Multimedia Tools and Applications

, Volume 78, Issue 2, pp 2481–2506 | Cite as

A review on acute/sub-acute ischemic stroke lesion segmentation and registration challenges

  • M. Sunil BabuEmail author
  • V. Vijayalakshmi


The segmentation of lesion tissue in brain images of stroke patients serves to distinguish the degree of the affected tissues, to perform anticipation on its recovery, and to quantify its development in longitudinal reviews. Manual depiction, the present standard, is tedious and experiences high intra-and inter-observer differences. Because of limited scholastic investigations of ischemic stroke identification, the achievement rate to distinguish stroke is low utilizing just CT image. Combination of CT and MRI images makes a composite image which gives more data than any of the information signals. Image segmentation is accomplished by a Random forest (RF) classifier connected on an arrangement of image elements extricated from each voxel and its neighborhood. An underlying arrangement of marked voxels is required to begin the procedure, preparing an underlying RF. The most unverifiable unlabeled voxels are appeared to the human administrator to choose some of them for incorporation in the preparation set, retraining the RF classifier. These strategies give very accurate segmented tumor output with very low error rate and very high accuracy.


Random forest Arterial vessel spin labeling Cerebral micro bleeds Magnetic resonance imaging Markov random field Computed tomography angiography 



  1. 1.
    Bhanu Prakash KN, Gupta V, Jianbo H, Nowinski WL (2008) Automatic processing of diffusion-weighted ischemic stroke images based on divergence measures: slice and hemisphere identification, and stroke region segmentation. Int J Comput Assist Radiol Surg 3(6):559–570CrossRefGoogle Scholar
  2. 2.
    Bienkowski P, Zatorski P, Baranowska A, Ryglewicz D, Sienkiewicz-Jarosz H (2010) Insular lesions and smoking cessation after first-ever ischemic stroke: a 3-month follow-up. Neurosci Lett 478(3):161–164CrossRefGoogle Scholar
  3. 3.
    Cai SS, von Coelln R, Kouo TJ (2016) Migratory stroke-like lesions in a case of adult-onset mitochondrial encephalomyopathy, lactic acidosis, and stroke-like episodes (MELAS) syndrome and a review of imaging findings. Radiology Case ReportsGoogle Scholar
  4. 4.
    Cheng Chung Wan G, Shih H-C, Shyu BC, Huang ACW (2016) Effects of thalamic hemorrhagic lesions on explicit and implicit learning during the acquisition and retrieval phases in an animal model of central post-stroke pain. Behav Brain Res 317:251–262Google Scholar
  5. 5.
    Geurts P, Ernst D, Wehenkel L (2006) Extremely randomized trees. Mach Learn 63(1):3–42CrossRefGoogle Scholar
  6. 6.
    Ghafurian S, Hacihaliloglu I, Metaxas DN, Tan V, Li K (2017) A computationally efficient 3D/2D registration method based on image gradient direction probability density function. Neurocomputing 229:100–108CrossRefGoogle Scholar
  7. 7.
    Gillebert CR, Humphreys GW, Mantini D (2014) Automated delineation of stroke lesions using brain CT images. NeuroImage: Clinical 4:540–548CrossRefGoogle Scholar
  8. 8.
    Ji H, Wu G, Wang Q, Wang Y, Kim M, Shen D (2012) Directed graph based image registration. Comput Med Imaging Graph 36(2):139–151CrossRefGoogle Scholar
  9. 9.
    Liu SX (2009) Symmetry and asymmetry analysis and its implications to computer-aided diagnosis: a review of the literature. J Biomed Inform 42(6):1056–1064CrossRefGoogle Scholar
  10. 10.
    Mah Y-H, Jager R, Kennard C, Husain M, Nachev P (2014) A new method for automated high-dimensional lesion segmentation evaluated in vascular injury and applied to the human occipital lobe. Cortex 56:51–63CrossRefGoogle Scholar
  11. 11.
    Mahapatra D (2014) Analyzing training information from random forests for improved image segmentation. IEEE Trans Image Process 23(4):1504–1512MathSciNetCrossRefGoogle Scholar
  12. 12.
    Maiora J, Ayerdi B, Graña M (2014) Random forest active learning for AAA thrombus segmentation in computed tomography angiography images. Neurocomputing 126:71–77CrossRefGoogle Scholar
  13. 13.
    Menze BH, Van Leemput K, Lashkari D, Riklin-Raviv T, Geremia E, Alberts E, Gruber P, Wegener S, Weber M-A, Szekely G, Ayache N, Golland P (2016) A generative probabilistic model and discriminative extensions for brain lesion segmentation— with application to tumor and stroke. IEEE Trans Med Imaging 35(4):933–946CrossRefGoogle Scholar
  14. 14.
    Mitra J, Bourgeat P, Fripp J, Ghose S, Rose S, Salvado O, Connelly A, Campbell B, Palmer S, Sharma G, Christensen S, Carey L (2014) Stroke laterality bias in the management of acute ischemic stroke. NeuroImage 98:324–335CrossRefGoogle Scholar
  15. 15.
    Moro V, Pernigo S, Tsakiris M, Avesani R, Edelstyn NMJ, Jenkinson PM, Fotopoulou A (2016) Motor versus body awareness: voxel-based lesion analysis in anosognosia for hemiplegia and somatoparaphrenia following right hemisphere stroke. Cortex 83:62–77CrossRefGoogle Scholar
  16. 16.
    Mun JK, Park SJ, Kim SJ, Young Bang O, Chung C-S, Lee KH, Kim G-M (2016) Characteristic lesion pattern and echocardiographic findings in extra-cardiac shunt-related stroke. J Neurol Sci 369:176–180CrossRefGoogle Scholar
  17. 17.
    Rekik I, Allassonnière S, Carpenter TK, Wardlaw JM (2014) Using longitudinal metamorphosis to examine ischemic stroke lesion dynamics on perfusion-weighted images and in relation to final outcome on T2-w images. NeuroImage: Clinical 5:332–340CrossRefGoogle Scholar
  18. 18.
    Rosales RL, Efendy F, Teleg ESA, Delos Santos MMD, Rosalesd MCE, Ostrea M, Tanglao MJ, Ng AR (2016) Botulinum toxin as early intervention for spasticity after stroke or non-progressive brain lesion: a meta-analysis. J Neurol Sci 371:6–14CrossRefGoogle Scholar
  19. 19.
    Saad NM, Noor NSM, Abdullah AR, Muda S, Muda AF, Abdul Rahman NNS (2017) Automated stroke lesion detection and diagnosis system. In: Proceedings of the International MultiConference of Engineers and Computer Scientists, vol. 1Google Scholar
  20. 20.
    So RWK, Chung ACS (2017) A novel learning-based dissimilarity metric for rigid and non-rigid medical image registration by using Bhattacharyya distances. Pattern Recogn 62:161–174CrossRefGoogle Scholar
  21. 21.
    Stille M, Smith EJ, Crum WR, Modo M (2013) 3D reconstruction of 2D fluorescence histology images and registration with in vivo MR images: application in a rodent stroke model. J Neurosci Methods 219(1):27–40CrossRefGoogle Scholar
  22. 22.
    Sweeney EM, Shinohara RT, Shiee N, Mateen FJ, Chudgar AA, Cuzzocreo JL, Calabresi PA, Pham DL, Reich DS, Crainiceanu CM (2013) OASIS is automated statistical inference for segmentation, with applications to multiple sclerosis lesion segmentation in MRI. NeuroImage: Clinical 2:402–413CrossRefGoogle Scholar
  23. 23.
    Tao D, Cheng J, Gao X, Li X, Deng C (2017) Robust sparse coding for mobile image labeling on the cloud. IEEE Transactions on Circuits and Systems for Video Technology 27(1):62–72CrossRefGoogle Scholar
  24. 24.
    Tao D, Guo Y, Li Y, Gao X (2018) Tensor rank preserving discriminant analysis for facial recognition. IEEE Trans Image Process 27(1):325–334MathSciNetCrossRefGoogle Scholar
  25. 25.
    Tateishi Y, Hamabe J, Kanamoto T, Nakaoka K, Morofuji Y, Horie N, Izumo T, Morikawa M, Tsujino A (2016) Subacute lesion volume as a potential prognostic biomarker for acute ischemic stroke after intravenous thrombolysis. J Neurol Sci 369:77–81CrossRefGoogle Scholar
  26. 26.
    van Asselena M, Kessels RPC, Frijns CJM, Jaap Kappelle L, Neggers SFW, Postma A (2009) Object-location memory: a lesion-behavior mapping study in stroke patients. Brain Cogn 71(3):287–294CrossRefGoogle Scholar
  27. 27.
    Wilke M, de Haan B, Juenger H, Karnath H-O (2011) Manual, semi-automated, and automated delineation of chronic brain lesions: a comparison of methods. Neuroimage 56(4):2038–2204CrossRefGoogle Scholar
  28. 28.
    Yang X, Liu W, Tao D, Cheng J (2017) Canonical correlation analysis networks for two-view image recognition. Inf Sci 385:338–352CrossRefGoogle Scholar
  29. 29.
    Yu W, Tannast M, Zheng G (2017) Non-rigid free-form 2D–3D registration using a B-spline-based statistical deformation model. Pattern Recogn 63:689–699CrossRefGoogle Scholar
  30. 30.
    Zhang T, Xue J, Zhao X, Wang C, Liu Z, Zhou Y, Wang Y, Wang Y (2012) A prospective cohort study of lesion location and its relation to post-stroke depression among Chinese patients. J Affect Disord 136(1–2):e83–e87CrossRefGoogle Scholar

Copyright information

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

Authors and Affiliations

  1. 1.Department of Electronics and Communication Engineering, Pondicherry Engineering College (PEC)Pondicherry University (A Central University)PuducherryIndia
  2. 2.Department of Electronics and Communication EngineeringPondicherry Engineering College (PEC)PuducherryIndia

Personalised recommendations