Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 6, pp 6559–6579 | Cite as

Segmentation of ischemic stroke lesion from 3d mr images using random forest

  • Anjali GautamEmail author
  • Balasubramanian Raman
Article
  • 287 Downloads

Abstract

This paper focuses on segmentation of ischemic stroke lesion from the dataset contributed by Ischemic Stroke Lesion Segmentation (ISLES)-2015 Sub-acute Ischemic Stroke lesion Segmentation (SISS) challenge. The dataset comprises 28 stroke cases of magnetic resonance (MR) images. This study considers fluid attenuation inversion recovery (FLAIR) MR images for the segmentation of lesions. MR images are affected by various artifacts and noise. Hence, we applied wavelet based data denoising technique by optimal parameter selection for stroke lesion enhancement followed by random forest (RF). RF classifier was trained for different part of the brain for segmenting the stroke lesion. The obtained results show best overall segmentation accuracy when compared with the other methods. To measure the image similarity between the ground truth and the segmented image, we used the evaluation method provided by the ISLES-2015. The average symmetric surface distance (ASSD) of the segmentation was measured to be 4.57 mm, while Dice’s coefficient ((DC) lies between 0 and 1) was used to measure the volume overlap accuracy with an average of 0.67. The maximum of all surface distance was given by Hausdorff distance (HD) with an average of 28.09 mm. The average precision and average recall observed was 0.70 and 0.71 respectively. The ISLES image data and ground truth images kept on being openly accessible through an online virtual skeleton database which is an ongoing benchmarking resource.

Keywords

Segmentation Ischemic stroke Random forest FLAIR MR ISLES-2015 

Notes

Acknowledgements

We would like to thank Indian Institute of Technology Roorkee, Roorkee, India for their support.

Funding Information

This study was funded by the Ministry of Human Resource Development, Government of India, India (grant number MHC-02-23-200-428).

Compliance with Ethical Standards

Conflict of interests

All authors declare that they have no conflict of interest.

References

  1. 1.
    Alexander B, Murray AL, Loh WY, Matthews LG, Adamson C, Beare R, Chen J, Kelly CE, Rees S, Warfield SK, Anderson PJ (2017) A new neonatal cortical and subcortical brain atlas: the Melbourne Children’s Regional Infant Brain (m-CRIB) atlas. NeuroImage 147:841–851Google Scholar
  2. 2.
    Anbeek P, Vincken K, van Osch M, Bisschops B, Viergever M, van der Grond J (2003) Automated white matter lesion segmentation by voxel probability estimation. In: Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer Berlin Heidelberg, pp 610–617Google Scholar
  3. 3.
    Bernarding J, Braun J, Hohmann J, Mansmann U, Hoehn-Berlage M, Stapf C, Wolf KJ, Tolxdorff T (2000) Histogram-based characterization of healthy and ischemic brain tissues using multiparametric MR imaging including apparent diffusion coefficient maps and relaxometry. Magn Reson Med 43(1):52–61Google Scholar
  4. 4.
    Bisio I, Fedeli A, Lavagetto F, Pastorino M, Randazzo A, Sciarrone A, Tavanti E (2018) A numerical study concerning brain stroke detection by microwave imaging systems. Multimed Tools Appl 77(88):9341–9363Google Scholar
  5. 5.
    Bonita R, Mendis S, Truelsen T, Bogousslavsky J, Toole J, Yatsu F (2004) The global stroke initiative. Lancet Neurol 3(7):391–393Google Scholar
  6. 6.
    Braun J, Bernarding J, Koennecke HC, Wolf KJ, Tolxdorff T (2002) Feature-based, automated segmentation of cerebral infarct patterns using T2- and Diffusion-weighted imaging. Comput Methods Biomech Biomed Engin 5(6):411–420Google Scholar
  7. 7.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32zbMATHGoogle Scholar
  8. 8.
    Burt P, Adelson E (1983) The Laplacian pyramid as a compact image code. IEEE Trans Commun 31(4):532–540Google Scholar
  9. 9.
    Carano RA, Li F, Irie K, Helmer KG, Silva MD, Fisher M, Sotak CH (2000) Multispectral analysis of the temporal evolution of cerebral ischemia in the rat brain. J Magn Reson Imaging 12(6):842–858Google Scholar
  10. 10.
    Caselles V, Catté F, Coll T, Dibos F (1993) A geometric model for active contours in image processing. Numer Math 66(1):1–31MathSciNetzbMATHGoogle Scholar
  11. 11.
    Caselles V, Kimmel R, Sapiro G (1997) Geodesic active contours. Int J Comput Vis 22(1):61–79zbMATHGoogle Scholar
  12. 12.
    Castillo J, Leira R, García MM, Serena J, Blanco M, Dávalos A (2004) Blood pressure decrease during the acute phase of ischemic stroke is associated with brain injury and poor stroke outcome. Stroke 35(2):520–526Google Scholar
  13. 13.
    Chawla M, Sharma S, Sivaswamy J, Kishore LT (2009) A method for automatic detection and classification of stroke from brain CT images. In: Proc of the 31st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), pp 3581–3584Google Scholar
  14. 14.
    Chen L, Bentley P, Rueckert D (2015) A novel framework for sub-acute stroke lesion segmentation based on random forest. In: Proc of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2015, Ischemic Stroke Lesion Segmentation, pp 9–12Google Scholar
  15. 15.
    Chyzhyk D, Dacosta-Aguayo R, Mataró M, Graña M (2015) An active learning approach for stroke lesion segmentation on multimodal MRI data. Neurocomputing 150:26–36Google Scholar
  16. 16.
    Crinion J, Holland AL, Copland DA, Thompson CK, Hillis AE (2013) Neuroimaging in aphasia treatment research: quantifying brain lesions after stroke. Neuroimage 73:208–214Google Scholar
  17. 17.
    Crowley JL (1981) A representation for visual information. PhD thesis, Carnegie Mellon UniversityGoogle Scholar
  18. 18.
    Cui J, Liu Y, Xu Y, Zhao H, Zha H (2013) Tracking generic human motion via fusion of low-and high-dimensional approaches. IEEE Trans Syst Man Cybern Syst 43(4):996–1002Google Scholar
  19. 19.
    Donoho DL (1995) De-noising by soft-thresholding. IEEE Trans Inf Theory 41 (3):613–627MathSciNetzbMATHGoogle Scholar
  20. 20.
    Gao S, Yang J, Yan Y (2014) A novel multiphase active contour model for inhomogeneous image segmentation. Multimed Tools Appl 72(3):2321–37Google Scholar
  21. 21.
    Grossmann A, Morlet J (1984) Decomposition of Hardy functions into square integrable wavelets of constant shape. SIAM J Math Anal 15(4):723–736MathSciNetzbMATHGoogle Scholar
  22. 22.
    Grzesik A, Bernarding J, Braun J, Koennecke HC, Wolf KJ, Tolxdorff T (2000) Characterization of storke lesions using a histrogram-based data analysis including diffusion-and perfusion-weighted imaging. Bildverarbeitung für die Medizin, SpringerGoogle Scholar
  23. 23.
    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 17:918–934Google Scholar
  24. 24.
    Güler İ, Demirhan A, Karakış R (2009) Interpretation of MR images using self-organizing maps and knowledge-based expert systems. Digit Signal Process 19(4):668–677Google Scholar
  25. 25.
    Haeck T, Maes F, Suetens P (2015) ISLES Challenge 2015: Automated model-based segmentation of ischemic stroke in MR images. In: Proc of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2015, Ischemic Stroke Lesion Segmentation, pp 47–50Google Scholar
  26. 26.
    Heart Disease and Stroke Statistics 2017 At-a-Glance. https://www.heart.org/idc/groups/ahamah-public/@wcm/@sop/@smd/documents/downloadable/ucm_491265.eps. Accessed 27 January 2017
  27. 27.
    Hillman GR, Chang CW, Ying H, Kent TA, Yen J (1995) Automatic system for brain MRI analysis using a novel combination of fuzzy rule-based and automatic clustering techniques. In: Proceedings of medical imaging 1995: Image processing, SPIE, vol 2434, pp 16–26Google Scholar
  28. 28.
    Hong YC, Lee JT, Kim H, Kwon HJ (2002) Air pollution. Stroke 33 (9):2165–2169Google Scholar
  29. 29.
    Hutter A, Schwetye KE, Bierhals AJ, McKinstry RC (2003) Brain neoplasms: epidemiology, diagnosis, and prospects for cost-effective imaging. Neuroimaging Clin N Am 13(2):237–250Google Scholar
  30. 30.
    Jacobs MA, Mitsias P, Soltanian-Zadeh H, Santhakumar S, Ghanei A, Hammond R, Peck DJ, Chopp M, Patel S (2001) Multiparametric MRI tissue characterization in clinical stroke with correlation to clinical outcome. Stroke 32 (4):950–957Google Scholar
  31. 31.
    Jenkinson M, Pechaud M, Smith S (2005) BET2: MR-Based estimation of brain, skull and scalp surfaces. In: Eleventh annual meeting of the organization for human brain mapping, vol 17, pp 167Google Scholar
  32. 32.
    Kabir Y, Dojat M, Scherrer B, Forbes F, Garbay C (2007) Multimodal MRI segmentation of ischemic stroke lesions. In: Proc of the 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBS), pp 1595–1598Google Scholar
  33. 33.
    Kamnitsas K, Chen L, Ledig C, Rueckert D, Glocker B (2015) Multi-scale 3D convolutional neural networks for lesion segmentation in brain MRI. In: Proc of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2015, Ischemic Stroke Lesion Segmentation, pp 13–16Google Scholar
  34. 34.
    Kohler R (1981) A segmentation system based on thresholding. Comput Graph Image Process 15(4):319–338Google Scholar
  35. 35.
    Liu Y, Nie L, Han L, Zhang L, Rosenblum DS (2015) Action2activity: Recognizing Complex Activities from Sensor Data. In: IJCAI, vol 2015, pp 1617–1623Google Scholar
  36. 36.
    Liu Y, Nie L, Liu L, Rosenblum DS (2016) From action to activity: sensor-based activity recognition. Neurocomputing 181:108–15Google Scholar
  37. 37.
    Liu Y, Zhang L, Nie L, Yan Y, Rosenblum DS (2016) Fortune teller: Predicting your career path. In: AAAI 2016, vol 2016, pp 201–207Google Scholar
  38. 38.
    Liu Y, Zheng Y, Liang Y, Liu S, Rosenblum DS (2016) Urban water quality prediction based on multi-task multi-view learningGoogle Scholar
  39. 39.
    Mackay J, Mensah GA, Mendis S, Greenlund K (2004) The atlas of heart disease and stroke. World Health Organization, GenevaGoogle Scholar
  40. 40.
    Mahmood Q, Basit A (2015) Automatic ischemic stroke lesion segmentation in multi-spectral MRI images using random forests classifier. In: Proc of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2015, Ischemic Stroke Lesion Segmentation, pp 43–46Google Scholar
  41. 41.
    Maier O, Wilms M, Handels H (2015) Random forests with selected features for stroke lesion segmentation. In: Proc of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2015, Ischemic Stroke Lesion Segmentation, pp 17–21Google Scholar
  42. 42.
    Maier O, Menze BH, von der Gablentz J, Häni L, Heinrich MP, Liebrand M, Winzeck S, Basit A, Bentley P, Chen L, Christiaens D (2017) ISLES 2015-A Public evaluation benchmark for ischemic stroke lesion segmentation from multispectral MRI. Med Image Anal 35:250–269Google Scholar
  43. 43.
    Mitra J, Bourgeat P, Fripp J, Ghose S, Rose S, Salvado O, Connelly A, Campbell B, Palmer S, Sharma G, Christensen S (2014) Lesion segmentation from multimodal MRI using random forest following ischemic stroke. NeuroImage 98:324–335Google Scholar
  44. 44.
    Neumann-Haefelin T, Wittsack HJ, Wenserski F, Siebler M, Seitz RJ, Mödder U, Freund HJ (1999) Diffusion-and perfusion-weighted MRI. Stroke 30(8):1591–1597Google Scholar
  45. 45.
    Parsons MW, Pepper EM, Bateman GA, Wang Y, Levi CR (2007) Identification of the penumbra and infarct core on hyperacute noncontrast and perfusion CT. Neurology 68(10):730–736Google Scholar
  46. 46.
    Plunkett JW (2008) Plunkett’s health care industry almanac. Plunkett Research, Ltd, HoustonGoogle Scholar
  47. 47.
    Rajini NH, Bhavani R (2013) Computer aided detection of ischemic stroke using segmentation and texture features. Measurement 46(6):1865–1874Google Scholar
  48. 48.
    Rekik I, Allassonnière S, Carpenter TK, Wardlaw JM (2012) Medical image analysis methods in MR/CT-imaged acute-subacute ischemic stroke lesion: segmentation, prediction and insights into dynamic evolution simulation models. A critical appraisal. Neuroimage Clin 1(1):164–178Google Scholar
  49. 49.
    Reza SM, Pei L, Iftekharuddin KM (2015) Ischemic stroke lesion segmentation using local gradient and texture features. In: Proc of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2015, Ischemic Stroke Lesion Segmentation, pp 23–26Google Scholar
  50. 50.
    Robben D, Christiaens D, Rangarajan JR, Gelderblom J, Joris P, Maes F, Suetens P (2015) ISLES Challenge 2015: A voxel-wise, cascaded classification approach to stroke lesion segmentation. In: Proc of International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) 2015, Ischemic Stroke Lesion Segmentation, pp 27–30Google Scholar
  51. 51.
    Roy S, Chatterjee K, Bandyopadhyay SK (2014) Segmentation of acute brain stroke from MRI of brain image using power law transformation with accuracy estimation. In: Advanced computing, networking and informatics, springer international publishing, vol 1, pp 453–461Google Scholar
  52. 52.
    Schaefer PW, Ozsunar Y, He J, Hamberg LM, Hunter GJ, Sorensen AG, Koroshetz WJ, Gonzalez RG (2003) Assessing tissue viability with MR diffusion and perfusion imaging. AJNR Am J Neuroradiol 24(3):436–443Google Scholar
  53. 53.
    Schlaug G, Siewert B, Benfield A, Edelman RR, Warach S (1997) Time course of the apparent diffusion coefficient (ADC) abnormality in human stroke. Neurology 49(1):113–119Google Scholar
  54. 54.
    Seghier ML, Ramlackhansingh A, Crinion J, Leff AP, Price CJ (2008) Lesion identification using unified segmentation-normalisation models and fuzzy clustering. Neuroimage 41(4):1253–1266Google Scholar
  55. 55.
    Selesnick IW, Baraniuk RG, Kingsbury NC (2005) The dual-tree complex wavelet transform. IEEE Signal Process Mag 22(6):123–151Google Scholar
  56. 56.
    Shih LC, Saver JL, Alger JR, Starkman S, Leary MC, Vinuela F, Duckwiler G, Gobin YP, Jahan R, Villablanca JP, Vespa PM (2003) Perfusion-weighted magnetic resonance imaging thresholds identifying core, irreversibly infarcted tissue. Stroke 34(6):1425–1430Google Scholar
  57. 57.
    Stroke Statistics | Internet Stroke Center. http://www.strokecenter.org/patients/about-stroke/stroke-statistics/. Accessed 30 January 2017
  58. 58.
    Yang X, Gao X, Tao D, Li X, Li J (2015) An efficient MRF embedded level set method for image segmentation. IEEE Trans Image Process 24(1):9–21MathSciNetzbMATHGoogle Scholar
  59. 59.
    Yushkevich PA, Piven J, Hazlett HC, Smith RG, Ho S, Gee JC, Gerig G (2006) User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability. Neuroimage 31(3):1116–1128Google Scholar
  60. 60.
    Zhang X, Sun Y, Wang G, Guo Q, Zhang C, Chen B (2017) Improved fuzzy clustering algorithm with non-local information for image segmentation. Multimed Tools Appl 76(6):7869–7895Google Scholar
  61. 61.
    Zhang R, Zhao L, Lou W, Abrigo JM, Mok VC, Chu WC, Wang D, Shi L (2018) Automatic Segmentation of Acute Ischemic Stroke from DWI using 3D Fully Convolutional DenseNets. IEEE Trans Med ImagingGoogle Scholar
  62. 62.
    Zhu SC, Yuille A (1996) Region competition: Unifying snakes, region growing, and bayes/MDL for multiband image segmentation. IEEE Trans Pattern Anal Mach Intell 18(9):884–900Google Scholar

Copyright information

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

Authors and Affiliations

  1. 1.Computer Science and Engineering DepartmentIndian Institute of Technology RoorkeeRoorkeeIndia

Personalised recommendations