Advertisement

Diagnosis of Schizophrenia Disorder Using Wasserstein Based Active Contour and Texture Features

  • M. Latha
  • G. Kavitha
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 490)

Abstract

Magnetic resonance (MR) brain images have a significant role in diagnosis of many neuropsychiatric disorders such as Schizophrenia (SZ). In this work, Wasserstein-based active contour and the texture features such as Hu moments and gray-level co-occurrence matrix (GLCM) are used to analyze Schizophrenic MR brain images. The images (N = 40) used for the analysis are obtained from National Alliance for Medical Image Computing (NAMIC) database. Initially, the normal and schizophrenic images are subjected to skull stripping using Wasserstein-based active contour method. The extracted brain from skull-stripping process is compared with Brain Extraction Tool (BET) and Brain Surface Extractor (BSE) methods. Seven features from Hu moment and twenty-two features from GLCM are extricated from the skull-stripped images. Further, these extracted features are analyzed to obtain discriminative information from normal and abnormal images. The result shows that the Wasserstein-based active contour method is able to separate the brain with an accuracy of 0.978, sensitivity of 0.934, and F-score of 0.958. The features extracted from Hu moments for abnormal images show higher magnitude value than normal images. Hu moments show significant percentage variation between normal and SZ subjects. Hu features such as ϕ3, ϕ4, and ϕ5 yield higher variation of 26.3%, 21.4%, and 20.1%, respectively, between normal abnormal images. In GLCM-based features, the features such as sum of squares, autocorrelation, and maximal correlation coefficient show better variation of 19.2%, 18.4%, and 15.6% between normal and abnormal images. Hu moments show better percentage variance in normal and abnormal images compared to GLCM features. Hence, the combination of Wasserstein-based active contour and Hu moments could be used for better demarcation of normal and Schizophrenia subjects.

Keywords

Schizophrenia Wasserstein-based active contour Texture feature GLCM Hu moments Magnetic resonance images 

References

  1. 1.
    Pawan KS, Sarkar R (2015) A simple and effective expert system for schizophrenia detection. Int J Intell Syst Technol Appl 14(1):27–49Google Scholar
  2. 2.
    Del Re EC, Konishi J, Bouix S, Blokland GA (2015) Enlarged lateral ventricles inversely correlate with reduced corpus callosum central volume in first episode Schizophrenia: association with functional measures. Brain Imaging Behav.  https://doi.org/10.1007/s11682-015-9493-2.j
  3. 3.
    Andre GRB, Traina AJM, Ribeiro MX, Paulo MAM, Balan CT (2012) Smart histogram analysis applied to the skull-stripping problem in T1-weighted MRI. Comput Biol Med 42(5):509–522CrossRefGoogle Scholar
  4. 4.
    Liu Y, Teverovskiy L, Carmichael O, Kikinis R, Shenton M, Carter CS, Davis Stenger VA, Davis S, Aizenstein H, Becker JT, Lopez OL, Meltzer CC (2004) Discriminative MR image feature analysis for automatic Schizophrenia and Alzheimer’s disease classification. Medical Image Computing and Computer-Assisted Intervention—MICCAI 2004 (Lecture Notes in Computer Science), vol 3216, pp 393–401Google Scholar
  5. 5.
    Dluhos P, Schwarz D, Kasparek T (2014) Wavelet features for recognition of first episode of Schizophrenia from MRI brain images. Radioengineering 23(1):274–281Google Scholar
  6. 6.
    Goulda IC, Shepherda AM, Laurensa KR, Cairns MJ, Carra VJ, Greena MJ (2014) Multivariate neuroanatomical classification of cognitive subtypes in Schizophrenia: a support vector machine learning approach. NeuroImage Clin 6:229–236CrossRefGoogle Scholar
  7. 7.
    Somasundaram K, Kalavathi P (2011) Skull stripping of MRI head scans based on chan-vese active contour model. Int J Knowl Manag e-Learn 3(1):7–14Google Scholar
  8. 8.
    Kalavathi P, Prasath VB (2016) Methods on skull stripping of MRI head scan images—a review. J Digit Imaging 29(3):65–79CrossRefGoogle Scholar
  9. 9.
    Smith SM (2002) Fast robust automated brain extraction. Hum Brain Mapp 17:143–155CrossRefGoogle Scholar
  10. 10.
    Shattuck DW, Sandor-leahy SR, Schaper KA, Rottenberg DA, Leahy RM (2001) Magnetic resonance image tissue classification using a partial volume model. NeuroImage 13:856–876CrossRefGoogle Scholar
  11. 11.
    Jiang S, Zhang W, Wang Y, Chen Z (2013) Brain extraction from cerebral MRI volume using a hybrid level set based active contour neighborhood model. Biomed Eng Online 12(31):1–18Google Scholar
  12. 12.
    Zhang H, Liu J, Zhu Z, Haiyun L (2011) An automated and simple method for brain MR image extraction. BioMed Eng Online.  https://doi.org/10.1186/1475-925X-10-81Google Scholar
  13. 13.
    Roura E, Oliver A, Cabezas M, Vilanova JC, Rovira À, Ramio-Torrenta L, Llado X (2014) MARGA: multispectral adaptive region growing algorithm for brain extraction on axial MRI. Comput Methods Programs Biomed 113:655–673CrossRefGoogle Scholar
  14. 14.
    Kangyu N, Bresson X, Chan T, Esedoglu S (2009) Local histogram based segmentation using the Wasserstein Distance. Int J Comput Vis 84:97–111CrossRefGoogle Scholar
  15. 15.
    Zhang Y, Jianfei Y, Shuihua W, Zhengchao D, Preetha P (2015) Pathological brain detection in MRI scanning via Hu moment invariants and machine learning. J Exp Theor Artif Intell.  https://doi.org/10.1080/0952813X.2015.1132274Google Scholar
  16. 16.
    Pattanachai N, Covavisaruch N, Sinthanayothin C (2014) Tooth recognition in dental radiographs via Hu’s moment invariants. In: IEEE international conference on mechatronics and automation, pp 1581–1586Google Scholar
  17. 17.
    Sun Y, Wen G, Wang J (2015) Weighted spectral features based on local Hu moments for speech emotion recognition. Biomed Signal Process Control Biomed Signal Process Control 18:80–90CrossRefGoogle Scholar
  18. 18.
    Zhang HF, Zhang X (2011) Shape recognition using a moment algorithm. In: International conference on multimedia technology, pp 3226–3229Google Scholar
  19. 19.
    Beura S, Majh B, Ratnakar D (2015) Mammogram classification using two dimensional discrete wavelet transform and gray-level co-occurrence matrix for detection of breast cancer. Neurocomputing 154:1–14CrossRefGoogle Scholar
  20. 20.
    Mariarputham EJ, Stephen A (2015) Nominated texture based cervical cancer classification. Comput Math Methods Med 586928:1–10CrossRefzbMATHGoogle Scholar
  21. 21.
    Shin YG, Yoo J, Kwon HJ, Hong JH, Lee HS, Yoon JH, Kim EK, Moon HJ, Han K, Kwak JY (2016) Histogram and gray level co-occurrence matrix on gray-scale ultrasound images for diagnosing lymphocytic thyroiditis. Comput Biol Med 75:257–266CrossRefGoogle Scholar
  22. 22.
    Xian G (2010) An identification method of malignant and benign liver tumors from ultrasonography based on GLCM texture features and fuzzy SVM. Expert Syst Appl 37:6737–6741CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Department of Electronics EngineeringMIT Campus, Anna UniversityChennaiIndia

Personalised recommendations