Advertisement

Automatic segmentation of sub-acute ischemic stroke lesion by using DTCWT and DBN with parameter fine tuning

  • Sunil Babu MelingiEmail author
  • V. Vijayalakshmi
Research Paper
  • 3 Downloads

Abstract

In image processing the ischemic stroke lesion segmentation is a major procedure used to extricate suspicious regions from the given MRI brain image. For classification and segmentation of MRI in this paper, we proposed a three-step framework. To remove noise the initial step utilizes a de-noising technique based on dual tree complex wavelet transform (DTCWT) test without affective the essential image features and content. In the second step, an un-supervised deep belief network (DBN) is intended for learning the unlabelled features. Here, the noise in MRI can cause a significant corruption of data that impedes the execution of DBNs. The DTCWT in the initial step enhances execution of DBNs. Additionally, we manage the issue of DBNs parameters fine-tuning by means of a quick meta-heuristic approach named salp swarm algorithm. Based on the simulation behaviour of salps this new meta-heuristic algorithm is planned to solve optimisation issues. It is validated against different benchmark test functions and afterward contrasted with well known state-of-the-art optimisation algorithms like genetic algorithm, particle swarm optimisation, bat algorithm, artificial bee colony algorithm and cuckoo search algorithm for performance efficiency.

Keywords

Dual tree complex wavelet transforms deep belief network Salp swarm algorithm Parameter fine-tuning Stroke lesion Segmentation Classification 

Notes

References

  1. 1.
    Wang Y, Katsaggelos A, Wang X, Parrish T (2016) A deep symmetry convnet for stroke lesion segmentation. In: 2016 IEEE international conference on image processing (ICIP), Phoenix, AZ, USA.  https://doi.org/10.1109/icip.2016.7532329
  2. 2.
    Donnan G, Baron J, Ma H, Davis S (2009) Penumbral selection of patients for trials of acute stroke therapy. Lancet Neurol 8:261–269.  https://doi.org/10.1016/s1474-4422(09)70041-9 CrossRefGoogle Scholar
  3. 3.
    Hema Rajini N, Bhavani R (2013) Computer aided detection of ischemic stroke using segmentation and texture features. Measurement 46:1865–1874.  https://doi.org/10.1016/j.measurement.2013.01.010 CrossRefGoogle Scholar
  4. 4.
    Rost NS, Sadaghiani S, Biffi A, Fitzpatrick KM, Cloonan L, Rosand J, Shibata DK, Mosley TH Jr (2014) Setting a gold standard for quantification of leukoaraiosis burden in patients with ischemic stroke: the Atherosclerosis Risk in Communities Study. J Neurosci Methods 221:196–201.  https://doi.org/10.1016/j.jneumeth.2013.10.009 CrossRefGoogle Scholar
  5. 5.
    Nabizadeh N, John N, Wright C (2014) Histogram-based gravitational optimization algorithm on single MR modality for automatic brain lesion detection and segmentation. Expert Syst Appl 41:7820–7836.  https://doi.org/10.1016/j.eswa.2014.06.043 CrossRefGoogle Scholar
  6. 6.
    Maier O, Wilms M, von der Gablentz J, Krämer UM, Münte TF, Handels H (2015) Extra Tree forests for sub-acute ischemic stroke lesion segmentation in MR sequences. J Neurosci Methods 240:89–100.  https://doi.org/10.1016/j.jneumeth.2014.11.011 CrossRefGoogle Scholar
  7. 7.
    Artzi M, Aizenstein O, Jonas-Kimchi T, Myers V, Hallevi H, Bashat DB (2013) FLAIR lesion segmentation: application in patients with brain tumors and acute ischemic stroke. Eur J Radiol 82:1512–1518.  https://doi.org/10.1016/j.ejrad.2013.05.029 CrossRefGoogle Scholar
  8. 8.
    Benders MJ, van der Aa NE, Roks M, van Straaten HL, Isgum I, Viergever MA, Groenendaal F, de Vries LS, van Bel F (2014) Feasibility and safety of erythropoietin for neuroprotection after perinatal arterial ischemic stroke. J Pediatr 164:481–486.e2.  https://doi.org/10.1016/j.jpeds.2013.10.084 CrossRefGoogle Scholar
  9. 9.
    Ghosh N, Sun Y, Bhanu B, Ashwal S, Obenaus A (2014) Automated detection of brain abnormalities in neonatal hypoxia ischemic injury from MR images. Med Image Anal 18:1059–1069.  https://doi.org/10.1016/j.media.2014.05.002 CrossRefGoogle Scholar
  10. 10.
    Patel A, van Ginneken B, Meijer FJ, van Dijk EJ, Prokop M, Manniesing R (2017) Robust cranial cavity segmentation in CT and CT perfusion images of trauma and suspected stroke patients. Med Image Anal 36:216–228.  https://doi.org/10.1016/j.media.2016.12.002 CrossRefGoogle Scholar
  11. 11.
    Griffis J, Allendorfer J, Szaflarski J (2016) Voxel-based Gaussian naïve Bayes classification of ischemic stroke lesions in individual T1-weighted MRI scans. J Neurosci Methods 257:97–108.  https://doi.org/10.1016/j.jneumeth.2015.09.019 CrossRefGoogle Scholar
  12. 12.
    Yassi N, Campbell BC, Moffat BA, Steward C, Churilov L, Parsons MW, Desmond PM, Davis SM, Bivard A (2015) Know your tools—concordance of different methods for measuring brain volume change after ischemic stroke. Neuroradiology 57:685–695.  https://doi.org/10.1007/s00234-015-1522-8 CrossRefGoogle Scholar
  13. 13.
    Menze BH, Van Leemput K, Lashkari D, Riklin-Raviv T, Geremia E, Alberts E, Gruber P, Wegener S, Weber MA, Székely G, Ayache N (2016) A generative probabilistic model and discriminative extensions for brain lesion segmentation—with application to tumor and stroke. IEEE Trans Med Imaging 35:933–946.  https://doi.org/10.1109/tmi.2015.2502596 CrossRefGoogle Scholar
  14. 14.
    Murphy K, van der Aa NE, Negro S, Groenendaal F, de Vries LS, Viergever MA, Boylan GB, Benders MJ, Išgum I (2017) Automatic quantification of ischemic injury on diffusion-weighted MRI of neonatal hypoxic ischemic encephalopathy. NeuroImage Clin 14:222–232.  https://doi.org/10.1016/j.nicl.2017.01.005 CrossRefGoogle Scholar
  15. 15.
    Mirtskhulava L, Wong J, Al-Majeed S, Pearce G (2015) Artificial neural network model in stroke diagnosis. In: 2015 17th UKSim-AMSS international conference on modelling and simulation (UKSim).  https://doi.org/10.1109/uksim.2015.33
  16. 16.
    Ibrahim I, Khatib T (2017) A novel hybrid model for hourly global solar radiation prediction using random forests technique and firefly algorithm. Energy Convers Manag 138:413–425.  https://doi.org/10.1016/j.enconman.2017.02.006 CrossRefGoogle Scholar
  17. 17.
    Karthik R, Menaka R (2017) A multi-scale approach for detection of ischemic stroke from brain MR images using discrete curvelet transformation. Measurement 100:223–232.  https://doi.org/10.1016/j.measurement.2017.01.001 CrossRefGoogle Scholar
  18. 18.
    Guerrero R, Qin C, Oktay O, Bowles C, Chen L, Joules R, Wolz R, Valdés-Hernández MC, Dickie DA, Wardlaw J, Rueckert D (2018) White matter hyperintensity and stroke lesion segmentation and differentiation using convolutional neural networks. NeuroImage Clin 17:918–934.  https://doi.org/10.1016/j.nicl.2017.12.022 CrossRefGoogle Scholar
  19. 19.
    Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y, Pal C, Jodoin PM, Larochelle H (2017) Brain tumor segmentation with deep neural networks. Med Image Anal 35:18–31.  https://doi.org/10.1016/j.media.2016.05.004 CrossRefGoogle Scholar
  20. 20.
    Chen L, Bentley P, Rueckert D (2017) Fully automatic acute ischemic lesion segmentation in DWI using convolutional neural networks. NeuroImage Clin 15:633–643.  https://doi.org/10.1016/j.nicl.2017.06.016 CrossRefGoogle Scholar
  21. 21.
    Hussain S, Anwar S, Majid M (2018) Segmentation of glioma tumors in brain using deep convolutional neural network. Neurocomputing 282:248–261.  https://doi.org/10.1016/j.neucom.2017.12.032 CrossRefGoogle Scholar
  22. 22.
    Sivakumar P, Ganeshkumar P (2017) An efficient automated methodology for detecting and segmenting the ischemic stroke in brain MRI images. Int J Imaging Syst Technol 27:265–272.  https://doi.org/10.1002/ima.22231 CrossRefGoogle Scholar
  23. 23.
    Davis A, Gordillo N, Montseny E, Aymerich FX, López-Córdova M, Mej’ia J, Ortega L, Mederos B (2018) Automated detection of parenchymal changes of ischemic stroke in non-contrast computer tomography: a fuzzy approach. Biomed Signal Process Control 45:117–127.  https://doi.org/10.1016/j.bspc.2018.05.037 CrossRefGoogle Scholar
  24. 24.
    Praveen G, Agrawal A, Sundaram P, Sardesai S (2018) Ischemic stroke lesion segmentation using stacked sparse autoencoder. Comput Biol Med 99:38–52.  https://doi.org/10.1016/j.compbiomed.2018.05.027 CrossRefGoogle Scholar
  25. 25.
    Selesnick I, Baraniuk R, Kingsbury N (2005) The dual-tree complex wavelet transform. IEEE Signal Process Mag 22:123–151.  https://doi.org/10.1109/msp.2005.1550194 CrossRefGoogle Scholar
  26. 26.
    Hinton G, Osindero S, Teh Y (2006) A fast learning algorithm for deep belief nets. Neural Comput 18:1527–1554.  https://doi.org/10.1162/neco.2006.18.7.1527 MathSciNetCrossRefzbMATHGoogle Scholar
  27. 27.
    Mirjalili S, Gandomi AH, Mirjalili SZ, Saremi S, Faris H, Mirjalili SM (2017) Salp swarm algorithm: a bio-inspired optimizer for engineering design problems. Adv Eng Softw 114:163–191.  https://doi.org/10.1016/j.advengsoft.2017.07.002 CrossRefGoogle Scholar
  28. 28.
    Zhang W, Li R, Deng H, Wang L, Lin W, Ji S, Shen D (2015) Deep convolutional neural networks for multi-modality isointense infant brain image segmentation. NeuroImage 108:214–224.  https://doi.org/10.1016/j.neuroimage.2014.12.061 CrossRefGoogle Scholar
  29. 29.
    Akkus Z, Galimzianova A, Hoogi A, Rubin DL, Erickson BJ (2017) Deep learning for brain MRI segmentation: state of the art and future directions. J Digit Imaging 30(4):449–459.  https://doi.org/10.1007/s10278-017-9983-4 CrossRefGoogle Scholar
  30. 30.
    Havaei M, Guizard N, Larochelle H, Jodoin PM (2016) Deep learning trends for focal brain pathology segmentation in MRI. In: Holzinger A (ed) Machine learning for health informatics, vol 9605. Lecture notes in computer science book series (LNCS). Springer, Berlin, pp 125–148CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Department of Electronics and Communication EngineeringPondicherry Engineering CollegePillaichavadiIndia

Personalised recommendations