  • Deep Learning Feature Extraction with Ensemble Spectral Cluster and Gaussian Mixture for Malicious Tumor Detection

Abstract Views: 222  |  PDF Views: 2

Authors

S. Subash Chandra Bose
Department of Computer Science, Government Arts College, Udumalpet, India
T. Christopher
Department of Computer Science, Government Arts College, Coimbatore, India

Abstract


Different clustering algorithms produce distinct sub-divisions as they apply disparate partition on the data. Hence, no single clustering algorithm is said to be optimal and therefore resulting in different partitions. To utilize the complementary nature of different partitions, ensemble clustering is used. The work in this paper focuses on producing ensembles through several clustering algorithms that perform feature extraction using deep learning and malicious tumor detection through ensemble cluster. In this study, to improve the performance and reduce the complexity involved in the malicious tumor detection process, Deep Learning Feature Extraction (DLFE) technique is presented. Furthermore, to improve the quality of results obtained, ensemble clusters namely, Normalized Spectral Cluster and Gaussian Mixture technique has been applied to the extracted features. The experimental results of the proposed technique have been evaluated and validated for performance and quality analysis on three datasets based on accuracy, sensitivity, specificity. The experimental results achieved 85.28% accuracy, 70.43% specificity, and 97.19% sensitivity, demonstrating the effectiveness of the proposed technique for identifying normal and abnormal tissues from various test images. The simulation results prove the significance in terms of quality parameters and accuracy in comparison to the state-of-the-art techniques.

Keywords


Clustering Algorithm, Deep Learning, Feature Extraction, Normalized Spectral Cluster, Gaussian Mixture.

References