Skip to main content

Advertisement

SpringerLink
Log in

Texture-based features for classification of mammograms using decision tree

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Mammogram—breast X-ray—is considered the most effective, low cost, and reliable method in early detection of breast cancer. Although general rules for the differentiation between benign and malignant breast lesions exist, only 15–30 % of masses referred for surgical biopsy are actually malignant. In this work, an approach is proposed to develop a computer-aided classification system for cancer detection from digital mammograms. The proposed system consists of three major steps. The first step is region of interest (ROI) extraction of 256 × 256 pixels size. The second step is the feature extraction; we used a set of 19 GLCM and GLRLM features, and the 19 (nineteen) features extracted from gray-level run-length matrix and gray-level co-occurrence matrix could distinguish malignant masses from benign masses with an accuracy of 96.7 %. Further analysis was carried out by involving only 12 of the 19 features extracted, which consists of 5 features extracted from GLCM matrix and 7 features extracted from GLRL matrix. The 12 selected features are as follows: Energy, Inertia, Entropy, Maxprob, Inverse, SRE, LRE, GLN, RLN, LGRE, HGRE, and SRLGE; ARM with 12 features as prediction can distinguish malignant mass image and benign mass with a level of accuracy of 93.6 %. Further analysis showed that area under the receiver operating curve was 0.995, which means that the accuracy level of classification is good or very good. Based on that data, it was concluded that texture analysis based on GLCM and GLRLM could distinguish malignant image and benign image with considerably good result. The third step is the classification process; we used the technique of decision tree using image content to classify between normal and cancerous masses. The proposed system was shown to have the large potential for cancer detection from digital mammograms.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Majid AS, de Paredes ES, Doherty RD, Sharma N, Salvador X (2003) Missed breast carcinoma: pitfalls and pearls. Radiographics 23:881–895

    Article  Google Scholar 

  2. Osmar RZ, Antonie M-L, Coman A (2002) Mammography classification by association rulebased classifier. MDM/KDD2002 International workshop on multimedia data mining with (ACM SIGKDD 2002, Edmonton, Alberta, Canada, 17–19 July 2002), pp 62–69

  3. Xie X, Gong Y, Wan S, Li X (2005) Computer aided detection of SARS based on radiographs data mining. In: Proceedings of the 2005 IEEE engineering in medicine and biology 27th annual conference Shanghai, China, 1–4 Sept 2005

  4. Shuyan W, Mingquan Z, Guohua G (2005) Application of fuzzy cluster analysis for medical image data mining. In: Proceedings of the IEEE international conference on mechatronics & automation Niagara Falls, Canada, July 2005

  5. Jensen R, Qiang S (2004) Semantics preserving dimensionality reduction: rough and fuzzy-rough based approaches. IEEE Trans Knowl Data Eng 16:1457–1471

    Article  Google Scholar 

  6. Walid E, Hakim H (2006) A new cost sensitive decision tree method application for mammograms classification. IJCSNS Int J Comp Sci Netw Secur, 6 No. 11

  7. Liu Y, Zhang D, Lu G (2008) Region based image retrieval with high-level semantics using decision tree learning. Pattern Recognit 41:2554–2570

    Article  MATH  Google Scholar 

  8. Polat K, Günes S (2009) A novel hybrid intelligent method based on C4.5 decision tree classifier and one-against-all approach for multi-class classification problems. Expert Syst Appl 36:1587–1592

    Article  Google Scholar 

  9. Chen C, Lee G (1997) Image segmentation using multitiresolution wavelet analysis and expectation maximum (em) algorithm for mammography. Int J Imaging Syst Technol 8(5):491–504

    Article  Google Scholar 

  10. Wang T, Karayaiannis N (1998) Detection of microcalcifications in digital mammograms using wavelets. IEEE Trans Med Imaging 17(4):498–509

    Article  Google Scholar 

  11. Christiyanni I et al (2000) Fast detection of masses in computer aided mammography. IEEE Signal Process Mag 54–64

  12. Faderl S, Keating MJ, Do KA, Liang SY, Kantarjian HM, O’Brien S et al (2002) Expression profile of 11 proteins and their prognostic significance in patients with chronic lymphocytic leukemia (CLL). Leukemia 16:1045–1052

    Article  Google Scholar 

  13. Quinlan J (1993) C4.5: programs for machine learning. Morgan Kaufmann, San Francisco, CA

  14. http://www.rulequest.com/see5-info.html. http://marathon.csee.usf.edu/Mammography/Database.html

  15. Cherif chaabani A, Boujelben A, Mahfoudhi A, Abid M (2010) An automatic-pre-processing method for mammographic images. JDCTA Int J Digit Content Technol Appl 4(3):190–201

    Google Scholar 

  16. Hanmandlu M, Madasu VK, Vasikarla S (2004) A fuzzy Approach to texture segmentation. Proc Int Conf Inf Technol: Coding and Computing 1:636–642

    Google Scholar 

  17. Chalana V, Kim Y (1997) A methodology for evaluation of boundary algorithms on medical images. IEEE Trans Med Imaging 16(5):642–652

    Article  Google Scholar 

  18. Perkins WA (1980) Area segmentation of images using edge points. IEEE Trans Pattern Anal Mach Intell PAMI-2:8–15

    Article  Google Scholar 

  19. Torheim G, Godtliebsen F, Axelson D, Kvistad KA, Haraldseth O, Rinck PA (2001) Feature extraction and classification of dynamic contrast-enhanced T2*-weighted breast image data. IEEE Trans Med Imaging 20:1293–1301

    Article  Google Scholar 

  20. Sohail A, Bhattacharya P, Mudur SP, Krishnamurthy S (2011) Classification of ultrasound medical images using distance based feature selection and fuzzy-SVM. Pattern Recognit Image Anal, Lecture notes in computer science. 6669:176–183. doi:10.1007/978-3-642-21257-4_22

  21. Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3:610–621

    Article  Google Scholar 

  22. Gupta R, Undrill PE (1997) The use of texture analysis to identify suspicious masses in mammography. Phys Med Biol 15:835–855

    Google Scholar 

  23. Chan HP et al (1995) Computer-aided classification of mammographic masses and normal tissue: linear discriminant analysis in texture feature space. Phys Med Biol 40:857–876

    Article  Google Scholar 

  24. Wei D, Chan HP, Helvie MA, Sahiner B, Petrick N, Adler DD, Goodsitt MM (1995) Classification of mass and normal breast tissue on digital mammograms: multiresolution texture analysis. Med Phys 22:1501–1513

    Article  Google Scholar 

  25. Gibbs P, Turnbull LW (2003) Textural analysis of contrast-enhanced MR images of the breast. Magn Reson Med 50:92–98

    Article  Google Scholar 

  26. Mohanty AK, Senapati MR, Lenka SK (2012) A novel image mining technique for classification of mammograms using hybrid feature selection. Neural Comput Appl. doi:10.1007/s00521-012-0881-x

  27. Conners RW, Harlow CA (1980) A theoretical comparison texture algorithms. IEEE Trans Pattern Anal Mach Intell 2:204–222

    Article  MATH  Google Scholar 

  28. Arivazhagan S, Ganesan L (2003) Texture classification using wavelet transform. Pattern Recognit Lett 24:1513–1521

    Article  MATH  Google Scholar 

  29. Hiremath PS, Shivashankar S (2006) Texture classification using wavelet packet decomposition. ICGSTs GVIP J 6(2):77–80

    Google Scholar 

  30. Albregtsen F (1995) Statistical texture measures computed from gray level run-length matrices. University of Oslo

  31. Hall-Beyer M (2004) GLCM texture: a tutorial v.2.7.1, on-line document, www.fp.ucalgary.ca/mhallbey/tutorial.htm

  32. Haralick RM, Shanmugam K, Dinstein I (1973) Texture features for image classification. IEEE Trans SMC 3(6):610–621

    Google Scholar 

  33. Kulak E (2002) Image analysis of textural Features for Content based retrieval. Thesis, Sabanci University

  34. Tang X (1998) Texture information in run-length matrices. IEEE Trans Image Process 7(11):1602–1609

    Article  Google Scholar 

  35. Chu A, Sehgal CM (1990) Use of gray value distribution of run lengths for texture analysis. Pattern Recognit Lett 415–420

  36. Dasarathy BV, Holder EB (1991) Image characterizations based on joint gray level—run length distributions. Pattern Recognit Lett 12(8):497–502

    Article  Google Scholar 

  37. Nisbet R, Elder J, Miner G (2009) Handbook of statistical analysis and data mining applications. Academic Press, Burlington

    MATH  Google Scholar 

  38. Quinlan J (1986) Induction of decision trees. Machine Learning 1:81–106

    Google Scholar 

  39. Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Wadsworth & Brooks/Cole Advanced Books & Software, Monterey, CA

  40. Loh WY, Shih YS (1997) Split selection methods for classification trees. Stat Sin 7:815–840

    MathSciNet  MATH  Google Scholar 

  41. Michael JA, Gordon SL (1997) Data mining technique: for marketing, sales and customer support. Wiley, New York

    Google Scholar 

  42. Han JW, Kamber M (2006) Data mining concepts and techniques, 2nd edn. Morgan Kaufmann Publishers, San Francisco

    MATH  Google Scholar 

  43. Dudoit S, Fridlyand J, Speed TP (2000) Comparison of discrimination methods for the classification of tumors using gene expression data. Technical report 576, Department of Statistics, University of California at Berkeley, Berkeley, CA

  44. Quinlan JR (1996) Improved use of continuous attributes in C4.5. J Artif Intell Res 4:77–90

    MATH  Google Scholar 

  45. Murthy SK (1998) Automatic construction of decision trees from data: a multi-disciplinary survey. Data Min Knowl Disc 2(4):345–389

    Article  Google Scholar 

  46. Zou KH, O’Malley AJ, Mauri L (2007) Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models. J Am Heart Assoc 654–657. doi:10.1161/CIRCULATIONAHA.105.594929

  47. Park SH, Goo JM, Jo C-H (2004) Receiver operating characteristic (roc) curve: practical review for radiologists. Korean J Radiol 5(1):11–18

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. SOA University, Bhubaneswar, Odisha, India

    Aswini Kumar Mohanty

  2. Department of Computer Science, Krupajal Engineering College, Bhubaneswar, Odisha, India

    Manas Ranjan Senapati

  3. BPUT, Rourkela, Odisha, India

    Swapnasikta Beberta

  4. Department of Computer Science, Mody Univesity, Lakshmangarh, 332311, Rajasthan, India

    Saroj Kumar Lenka

Authors
  1. Aswini Kumar Mohanty
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Manas Ranjan Senapati
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Swapnasikta Beberta
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Saroj Kumar Lenka
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Aswini Kumar Mohanty.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Mohanty, A.K., Senapati, M.R., Beberta, S. et al. Texture-based features for classification of mammograms using decision tree. Neural Comput & Applic 23, 1011–1017 (2013). https://doi.org/10.1007/s00521-012-1025-z

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-012-1025-z

Keywords

Search

Navigation