Multi-Instance Image Classification for Cancer Diagnosis using Statistical Mapping Support Vector Machine

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    This paper presents multi-instance (MI) image classification for cancer diagnosis using statistical mapping Support Vector Machine (SVM). The existing MI image classification is limited to focusing on standard multi-instance classification (MIC) assumption, but do not generalize to the whole range of MI data and do not fully utilize the power of conventional SVM. The standard MIC assumption labelled a bag of image as positive if there is at least one instance in it which is positive. Unfortunately, this assumption is not applicable if there is less information about abnormal instances provided in a bag. Therefore, the paper aims to propose conventional SVM that utilized the basic statistical mapping to form a bag vector of instances in order to classify MI images and give the benefit of the automated image diagnostic procedure. Numerical tests examine the benefit of instances’ features transformation to be a vector of bag representation using mean and covariance mapping to Linear-SVM, Square-SVM and Cube-SVM. The experiments used a secondary dataset. The numerical dataset extracted breast histopathology image of 58 patients, which contains 708 features and 2002 instances. The result obtained shows that the proposed SVM can achieve 100% sensitivity after utilizing the covariance mapping with Square-SVM. It means the classification task able to detect the malignant class. In conclusion, the conventional SVM has great potential to improve medical diagnostic procedure using MI image, particularly for cancer diagnostic after adapting statistical features transformation.

     

     

     

  • Keywords


    multi-instance classification; bag-level decision; statistical mapping; medical images; disease diagnostic

  • References


      [1] Guthier B., Enjamin, Kopf S., and Effelsberg W. (2013), “Algorithms for a real-time HDR video system,” Pattern Recognit. Lett., vol. 34, no. 1, pp. 25–33.

      [2] Wang X. (2013), “Intelligent multi-camera video surveillance: A review,” Pattern Recognit. Lett., vol. 34, no. 1, pp. 3–19.

      [3] Xiang Z., Lv X., and Zhang K. (2014), “An Image Classification Method Based on Multi-feature Fusion and Multi-kernel SVM,” Seventh Int. Symp. Comput. Intell. Des., vol. 2, no. 1, pp. 49–52.

      [4] Battula B. P. and Prasad R. S. (2013), “An Overview of Recent Machine Learning Strategies in Data Mining,” Int. J. Adv. Comput. Sci. Appl., vol. 4, no. 3, pp. 50–54.

      [5] Chuah T. K., Van Reeth E., Sheah K., and Poh C. L. (2013.), “Texture Analysis of Bone Marrow in Knee MRI for Classification of Subjects with Bone Marrow Lesion - Data from The Osteoarthritis Initiative,” Magn. Reson. Imaging, vol. 31, no. 6, pp. 930–938.

      [6] Seidel M., Rasin A., Furst J. D., and Raicu D. S. (2014), “Towards Achieving Diagnostic Consensus in Medical Image Interpretation,” IEEE Int. Conf. Data Min. Work., pp. 771–780,.

      [7] Venkatesan R., Chandakkar P. S., and Li B. (2016), “Simpler Non-Parametric Methods Provide as Good or Better Results to Multiple-Instance Learning,” Proc. IEEE Int. Conf. Comput. Vis., vol. 11–18–Dece, pp. 2605–2613.

      [8] Mendez C. A., Menegaz G., and Summers P. (2014), “A Multi-View Approach To Consensus Clustering in Multi-modal MRI,” ICASSP, IEEE Int. Conf. Acoust. Speech Signal Process. - Proc., pp. 6627–6631.

      [9] Liu S., Cai W., Liu S., Pujol S., Kikinis R., and Feng D. (2015), “Subject-Centered Multi-View Feature Fusion For Neuroimaging Retrival and Classsification,” IEEE Int. Conf. Image Process., pp. 2505–2509.

      [10] Legg P. A., Rosin P. L., Marshall D., and Morgan J. E. (2015), “Feature Neighbourhood Mutual Information for Multi-modal Image Registration: AnApplication to Eye Fundus Imaging,” Pattern Recognit., vol. 48, no. 6, pp. 1937–1946.

      [11] Kandemir M., Feuchtinger A., Walch A., and. Hamprecht F. A (2014), “Digital Pathology: Multiple Instance Learning Can Detect Barrett’s Cancer,” 2014 IEEE 11th Int. Symp. Biomed. Imaging, pp. 1348–1351,.

      [12] Li W., Zhang J., and McKenna S. J. (2015), “Multiple Instance Cancer Detection by Boosting Regularised Trees,” Med. Image Comput. Comput. Interv. (MICCAI ), vol. 9349, pp. 589–596.

      [13] Ilse M., Tomczak J. M., and Welling M. (2018), “Attention-based Deep Multiple Instance Learning,”.

      [14] J. Wu, S. Pan, X. Zhu, C. Zhang, and X. Wu (2018), “Multi-instance learning with discriminative bag mapping,” IEEE Trans. Knowl. Data Eng., vol. 30, no. 6, pp. 1065–1080.

      [15] Yuan L., Zhao L., and Xu H. (2015), “Multi-instance learning via instance-based and bag-based representation transformations,” Proc. - Int. Conf. Image Process. ICIP, vol. 2015–Decem, pp. 2771–2775.

      [16] Amores J. (2013), “Multiple instance classification: Review, taxonomy and comparative study,” Artif. Intell., vol. 201, pp. 81–105.

      [17] Vu T. H., Mousavi H. S., Monga V., Rao G., and. Rao U. K. A (2016), “Histopathological Image Classification Using Learning Discriminative Feature-oriented Dictionary,” IEEE Trans. On Medical Imaging, vol. 35, no. 3, pp. 738–751.

      [18] Hiremath B. and Prasannakumar SC (2015), “Automated Evaluation of Breast Cancer Detection Using SVM Classifier,” Int. J. Comput. Sci. Eng. Inf. Technol. Res., vol. 5, no. 1, pp. 7–16.

      [19] Beheshti S. M. A., Ahmadi Noubari H., Fatemizadeh E., and Khalili M. (2014), “Classification of Abnormalities in Mammograms by New Asymmetric Fractal Features,” Biocybern. Biomed. Eng., vol. 36, no. 1, pp. 56–65.

      [20] Ghaddar B. and Naoum-Sawaya J. (2017), “High dimensional data classification and feature selection using support vector machines,” Eur. J. Oper. Res., vol. 265, pp. 993–1004.

      [21] Thai L. H., Hai T. S., and Thuy N. T. (2012), “Image Classification using Support Vector Machine and Artificial Neural Network,” International Journal of Information Technology and Computer Science vol. 4, no. 5, pp. 32–38.

      [22] Jothi J. A. A.and Rajam V. M. A. (2016), “A Survey on Automated Cancer Diagnosis from Histopathology Images,” Artif. Intell. Rev., pp. 1–51.

      [23] Anuranjeeta, Saxena S., Shukla K. K., and Sharma S. (2016), “Cellular Image Segmentation using Morphological Operators and Extraction of Features for Quantitative Measurement,” Biosci. Biotechnol. Res. Asia, vol. 13(2), no. June, pp. 1101–1112.

      [24] Wenqi L., Zhang J., and McKenna S. J. (2015), “Multiple Instance Cancer Detection by Boosting Regularised Trees,” Medical. Image Computing and Computer-Assisted Intervention. (MICCAI), vol. 9349, pp. 645–652.

      [25] Manivannan S., Cobb C., Burgess S., and Trucco E. (2016.), “Sub-category Classifiers for Multiple-instance Learning and Its Application to Retinal Nerve Fiber Layer Visibility Classification,” Int. Conf. Med. Image Comput

      [26] Li X. and Plataniotis K. N. (2015), “Color Model Comparative Analysis for Breast Cancer Diagnosis using H & E Stained Images,” Prog. Biomed. Opt. Imaging - Proc. SPIE.

      [27] Sikka K., Giri R., and Bartlett M. (2015), “Joint Clustering and Classification for Multiple Instance Learning,” Proc. Br. Mach. Vis. Conf. BMVA Press, pp. 1–12,.

      [28] Cheplygina V. and Tax D. M. J. (2015), “Characterizing Multiple Instance Datasets,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9370, pp. 15–27.

      [29] Xu Y., Mo T., Feng Q., Zhong P., Lai M., and Chang E. I.-C. (2014), “Deep Learning of Feature Representation with Multiple Instance Learning for Medical ImageAanalysis,” 2014 IEEE Int. Conf. Acoust. Speech Signal Process., no. 1, pp. 1626–1630.

      [30] Quellec G., Cazuguel G., Cochener B., and Lamard M. (2017), “Multiple-instance Learning for Medical Image and Video Analysis,” IEEE Rev. Biomed. Eng., vol. 3333, no. c, pp. 1–22,.

      [31] Kumar Y. and. Sahoo G (2012), “Analysis of Parametric & Non Parametric Classifiers for Classification Technique using WEKA,” I.J. Information Technology and Computer Science,. [Online]. Available: http://www.mecs-press.org/ijitcs/ijitcs-v4-n7/IJITCS-V4-N7-6.pdf. [Accessed: 07-Jan-2016].

      [32] Krawczyk B., Galar M., Jelen L., and Herrera F. (2016.), “Evolutionary Undersampling Boosting for Imbalanced Classification of Breast Cancer Malignancy,” Appl. Soft Comput. J., vol. 38, pp. 714–726.

      [33] Sudeb D., Manish C., and Kundu M. K. (2013), “Brain MR Image Classification Using Multi- Scale Geometric Analysis of Ripplet,” Prog. Electromagn. Res., vol. 137, no. February, pp. 1–17.

      [34] Liu S., Cai W., Pujol S., Kikinis R., and Feng D. (2016), “Cross-View Neuroimage Pattern Analysis in Alzheimer ’ s Disease Staging,” Front. Aging Neurosci., vol. 8, no. February, pp. 1–22,.

      [35] Cavazza J., Zunino A., Biagio M. S., and Murino V. (2017), “Kernelized Covariance for Action Recognition.” Proceedings - International Conference on Pattern Recognition.pp 408-413


 

View

Download

Article ID: 27757
 
DOI: 10.14419/ijet.v7i4.38.27757




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.