Automated Identification of Injury Dynamics After Neonatal Hypoxia-Ischemia

Part of the Computational Biology book series (COBO, volume 22)


Neonatal hypoxic ischemic injury (HII) is a devastating brain disease for which hypothermia is currently the only approved treatment. As new therapeutic interventions emerge there is a significant need for noninvasive objective quantification of the spatiotemporal lesion dynamics combined with precise information about lesion constituents (ischemic core and penumbra). These metrics are important for deciding treatment parameters (type, time, site, and dose) and for monitoring injury-therapy interactions. Such information provided ‘on-line’ in a timely fashion to the clinician could revolutionize clinical management. Like other spatiotemporal biological processes, video bioinformatics can assist objective monitoring of injury–therapy interactions. We have been studying the efficacy of various potential treatments in translational (rodent) HII models using magnetic resonance imaging (MRI). We have developed a novel computational tool, hierarchical region splitting (HRS) to rapidly identify ischemic lesion metrics. HRS detects similar lesion volumes compared to manual detection methods and is fast, robust, and reliable compared to other computational methods. HRS also provides additional information about the location, size, and evolution of the core and penumbra, which are difficult to ascertain with manual methods. This chapter summarizes the ability of HRS to identify lesion dynamics and ischemic core-penumbra evolution following neonatal HII. In addition, we demonstrate that HRS provides information about lesion dynamics following different therapies (e.g., hypothermia, stem cell implantation). Our findings show that computational analysis of MR images using HRS provides novel quantitative approaches that can be applied to clinical and translational stroke research using data mining of standard experimental and clinical MRI data.


Lesion Volume Magnetic Resonance Imaging Data Spatiotemporal Evolution Ischemic Core Neuronal Stem Cell 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



Apparent diffusion coefficient




Computer vision and pattern recognition


Diffusion-perfusion mismatch


Diffusion-weighted imaging




Hypoxic ischemic injury


Hierarchical region splitting






Magnetic resonance


Magnetic resonance imaging


Modified watershed


National Institute of Health


Neural stem cell




Perfusion-weighted imaging


Region of interest


Rat pup severity score


Symmetry-integrated region growing


Susceptibility weighted imaging


T2-weighted imaging



This research work has been supported by grants from the Department of Pediatrics (School of Medicine, Loma Linda University) and NIH-NINDS (1RO1NS059770-01A2). The authors would also like to acknowledge kind sharing of comparative results from SIRG and MWS methods by Dr. Yu Sun and Prof. Bir Bhanu in the Center of Research in Intelligent Systems (Department of Electrical and Computer Engineering, University of California at Riverside).


  1. 1.
    Adler ED, Bystrup A, Briley-Saebo KC, Mani V, Young W, Giovanonne S, Altman P, Kattman SJ, Frank JA, Weinmann HJ, Keller GM, Fayad ZA (2009) In vivo detection of embryonic stem cell-derived cardiovascular progenitor cells using Cy3-labeled Gadofluorine M in murine myocardium. JACC Cardiovasc Imaging 2:1114–1122CrossRefGoogle Scholar
  2. 2.
    Alonso-Alconada D, Hilario E, Alvarez FJ, Alvarez A (2012) Apoptotic cell death correlates with ROS overproduction and early cytokine expression after hypoxia-ischemia in fetal lambs. Reprod Sci 19(7):754–763CrossRefGoogle Scholar
  3. 3.
    Aly H, Khashaba MT, El-Ayouty M, El-Sayed O, Hasanein BM (2006) IL-1beta, IL-6 and TNF-alpha and outcomes of neonatal hypoxic ischemic encephalopathy. Brain Dev 28(3):178–182CrossRefGoogle Scholar
  4. 4.
    Ashwal S, Tone B, Tian HR, Chong S, Obenaus A (2007) Comparison of two neonatal ischemic injury models using magnetic resonance imaging. Pediatr Res 61:9–14CrossRefGoogle Scholar
  5. 5.
    Ashwal S, Obenaus A, Snyder EY (2009) Neuroimaging as a basis for rational stem cell therapy. Pediatr Neurol 40:227–236CrossRefGoogle Scholar
  6. 6.
    Ashwal S, Ghosh N, Turenius CI, Dulcich M, Denham CM, Tone B, Hartman R, Snyder EY, Obenaus A (2014) The reparative effects of neural stem cells in neonatal hypoxic ischemic injury are not influenced by host gender. Pediatr Res 75(5):603–611CrossRefGoogle Scholar
  7. 7.
    Badaut J, Ashwal S, Obenaus A (2011) Aquaporins in cerebrovascular disease: a target for treatment of brain edema? Cerebrovasc Dis 31:521–531CrossRefGoogle Scholar
  8. 8.
    Birgani PM, Ashtiyani M, Asadi S (2008) MRI segmentation using fuzzy C-means clustering algorithm basis neural network. In: Proceedings of IEEE international conference on information & communication technology, pp 1–5Google Scholar
  9. 9.
    Corso JJ, Sharon E, Dube S, El-Saden S, Sinha U, Yuille A (2008) Efficient multilevel brain tumor segmentation with integrated bayesian model classification. IEEE Trans Med Imaging 27(5):629–640CrossRefGoogle Scholar
  10. 10.
    Counsell SJ, Tranter SL, Rutherford MA (2010) Magnetic resonance imaging of brain injury in the high-risk term infant. Semin Perinatol 34(1):67–78CrossRefGoogle Scholar
  11. 11.
    Cuadra MB, Pollo C, Bardera A, Cuisenaire O, Villemure JG, Thiran JP (2004) Atlas-based segmentation of pathological MR brain images using a model of lesion growth. IEEE Trans Med Imaging 23(10):1301–1314CrossRefGoogle Scholar
  12. 12.
    del Zoppo GJ, Sharp FR, Heiss WD, Albers GW (2011) Heterogeneity in the penumbra. J Cereb Blood Flow Metab 31:1836–1851CrossRefGoogle Scholar
  13. 13.
    Dinov ID, Van Horn JD, Lozev KM, Magsipoc R, Petrosyan P, Liu Z, Mackenzie-Graham A, Eggert P, Parker DS, Toga AW (2009) Efficient, distributed and interactive neuroimaging data analysis using the LONI pipeline. Front Neuroinform 3:22CrossRefGoogle Scholar
  14. 14.
    Faiz M, Acarin L, Villapol S, Schulz S, Castellano B, Gonzalez B (2008) Substantial migration of SVZ cells to the cortex results in the generation of new neurons in the excitotoxically damaged immature rat brain. Mol Cell Neurosci 38:170–182CrossRefGoogle Scholar
  15. 15.
    Ghosh N, Bhanu B (2008) How current BNs fail to represent evolvable pattern recognition problems and a proposed solution. In: Proceedings of 19th IEEE international conference on pattern recognition (ICPR), Tampa, Florida, USA, pp 3618–3621Google Scholar
  16. 16.
    Ghosh N, Recker R, Shah A, Bhanu B, Ashwal S, Obenaus A (2011) Automated ischemic lesion detection in a neonatal model of hypoxic ischemic injury. Magn Reson Imaging 33:772–781CrossRefGoogle Scholar
  17. 17.
    Ghosh N, Sun Y, Turenius C, Bhanu B, Obenaus A, Ashwal S (2012) Computational analysis: a bridge to translational stroke treatment. In: Translational stroke research. Springer, New York, pp 881–909Google Scholar
  18. 18.
    Ghosh N, Yuan X, Turenius CI, Tone B, Ambadipudi K, Snyder EY, Obenaus A, Ashwal S (2012) Automated core-penumbra quantification in neonatal ischemic brain injury. J Cereb Blood Flow Metab 32(12):2161–2170CrossRefGoogle Scholar
  19. 19.
    Ghosh N, Bhanu B (2014) Evolving bayesian graph for 3D vehicle model building from video. In: IEEE transaction on intelligent transportation systems (TITS), vol 15(2), pp 563–578Google Scholar
  20. 20.
    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 (MedIA). 18(7):1059–1069CrossRefGoogle Scholar
  21. 21.
    Gousias IS, Rueckert D, Heckemann RA, Dyet LE, Boardman JP, Edwards AD, Hammers A (2008) Automatic segmentation of brain MRIs of 2-year-olds into 83 regions of interest. NeuroImage 40:672–684CrossRefGoogle Scholar
  22. 22.
    Gutierrez LG, Rovira A, Portela LA, Leite Cda C, Lucato LT (2010) CT and MR in non-neonatal hypoxic-ischemic encephalopathy: radiological findings with pathophysiological correlations. Neuroradiology 52(11):949–976CrossRefGoogle Scholar
  23. 23.
    Jacobs SE, Berg M, Hunt R, Tarnow-Mordi WO, Inder TE, Davis PG (2013) Cooling fornewborns with hypoxic ischaemic encephalopathy. Cochrane Database Syst Rev 1:CD003311Google Scholar
  24. 24.
    Johnston MV, Fatemi A, Wilson MA, Northington F (2011) Treatment advances in neonatal neuroprotection and neurointensive care. Lancet Neurol 10(4):372–382CrossRefGoogle Scholar
  25. 25.
    Kabir Y, Dojat M, Scherrer B, Forbes F, Garbay C (2007) Multimodal MRI segmentation of ischemic stroke lesions. In: Conference proceedings of IEEE engineering in medicine and biology society, pp 1595–1598Google Scholar
  26. 26.
    Kim D, Hong KS, Song J (2007) The present status of cell tracking methods in animal models using magnetic resonance imaging technology. Mol Cells 23:132–137Google Scholar
  27. 27.
    Klein S, Staring M, Murphy K, Viergever MA, Pluim JP (2010) Elastix: a toolbox for intensity-based medical image registration. IEEE Trans Med Imaging 29(1):196–205CrossRefGoogle Scholar
  28. 28.
    Kraitchman DL, Gilson WD, Lorenz CH (2008) Stem cell therapy: MRI guidance and monitoring. J Magn Reson Imaging: JMRI 27:299–310CrossRefGoogle Scholar
  29. 29.
    Kressler B, de Rochefort L, Liu T, Spincemaille P, Jiang Q, Wang Y (2009) Nonlinear regularization for per voxel estimation of magnetic susceptibility distributions from MRI field maps. IEEE Trans Med Imaging 29:273–281CrossRefGoogle Scholar
  30. 30.
    Kruggel F, Paul JS, Gertz HJ (2008) Texture-based segmentation of diffuse lesions of the brain’s white matter. NeuroImage 39(3):987–996CrossRefGoogle Scholar
  31. 31.
    Leger PL, Bonnin P, Lacombe P, Couture-Lepetit E, Fau S, Renolleau S, Gharib A, Baud O, Charriaut-Marlanque C (2013) Dynamic spatio-temporal imaging of early reflow in a neonatal rat stroke model. J Cereb Blood Flow Metab 33(1):137–145CrossRefGoogle Scholar
  32. 32.
    Liu J, Udupa JK, Odhner D, Hackney D, Moonis G (2005) A system for brain tumor volume estimation via MR imaging and fuzzy connectedness. Comp Med Image Graph 29(1):21–34CrossRefGoogle Scholar
  33. 33.
    Lo EH (2008) A new penumbra: transitioning from injury into repair after stroke. Nat Med 14:497–500CrossRefGoogle Scholar
  34. 34.
    Manana G, Romero E, Gonzalez F (2006) A grid computing approach to subtraction radiography. In: Proceedings of IEEE international conference on image processing (ICIP), pp 3325–3328Google Scholar
  35. 35.
    McAdams RM, Juul SE (2012) The role of cytokines and inflammatory cells in perinatal brain injury. Neurol Res Int 561494Google Scholar
  36. 36.
    Muldoon LL, Sandor M, Pinkston KE, Neuwelt EA (2005) Imaging, distribution, and toxicity of superparamagnetic iron oxide magnetic resonance nanoparticles in the rat brain and intracerebral tumor. Neurosurgery 57:785–796CrossRefGoogle Scholar
  37. 37.
    Neumann-Haefelin T, Steinmetz H (2007) Time is brain: is MRI the clock? Curr Opin Neurol 20(4):410–416CrossRefGoogle Scholar
  38. 38.
    Niimi T, Imai K, Maeda H, Ikeda M (2007) Information loss in visual assessments of medical images. Eur J Radiol 61(2):362–366CrossRefGoogle Scholar
  39. 39.
    Northington FJ, Zelaya ME, O’Riordan DP, Blomgren K, Flock DL, Hagberg H, Ferriero DM, Martin LJ (2007) Failure to complete apoptosis following neonatal hypoxia-ischemia manifests as “continuum” phenotype of cell death and occurs with multiple manifestations of mitochondrial dysfunction in rodent forebrain. Neuroscience 149:822–833CrossRefGoogle Scholar
  40. 40.
    Obenaus A, Dilmac N, Tone B, Tian HR, Hartman R, Digicaylioglu M, Snyder EY, Ashwal S (2011) Long-term magnetic resonance imaging of stem cells in neonatal ischemic injury. Ann Neurol 69(2):282–291CrossRefGoogle Scholar
  41. 41.
    Panigrahy A, Blüml S (2008) Advances in magnetic resonance imaging of the injured neonatal brain. Pediatr Ann 37(6):395–402CrossRefGoogle Scholar
  42. 42.
    Park KI, Himes BT, Stieg PE, Tessler A, Fischer I, Snyder EY (2006) Neural stem cells may be uniquely suited for combined gene therapy and cell replacement: evidence from engraftment of Neurotrophin-3-expressing stem cells in hypoxic-ischemic brain injury. Exp Neurol 199:179–190CrossRefGoogle Scholar
  43. 43.
    Phillips AW, Johnston MV, Fatemi A (2013) The potential for cell-based therapy in perinatal brain injuries. Transl Stroke Res 4(2):137–148CrossRefGoogle Scholar
  44. 44.
    Qiao H, Zhang H, Zheng Y, Ponde DE, Shen D, Gao F, Bakken AB, Schmitz A, Kung HF, Ferrari VA, Zhou R (2009) Embryonic stem cell grafting in normal and infarcted myocardium: serial assessment with MR imaging and PET dual detection. Radiology 250:821–829CrossRefGoogle Scholar
  45. 45.
    Ratan R, Sharma S, Sharma SK (2009) Brain tumor detection based on multi-parameter MRI image analysis (2009) Int J Graph Vision Image Proc (GVIP) 9(3):9–17Google Scholar
  46. 46.
    Recker R, Adami A, Tone B, Tian HR, Lalas S, Hartman RE, Obenaus A, Ashwal S (2009) Rodent neonatal bilateral carotid artery occlusion with hypoxia mimics human hypoxic-ischemic injury. J Cereb Blood Flow Metab 29(7):1305–1316CrossRefGoogle Scholar
  47. 47.
    Sadasivan C, Cesar L, Seong J, Wakhloo AK, Lieber BB (2009) Treatment of rabbit elastase-induced aneurysm models by flow diverters: development of quantifiable indexes of device performance using digital subtraction angiography. IEEE Trans Med Imaging 28(7):1117–1125CrossRefGoogle Scholar
  48. 48.
    Schiemanck SK, Kwakkel G, Post MW, Prevo AJ (2006) Predictive value of ischemic lesion volume assessed with magnetic resonance imaging for neurological deficits and functional outcome poststroke: a critical review of the literature. Neurorehab Neural Repair 20:492–502CrossRefGoogle Scholar
  49. 49.
    Schmidt M, Levner I, Greiner R, Murtha A, Bistritz A (2005) Segmenting brain tumors using alignment-based features. In: Proceedings of IEEE international conference on machine learning application, pp 215–220Google Scholar
  50. 50.
    Shankaran S, Barnes PD, Hintz SR, Laptook AR, Zaterka-Baxter KM, McDonald SA et al (2012) Brain injury following trial of hypothermia for neonatal hypoxic-ischaemic encephalopathy. Arch Dis Child Fetal Neonatal Ed 97(6):F398–F404Google Scholar
  51. 51.
    Smith EJ, Stroemer RP, Gorenkova N, Nakajima M, Crum WR, Tang E, Stevanato L, Sinden JD, Modo M (2012) Implantation site and lesion topology determine efficacy of a human neural stem cell line in a rat model of chronic stroke. Stem Cells 30(4):785–796CrossRefGoogle Scholar
  52. 52.
    Snyder EY (2011) The intricate dance between repair and inflammation: introduction to special issue. Exp Neurol 230(1):1–2CrossRefGoogle Scholar
  53. 53.
    Stone BS, Zhang J, Mack DW, Mori S, Martin LJ, Northington FJ (2008) Delayed neural network degeneration after neonatal hypoxia-ischemia. Ann Neurol 64:535–546CrossRefGoogle Scholar
  54. 54.
    Straka M, Albers GW, Bammer R (2010) Real-time diffusion-perfusion mismatch analysis in acute stroke. J Magn Reson Imaging 32:1024–1037CrossRefGoogle Scholar
  55. 55.
    Sun Y, Bhanu B, Bhanu S (2009) Automatic symmetry-integrated brain injury detection in MRI sequences. In: IEEE Wshp mathematical methods in biomedical image analysis, held in conjunction with international conference on computer vision & pattern recognition, pp 79–86Google Scholar
  56. 56.
    Van Leemput K, Maes F, Vandermeulen D, Colchester A, Suetens P (2001) Automated segmentation of multiple sclerosis lesions by model outlier detection. IEEE Trans Med Imaging 20(8):677–688CrossRefGoogle Scholar
  57. 57.
    Vannucci RC, Vannucci SJ (2005) Perinatal hypoxic-ischemic brain damage: evolution of an animal model. Dev Neurosci 27:81–86CrossRefGoogle Scholar
  58. 58.
    Vexler ZS, Yenari MA (2009) Does inflammation after stroke affect the developing brain differently than adult brain? Dev Neurosci 31(5):378–393CrossRefGoogle Scholar
  59. 59.
    Vogt G, Laage R, Shuaib A, Schneider A (2012) VISTA Collaboration. Initial lesion volume is an independent predictor of clinical stroke outcome at day 90: an analysis of the Virtual International Stroke Trials Archive (VISTA) database. Stroke 43(5):1266–1272CrossRefGoogle Scholar
  60. 60.
    Wardlaw JM (2010) Neuroimaging in acute ischaemic stroke: insights into unanswered questions of pathophysiology. J Intern Med 267:172–190CrossRefGoogle Scholar
  61. 61.
    Wintermark P, Hansen A, Soul J, Labrecque M, Robertson RL, Warfield SK (2011) Early versus late MRI in asphyxiated newborns treated with hypothermia. Arch Dis Child Fetal Neonatal Ed 96(1):F36–F44CrossRefGoogle Scholar
  62. 62.
    Yuan X, Ghosh N, McFadden B, Tone B, Bellinger DL, Obenaus A, Ashwal S (2014) Hypothermia modulates cytokine responses after neonatal rat hypoxic-ischemic injury and reduces brain damage. ASN Neuro. 6(6):1–15Google Scholar
  63. 63.
    Zhiguo C, Xiaoxiao L, Bo P, Yiu-Sang M (2005) DSA image registration based on multiscale gabor filters and mutual information. In: Proceedings of IEEE international conference on information acquisition, pp 105–110Google Scholar
  64. 64.
    Zitová B, Flusser J (2003) Image registration methods: a survey. Image vis comput 21(11):977–1000Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Department of Pediatrics School of MedicineLoma Linda UniversityLoma LindaUSA

Personalised recommendations