Applied Intelligence

, Volume 49, Issue 3, pp 983–1001 | Cite as

A computer-aided diagnosis system using Tchebichef features and improved grey wolf optimized extreme learning machine

  • Figlu MohantyEmail author
  • Suvendu Rup
  • Bodhisattva Dash
  • Banshidhar Majhi
  • M. N. S. Swamy


Early detection is a key step for effective treatment of breast cancer and computer-aided diagnosis (CAD) is the most common tool used by the medical research community to detect early breast cancer development. Automated and accurate classification of mammogram images is an important criterion for the analysis and interpretation of these images and many methods have been proposed in this direction. In this paper, an improved CAD model is developed to classify the digital mammograms into normal and abnormal, and further, benign and malignant. The proposed model constitutes four different phases, namely, region of interest (ROI) generation, feature extraction, feature reduction, and classification. The proposed model first employs discrete Tchebichef transform (DTT) to extract the features from the ROIs. Subsequently, a technique based on a combination of principal component analysis (PCA) and linear discriminant analysis (LDA) is employed to reduce the dimensions of the feature vector. Next, the reduced features are sent to an extreme learning machine (ELM) for the classification. Here, to obtain a better generalization performance, the hidden node parameters of ELM are optimized through an improved grey wolf optimization-based ELM (IGWO-ELM). To validate the proposed CAD system, different performance metrics such as accuracy, sensitivity, specificity, and area under curve (AUC) are measured using k-fold stratified cross-validation (SCV). Moreover, to eliminate the issue of randomness, 10 independent runs are carried out on SCV. From a detailed analysis of the results, it is observed that the proposed model yields an average accuracy of 100% for MIAS dataset in both normal vs. abnormal, and benign vs. malignant cases. Further, the accuracy achieved for DDSM dataset is 99.50%, and 98.50% for normal vs. abnormal, and benign vs. malignant cases, respectively. The computation time taken by the proposed CAD model for MIAS and DDSM are 1.131 secs and 3.063 secs, respectively. The experimental analysis justifies the effectiveness of the proposed CAD model and as a result, this model can be considered as an effective tool to help the radiologists for better diagnosis.


Digital mammogram Computer-aided diagnosis Discrete Tchebichef transform Grey wolf optimization Extreme learning machine Area under curve 


Compliance with Ethical Standards

Conflict of interests

The authors declare no conflict of interest.


  1. 1.
    Society AC (2015) Cancer facts and figures 2015–2016Google Scholar
  2. 2.
    Society AC (2012) Cancer facts and figures 2012–2013Google Scholar
  3. 3.
    IA for Research on Cancer et al (2014) The globocan project: cancer incidence and mortality worldwide in 2012.
  4. 4.
    Society AC (2017) Cancer facts and figures 2017–2018Google Scholar
  5. 5.
    Smith RA, Cokkinides V, von Eschenbach AC, Levin B, Cohen C, Runowicz CD, Sener S, Saslow D, Eyre HJ (2002) American cancer society guidelines for the early detection of cancer. CA Cancer J Clin 52(1):8Google Scholar
  6. 6.
    Kolb TM, Lichy J, Newhouse JH (2002) Comparison of the performance of screening mammography, physical examination, and breast us and evaluation of factors that influence them: an analysis of 27,825 patient evaluations. Radiology 225(1):165Google Scholar
  7. 7.
    Cheng H, Shi X, Min R, Hu L, Cai X, Du H (2006) Approaches for automated detection and classification of masses in mammograms. Pattern Recogn 39(4):646Google Scholar
  8. 8.
    Prathibha B, Sadasivam V (2010) Multi-resolution texture analysis of mammograms using nearest neighbor classification techniques. Int J Inf Acquis 7(02):109Google Scholar
  9. 9.
    Eltoukhy MM, Faye I, Samir BB (2012) A statistical based feature extraction method for breast cancer diagnosis in digital mammogram using multiresolution representation. Comput Biol Med 42(1):123Google Scholar
  10. 10.
    Beura S, Majhi B, Dash R (2015) Mammogram classification using two dimensional discrete wavelet transform and gray-level co-occurrence matrix for detection of breast cancer. Neurocomputing 154:1Google Scholar
  11. 11.
    Zyout I, Czajkowska J, Grzegorzek M (2015) Multi-scale textural feature extraction and particle swarm optimization based model selection for false positive reduction in mammography. Comput Med Imaging Graph 46:95Google Scholar
  12. 12.
    de Lima SM, da Silva-Filho AG, dos Santos WP (2016) Detection and classification of masses in mammographic images in a multi-kernel approach. Comput Methods Programs Biomed 134:11Google Scholar
  13. 13.
    Zhou S, Shi J, Zhu J, Cai Y, Wang R (2013) Shearlet-based texture feature extraction for classification of breast tumor in ultrasound image. Biomed Signal Process Control 8(6):688Google Scholar
  14. 14.
    Gedik N (2016) A new feature extraction method based on multi-resolution representations of mammograms. Appl Soft Comput 44:128Google Scholar
  15. 15.
    Kanchana M, Varalakshmi P (2016) Computer aided system for breast cancer in digitized mammogram using shearlet band features with ls-svm classifier. Int J Wavelets Multiresolution Inf Process 14(03):1650017MathSciNetzbMATHGoogle Scholar
  16. 16.
    Jona J, Nagaveni N (2012) A hybrid swarm optimization approach for feature set reduction in digital mammograms. WSEAS Trans Inf Sci Appl 9:340Google Scholar
  17. 17.
    Mohamed H, Mabrouk MS, Sharawy A (2014) Computer aided detection system for micro calcifications in digital mammograms. Comput Methods Prog Biomed 116(3):226Google Scholar
  18. 18.
    Phadke AC, Rege PP (2016) Fusion of local and global features for classification of abnormality in mammograms. Sādhanā 41(4): 385MathSciNetzbMATHGoogle Scholar
  19. 19.
    Bajaj V, Pawar M, Meena VK, Kumar M, Sengur A, Guo Y (2017) Computer-aided diagnosis of breast cancer using bi-dimensional empirical mode decomposition. Neural Computing Applications pp 1–9.
  20. 20.
    Rouhi R, Jafari M, Kasaei S, Keshavarzian P (2015) Benign and malignant breast tumors classification based on region growing and cnn segmentation. Expert Syst Appl 42(3):990Google Scholar
  21. 21.
    Rouhi R, Jafari M (2016) Classification of benign and malignant breast tumors based on hybrid level set segmentation. Expert Syst Appl 46:45Google Scholar
  22. 22.
    Dheeba J, Singh NA, Selvi ST (2014) Computer-aided detection of breast cancer on mammograms: A swarm intelligence optimized wavelet neural network approach. J Biomed Inform 49:45Google Scholar
  23. 23.
    Dioçan L, Andreica A (2015) Multi-objective breast cancer classification by using multi-expression programming. Appl Intell 43(3):499Google Scholar
  24. 24.
    Khan S, Hussain M, Aboalsamh H, Mathkour H, Bebis G, Zakariah M (2016) Optimized gabor features for mass classification in mammography. Appl Soft Comput 44:267Google Scholar
  25. 25.
    Xie W, Li Y, Ma Y (2016) Breast mass classification in digital mammography based on extreme learning machine. Neurocomputing 173:930Google Scholar
  26. 26.
    Aminikhanghahi S, Shin S, Wang W, Jeon SI, Son SH, new fuzzy gaussian mixture model A (2017) (fgmm) based algorithm for mammography tumor image classification. Multimed Tools Appl 76(7):10191Google Scholar
  27. 27.
    Prathibha G, Chandra Mohan B (2017) Classification of benign and malignant masses using bandelet and orthogonal ripplet type ii transforms. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization pp 1–14.
  28. 28.
    Jiao Z, Gao X, Wang Y, Li J (2018) A parasitic metric learning net for breast mass classification based on mammography. Pattern Recogn 75:292Google Scholar
  29. 29.
    Dhahbi S, Barhoumi W, Kurek J, Swiderski B, Kruk M, Zagrouba E (2018) False-positive reduction in computer-aided mass detection using mammographic texture analysis and classification. Comput Methods Prog Biomed 160:75Google Scholar
  30. 30.
    Thawkar S, Ingolikar R (2018) Classification of masses in digital mammograms using firefly based optimization. Int J Image Graphics and Signal Process 10(2):25Google Scholar
  31. 31.
    Rampun A, Scotney BW, Morrow PJ, Wang H, Winder J (2018) Breast density classification using local quinary patterns with various neighbourhood topologies. J Imaging 4(1):14Google Scholar
  32. 32.
    Berraho S, El Margae S, Kerroum MA, Fakhri Y (2017) Texture classification based on curvelet transform and extreme learning machine with reduced feature set. Multimed Tools Appl 76(18):18425Google Scholar
  33. 33.
    Bharathi VS, Ganesan L (2008) Orthogonal moments based texture analysis of CT liver images. Pattern Recogn Lett 29(13):1868Google Scholar
  34. 34.
    Teh CH, Chin RT (1988) On image analysis by the methods of moments. IEEE Trans Pattern Anal Mach Intell 10(4): 496zbMATHGoogle Scholar
  35. 35.
    Mukundan R, Ong S, Lee PA (2001) Image analysis by Tchebichef moments. IEEE Trans Image Process 10(9):1357MathSciNetzbMATHGoogle Scholar
  36. 36.
    Yap PT, Paramesran R, Ong SH (2003) Image analysis by Krawtchouk moments. IEEE Trans Image Process 12(11):1367MathSciNetGoogle Scholar
  37. 37.
    Wee CY, Paramesran R, Mukundan R, Jiang X (2010) Image quality assessment by discrete orthogonal moments. Pattern Recogn 43(12):4055zbMATHGoogle Scholar
  38. 38.
    Marcos JV, Cristóbal G (2013) Texture classification using discrete Tchebichef moments. JOSA A 30 (8):1580Google Scholar
  39. 39.
    Yang J, Yang JY (2003) Why can LDA be performed in PCA transformed space?. Pattern Recogn 36 (2):563Google Scholar
  40. 40.
    Martínez AM, Kak AC (2001) PCA versus LDA. IEEE Trans Pattern Anal Mach Intell 23(2):228Google Scholar
  41. 41.
    Shlens J (2014) A tutorial on principal component analysis. arXiv:1404.1100
  42. 42.
    Ye J, Janardan R, Li Q (2005) In: Advances in neural information processing systems, pp 1569–1576Google Scholar
  43. 43.
    Mirjalili S, Mirjalili SM, Lewis A (2014) Grey wolf optimizer. Adv Eng Softw 69:46Google Scholar
  44. 44.
    Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489Google Scholar
  45. 45.
    Ortega JM (1987) Matrix theory. The University Series in MathematicsGoogle Scholar
  46. 46.
    Huang GB (2003) Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Trans Neural Netw 14(2):274Google Scholar
  47. 47.
    Huang GB, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2(2):107Google Scholar
  48. 48.
    Huang GB, Zhu QY, Siew CK (2004) . In: Proceedings of the 2004 IEEE international joint conference on neural networks, (IEEE, 2004), vol 2, pp 985–990Google Scholar
  49. 49.
    Zhao G, Shen Z, Miao C, Man Z (2009) In: 7th international conference on information, communications and signal processing, 2009. ICICS 2009. (IEEE, 2009), pp 1–5Google Scholar
  50. 50.
    Zhu QY, Qin AK, Suganthan PN, Huang GB (2005) Evolutionary extreme learning machine. Pattern Recogn 38(10):1759zbMATHGoogle Scholar
  51. 51.
    Xu Y, Shu Y (2006) Evolutionary extreme learning machine–based on particle swarm optimization. Adv Neural Networks-ISNN 2006:644–652Google Scholar
  52. 52.
    Han F, Yao HF, Ling QH (2013) An improved evolutionary extreme learning machine based on particle swarm optimization. Neurocomputing 116:87Google Scholar
  53. 53.
    Suckling J, Parker J, Dance D, Astley S, Hutt I, Boggis C, Ricketts I, Stamatakis E, Cerneaz N, Kok S et al (1994) In: Exerpta Medica, vol 1069. International Congress Series, pp 375– 378Google Scholar
  54. 54.
    Heath M, Bowyer K, Kopans D, Moore R, Kegelmeyer WP (2000) In: Proceedings of the 5th international workshop on digital mammography (Medical Physics Publishing), pp 212–218Google Scholar
  55. 55.
    Mohanty F, Rup S, Dash B, Majhi B, Swamy MNS (2018) Mammogram classification using contourlet features with forest optimization-based feature selection approach. Multimedia Tools and Applications, pp 1–30.
  56. 56.
    Do Nascimento MZ, Martins AS, Neves LA, Ramos RP, Flores EL, Carrijo GA (2013) Classification of masses in mammographic image using wavelet domain features and polynomial classifier. Expert Syst Appl 40 (15):6213Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Figlu Mohanty
    • 1
    Email author
  • Suvendu Rup
    • 1
  • Bodhisattva Dash
    • 1
  • Banshidhar Majhi
    • 2
  • M. N. S. Swamy
    • 3
  1. 1.Image and Video Processing Laboratory, Department of Computer Science and EngineeringInternational Institute of Information TechnologyBhubaneswarIndia
  2. 2.Pattern Recognition Research Laboratory, Department of Computer Science and EngineeringNational Institute of TechnologyRourkelaIndia
  3. 3.Life Member, IEEE - Department of Electrical and Computer EngineeringConcordia UniversityMontrealCanada

Personalised recommendations