Feature Ranking of Spatial Domain Features for Efficient Characterization of Stroke Lesions

  • Anish Mukherjee
  • Abhishek Kanaujia
  • R. Karthik
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 490)


Development of automatic framework for efficient characterization of brain lesions is a significant research concern due to the complex properties exhibited by the brain tissues. This study focuses on observing the properties of such composite structures in order to identify optimal features for characterizing the properties of normal and abnormal brain tissues. This work initially applies Fuzzy C Mean algorithm to identify the region of interest. After segmentation, four different types of features are extracted from the region of interest. These features include first-order parameters, Gray-level Co-occurrence Matrix (GLCM) parameters, Laws texture features, and Gray-Level Run-Length Matrix (GLRLM) parameters. These identification features were ranked in order of pertinence with the help of Mutual Information and Statistical Dependence-based feature ranking algorithms. Based on the inference obtained from the Mutual Information and Statistical Dependence-based feature ranking algorithms, twelve best features are selected for characterizing the properties of the normal and abnormal brain tissues.


Lesion Feature ranking Mutual information Statistical dependence 


  1. 1.
    Thom T, Haase N, Rosamond W, Howard VJ, Rumsfeld J, Manolio T (2006) Heart disease and stroke statistics—2006 update: are port from the American Heart Association Statistics Committee and Stroke Statistics Subcommittee. Circulation 113:e85–e151CrossRefGoogle Scholar
  2. 2.
    Adams H, Adams R, Del Zoppo G, Goldstein LB (2005) Guidelines for the early management of patients with ischemic stroke, 2005 guidelines update, a scientific statement from the Stroke Council of the American Heart Association/American Stroke Association. Stroke 36:916–921Google Scholar
  3. 3.
    Lee Y, Takahashi N, Tsai DY, Fujita H (2006) Detectability improvement of early sign of acute stroke on brain CT images using an adaptive partial smoothing filter. Proc Soc Photo Opt Instrum Eng Med Imaging 6144:2138–2145Google Scholar
  4. 4.
    Karthik R, Menaka R (2016) Statistical characterization of ischemic stroke lesion from MRI using discrete wavelet transformations. ECTI Trans Electr Eng Electron Commun 14(2):57–64Google Scholar
  5. 5.
    Karthik R, Menaka R (2016) A critical appraisal on wavelet based features from brain MR images for characterization if ischemic stroke injuries. Electron Lett Comput Vis Image Anal 15(3):1–6Google Scholar
  6. 6.
    Przelaskowski A, Sklinda KP, Bargie PJ, Walecki J, Biesiadko-Matus-zewska M, Kazubek M (2007) Improved early stroke detection: wavelet-based perception enhancement of computerized tomography exams. Comput Biol Med 37:524–533Google Scholar
  7. 7.
    Chawla M, Sharma S, Sivaswamy J, Kishore LT (2009) A method for automatic detection and classification of stroke from brain CT images. In: EMBC 2009, Annual International Conference of the IEEE, 2009, pp 3581–3584Google Scholar
  8. 8.
    Usinskas A, Dobrovolskis RA, Tomandl BF (2004) Ischemic stroke segmentation on CT images using joint features. Informatica 15(2):283–290Google Scholar
  9. 9.
    Maldjian JA, Chalela J (2001) Automated CT segmentation and analysis for acute middle cerebral artery stroke. Am J Neuroradiol 22(6):1050–1055Google Scholar
  10. 10.
    Fauzi MFA, Komiya R, Haw S-C (2008) Unsupervised abnormalities extraction and brain segmentation. In: International conference on intelligent system and knowledge engineering, vol 1, pp 1185–1190Google Scholar
  11. 11.
    Tang F, Ng DKS, Chow DHK (2011) An image feature approach for computer-aided detection of ischemic stroke. Comput Biol Med 41:529–536Google Scholar
  12. 12.
    Benaichouche AN, Oulhadj H, Siarry P (2013) Improved spatial fuzzy c-means clustering for image segmentation using PSO initialization, Mahalanobis distance and post-segmentation correction. Digital Signal Process 23:1390–1400Google Scholar
  13. 13.
    Schilling C (2012) Analysis of atrial electrograms, vol 17. KIT Scientific PublishingGoogle Scholar
  14. 14.
    Haralick RM (1979) Statistical and structural approaches to texture. Proc IEEE 67(5):786–804CrossRefGoogle Scholar
  15. 15.
    Chu A, Sehgal CM, Greenleaf JF (1990) Use of gray value distribution of run lengths for texture analysis. Pattern Recognit Lett 11:415–420Google Scholar
  16. 16.
    Dasarathyand BR, Holder EB (1991) Image characterizations based on joint gray-level run-length distributions. Patt Recogn Lett 12:497–502CrossRefGoogle Scholar
  17. 17.
    He D-C, Wang L (1990) Texture unit, texture spectrum, and texture analysis. Trans Geosci Remote Sens IEEE 28(4):509–512CrossRefGoogle Scholar
  18. 18.
    Galloway MM (1975) Texture analysis using gray level run lengths. Comput Graph Image Process 4:172–179CrossRefGoogle Scholar
  19. 19.
    Liua Y, Zhanga D, Lua G, Mab W-Y (2007) A survey of content-based image retrieval with high-level semantics. Patt Recogn 40:262–282CrossRefGoogle Scholar
  20. 20.
    Laws KI (1979) Texture energy measures. In: Proceedings of the image understanding workshop, pp 47–51, Nov 1979Google Scholar
  21. 21.
    Pohjalainen J (2013) Feature selection methods and their combinations in high dimensional classification of speaker likability, intelligibility and personality traits. Comput Speech LangGoogle Scholar
  22. 22.
    Karp RM (1972) Reducibility among combinatorial problems. Complex Comput Comput 85–103Google Scholar
  23. 23.
    Li S, Harner J, Adjeroh D (2011) Random kNN feature selection—a fast and stable alternative to random forests. BMC Bioinf 12Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Anish Mukherjee
    • 1
  • Abhishek Kanaujia
    • 1
  • R. Karthik
    • 1
  1. 1.School of Electronics EngineeringVIT UniversityChennaiIndia

Personalised recommendations