Skip to main content
SpringerLink
Log in

Deep convolutional neural network for automatically segmenting acute ischemic stroke lesion in multi-modality MRI

  • Multi-Source Data Understanding (MSDU)
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Correct segmentation of stroke lesions from magnetic resonance imaging (MRI) is crucial for neurologists and patients. However, manual segmentation relies on expert experience and is time-consuming. The complicated stroke evolution phase and the limited samples pose challenges for automatic segmentation. In this study, we propose a novel deep convolutional neural network (Res-CNN) to automatically segment acute ischemic stroke lesions from multi-modality MRIs. Our network draws on U-shape structure, and we embed residual unit into network. In Res-CNN, we use residual unit to alleviate the degradation problem and use multi-modality to exploit the complementary information in MRIs. Before training the model, we use data fusion and data augmentation methods to increase the number of training images. Seven neural networks are extensively evaluated on two acute ischemic stroke datasets. Res-CNN shows good performance compared with other six networks both in single modality and multi-modality. Furthermore, compared with the gold standard segmentation manually labeled by two neurologists on a local test dataset, our network achieves the best results in seven neural networks. The average Dice coefficient and Hausdorff distance of our method are 74.20% and 2.33 mm, respectively. Our proposed network may provide a useful tool for segmentation lesion of acute ischemic stroke.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Notes

  1. https://itk.org/.

References

  1. Polman CH, Reingold SC, Edan G, Filippi M, Hartung H-P, Kappos L, Lublin FD, Metz LM, McFarland HF, O’Connor PW (2005) Diagnostic criteria for multiple sclerosis: 2005 revisions to the “mcdonald criteria”. Ann Neurol 58(6):840–846

    Article  Google Scholar 

  2. Chyzhyk D (2015) An active learning approach for stroke lesion segmentation on multimodal mri data. Neurocomputing 150:26–36

    Article  Google Scholar 

  3. Jacobsen C, Hagemeier J, Myhr KM, Nyland H, Lode K, Bergsland N, Ramasamy DP, Dalaker TO, Larsen JP, Farbu E (2014) Brain atrophy and disability progression in multiple sclerosis patients: a 10-year follow-up study. J Neurol Neurosurg Psychiatr 85(10):1109

    Article  Google Scholar 

  4. McKinley R, Häni L, Wiest R, Reyes M (2015) Segmenting the ischemic penumbra: a decision forest approach with automatic threshold finding. In: International workshop on Brainlesion: Glioma, multiple sclerosis, stroke and traumatic brain injuries, pp 275–83

    Chapter  Google Scholar 

  5. Neumann AB, Jonsdottir KY, Mouridsen K, Hjort N, Gyldensted C, Bizzi A, Fiehler J, Gasparotti R, Gillard JH, Hermier M (2009) Interrater agreement for final infarct mri lesion delineation. Stroke 40(12):3768–3771

    Article  Google Scholar 

  6. Wardlaw JM, Smith EE, Biessels GJ, Cordonnier C, Fazekas F, Frayne R, Lindley RI, O’Brien JT, Barkhof F, Benavente OR (2013) Neuroimaging standards for research into small vessel disease and its contribution to ageing and neurodegeneration. Lancet Neurol 12(8):822–838

    Article  Google Scholar 

  7. Grimaud J, Lai M, Thorpe J, Adeleine P, Wang L, Barker GJ, Plummer DL, Tofts PS, Mcdonald WI, Miller DH (1996) Quantification of mri lesion load in multiple sclerosis: a comparison of three computer-assisted techniques. Magn Reson Imaging 14(5):495–505

    Article  Google Scholar 

  8. Cardoso MJ, Sudre CH, Modat M, Ourselin S (2015) Template-based multimodal joint generative model of brain data. In: International conference on information processing in medical imaging, pp 17–29

    Google Scholar 

  9. Ledig C, Heckemann RA, Hammers A, Lopez JC, Newcombe VF, Makropoulos A, Lötjönen J, Menon DK, Rueckert D (2015) Robust whole-brain segmentation: application to traumatic brain injury. Med Image Anal 21(1):40–58

    Article  Google Scholar 

  10. Rekik I, Allassonniére 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):164–178

    Article  Google Scholar 

  11. Hevia-Montiel N, Jiménez-Alaniz JR, Medina-Bańuelos V, Yáñez-Suárez O, Rosso C, Samson Y, Baillet S (2007) Robust nonparametric segmentation of infarct lesion from diffusion-weighted mr images. In: International conference of the IEEE engineering in medicine & biology society, pp 2102–2105

  12. Liu J, Li M, Wang J, Wu F, Liu T, Pan Y (2014) A survey of mri-based brain tumor segmentation methods. Tsinghua Sci Technol 19(6):578–595

    Article  MathSciNet  Google Scholar 

  13. Rajini NH, Bhavani R (2013) Computer aided detection of ischemic stroke using segmentation and texture features. Measurement 46(6):1865–1874

    Article  Google Scholar 

  14. Griffis JC, Allendorfer JB, Szaflarski JP (2016) Voxel-based Gaussian naïve Bayes classification of ischemic stroke lesions in individual t1-weighted MRI scans. J Neurosci Methods 257:97–108

    Article  Google Scholar 

  15. Chen L, Bentley P, Rueckert D (2017) Fully automatic acute ischemic lesion segmentation in dwi using convolutional neural networks. Neuroimage Clin 15:633–643

    Article  Google Scholar 

  16. 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 Imaging 37(9):2149–2160

    Article  Google Scholar 

  17. Liu Z, Cao C, Ding S, Han T, Wu H, Liu S (2018) Towards clinical diagnosis: automated stroke lesion segmentation on multimodal mr image using convolutional neural network, arXiv preprint arXiv:1803.05848, pp 1–20

  18. Havaei M, Dutil F, Pal C, Larochelle H, Jodoin PM (2015) A convolutional neural network approach to brain tumor segmentation. In: International Workshop on Brainlesion: Glioma, multiple sclerosis, stroke and traumatic brain injuries, pp 195–208

    Chapter  Google Scholar 

  19. Kamnitsas K, Ledig C, Newcombe VF, Simpson JP, Kane AD, Menon DK, Rueckert D, Glocker B (2016) Efficient multi-scale 3d cnn with fully connected crf for accurate brain lesion segmentation. Med Image Anal 36:61–78

    Article  Google Scholar 

  20. Forbes F, Doyle S, Garcia-Lorenzo D, Barillot C, Dojat M (2010) Adaptive weighted fusion of multiple mr sequences for brain lesion segmentation. In: IEEE international conference on biomedical imaging, pp 69–72

  21. Seghier ML, Ramlackhansingh A, Crinion J, Leff AP, Price CJ (2008) Lesion identification using unified segmentation-normalisation models and fuzzy clustering. Neuroimage 41(4):1253–1266

    Article  Google Scholar 

  22. James JR, Yoder KK, Osuntokun O, Kalnin A, Bruno A, Morris ED (2006) A supervised method for calculating perfusion/diffusion mismatch volume in acute ischemic stroke. Comput Biol Med 36(11):1268–1287

    Article  Google Scholar 

  23. 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

    Article  Google Scholar 

  24. Maier O, Menze BH, von der Gablentz J, Häni L, Heinrich MP, Liebrand M, Winzeck S, Basit A, Bentley P, Chen L (2017) Isles 2015-a public evaluation benchmark for ischemic stroke lesion segmentation from multispectral mri. Med Image Anal 35:250–269

    Article  Google Scholar 

  25. Bauer S, Nolte LP, Reyes M (2012) Skull-stripping for tumor-bearing brain images, arXiv preprint arXiv:1204.0357, 2012

  26. Beumer D, Rozeman AD, Nijeholt GJL, Brouwer PA, Jenniskens SFM, Algra A, Boiten J, Schonewille W, Oostenbrugge RJV, Dippel DWJ (2016) The effect of age on outcome after intra-arterial treatment in acute ischemic stroke: a mr clean pretrial study. BMC Neurol 16(1):1–7

    Article  Google Scholar 

  27. González RG, Schaefer PW, Buonanno FS, Schwamm LH, Budzik RF, Rordorf G, Wang B, Sorensen AG, Koroshetz WJ (1999) Diffusion-weighted mr imaging: diagnostic accuracy in patients imaged within 6 hours of stroke symptom onset. Radiology 210(1):155–162

    Article  Google Scholar 

  28. Moseley M, Kucharczyk J, Mintorovitch J, Cohen Y, Kurhanewicz J, Derugin N, Asgari H, Norman D (1990) Diffusion-weighted mr imaging of acute stroke: correlation with t2-weighted and magnetic susceptibility-enhanced mr imaging in cats. Am J Neuroradiol 11(3):423–429

    Google Scholar 

  29. Moseley M, Cohen Y, Mintorovitch J, Chileuitt L, Shimizu H, Kucharczyk J, Wendland M, Weinstein P (1990) Early detection of regional cerebral ischemia in cats: comparison of diffusion-and t2-weighted mri and spectroscopy. Magn Reson Med 14(2):330–346

    Article  Google Scholar 

  30. Sorensen AG, Copen WA, Ostergaard L, Buonanno FS, Gonzalez RG, Rordorf G, Rosen BR, Schwamm LH, Weisskoff RM, Koroshetz WJ (1999) Hyperacute stroke: simultaneous measurement of relative cerebral blood volume, relative cerebral blood flow, and mean tissue transit time. Radiology 210(2):519–527

    Article  Google Scholar 

  31. Collins DL, Neelin P, Peters TM, Evans AC (1994) Automatic 3d intersubject registration of mr volumetric data in standardized talairach space. J Comput Assist Tomogr 18(2):192–205

    Article  Google Scholar 

  32. 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, p 167

  33. Moeskops P, Viergever MA, Mendrik AM, de Vries LS, Benders MJ, Išgum I (2016) Automatic segmentation of mr brain images with a convolutional neural network. IEEE Trans Med Imaging 35(5):1252–1261

    Article  Google Scholar 

  34. Bauer S, Wagner M, Seiler A, Hattingen E, Deichmann R, Nóth U, Singer OC (2014) Quantitative t2’-mapping in acute ischemic stroke. Stroke 45(11):3280–3286

    Article  Google Scholar 

  35. Mohammadi-Nejad AR, Hossein-Zadeh GA, Soltanian-Zadeh H (2017) Structured and sparse canonical correlation analysis as a brain-wide multi-modal data fusion approach. IEEE Trans Med Imaging 36(7):1438–1448

    Article  Google Scholar 

  36. Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) Imagenet: a large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition, pp 248–255

  37. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542(7639):115–118

    Article  Google Scholar 

  38. Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: delving deep into convolutional nets. arXiv:1405.3531

  39. Dosovitskiy A, Fischer P, Springenberg J, Riedmiller M, Brox T (2016) Discriminative unsupervised feature learning with exemplar convolutional neural networks. IEEE Trans Pattern Anal Mach Intell 38(9):1734–1747

    Article  Google Scholar 

  40. Litjens G, Sánchez CI, Timofeeva N, Hermsen M, Nagtegaal I, Kovacs I, Hulsbergen-Van De Kaa C, Bult P, Van Ginneken B, Van Der Laak J (2016) Deep learning as a tool for increased accuracy and efficiency of histopathological diagnosis. Sci Rep 6:26286

    Article  Google Scholar 

  41. Pereira S, Pinto A, Alves V, Silva CA (2016) Brain tumor segmentation using convolutional neural networks in mri images. IEEE Trans Med Imaging 35(5):1240–1251

    Article  Google Scholar 

  42. He K, Sun J (2015) Convolutional neural networks at constrained time cost. In: IEEE conference on computer vision and pattern recognition, pp 5353–5360

  43. Srivastava RK, Greff K, Schmidhuber J (2015) Highway networks, arXiv preprint arXiv:1505.00387

  44. Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: International conference on international conference on machine learning, pp 807–814

  45. Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: International conference on medical image computing and computer-assisted intervention, pp 234–241

    Google Scholar 

  46. He K, Zhang X, Ren S, Sun J (2016) Identity mappings in deep residual networks. In: European conference on computer vision, pp 630–645

    Chapter  Google Scholar 

  47. LeCun Y, Boser B, Denker JS, Henderson D, Howard RE, Hubbard W, Jackel LD (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541–551

    Article  Google Scholar 

  48. Milletari F, Navab N, Ahmadi S (2016) V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: Fourth international conference on 3D Vision, pp 565–571

  49. Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: IEEE conference on computer vision and pattern recognition, pp 3431–3440

  50. Drozdzal M, Vorontsov E, Chartrand G, Kadoury S, Pal C (2016) The importance of skip connections in biomedical image segmentation. In: Deep learning and data labeling for medical applications, pp 179–187

    Chapter  Google Scholar 

  51. Drozdzal M, Chartrand G, Vorontsov E, Shakeri M, Di LJ, Tang A, Romero A, Bengio Y, Pal C, Kadoury S (2017) Learning normalized inputs for iterative estimation in medical image segmentation. Med Image Anal 44:1–13

    Article  Google Scholar 

  52. Dice LR (1945) Measures of the amount of ecologic association between species. J Ecol 26(3):297–302

    Article  Google Scholar 

  53. Huttenlocher DP, Klanderman GA, Rucklidge WA (1993) Comparing images using the Hausdorff distance. IEEE Trans Pattern Anal Mach Intell 15(9):850–863

    Article  Google Scholar 

  54. Saad NM, Abu-Bakar S, Muda S, Mokji M, Salahuddin L (2011) Brain lesion segmentation of diffusion-weighted mri using gray level co-occurrence matrix. In: IEEE international conference on imaging systems and techniques, pp 284–289

  55. Benjamini Y (1988) Opening the box of a boxplot. Am Stat 42(4):257–262

    Google Scholar 

  56. He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: IEEE international conference on computer vision, pp 1026–1034

  57. Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. Int Conf Mach Learn 30:3

    Google Scholar 

  58. Zhu X, Zhang S, Hu R, Zhu Y, Song J (2017) Local and global structure preservation for robust unsupervised spectral feature selection. IEEE Trans Knowl Data Eng 30(3):517–529

    Article  Google Scholar 

  59. Liu J, Li M, Lan W, Wu F-X, Pan Y, Wang J (2018) Classification of alzheimer’s disease using whole brain hierarchical network. IEEE/ACM Trans Comput Biol Bioinf 15(2):624–632

    Article  Google Scholar 

  60. Zhu Y, Zhu X, Kim M, Yan J, Kaufer D, Wu G (2018) Dynamic hyper-graph inference framework for computer assisted diagnosis of neurodegenerative diseases. IEEE Trans Med Imaging. https://doi.org/10.1109/TMI.2018.2868086

    Article  Google Scholar 

  61. Kong Y, Gao J, Xu Y, Pan Y, Wang J, Liu J (2019) Classification of autism spectrum disorder by combining brain connectivity and deep neural network classifier. Neurocomputing 324(9):63–68

    Article  Google Scholar 

  62. Liu J, Wang X, Zhang X, Pan Y, Wang X, Wang J (2018) Mmm: classification of schizophrenia using multi-modality multi-atlas feature representation and multi-kernel learning. Multimed Tools Appl 77(22):29651–29667

    Article  Google Scholar 

Download references

Acknowledgements

The authors would like to thank Chunlei Liu, an Associate Professor in the Department of Electrical Engineering and Computer Sciences, UC Berkeley, for his valuable comments on this study. The work described in this paper was supported by the National Natural Science Foundation of China under Grant Nos. 61772557, 61772552, 61622213, 61728211; the 111 Project (No.B18059); the Hunan Provincial Science and Technology Program (2018WK4001).

Author information

Authors and Affiliations

  1. School of Computer Science and Engineering, Central South University, Changsha, 410083, People’s Republic of China

    Liangliang Liu, Fuhao Zhang & Jianxin Wang

  2. School of Pingdingshan University, Pingdingshan, 467000, People’s Republic of China

    Liangliang Liu

  3. Department of Pathology, Pingdingshan First People’s Hospital, Pingdingshan, 467000, People’s Republic of China

    Shaowu Chen

  4. Division of Biomedical Engineering and Department of Mechanical Engineering, University of Saskatchewan, Saskatoon, SK, S7N5A9, Canada

    Fang-Xiang Wu

  5. Department of Computer Science, Georgia State University, Atlanta, GA, 30302, USA

    Yi Pan

Authors
  1. Liangliang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shaowu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fuhao Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Fang-Xiang Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yi Pan
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jianxin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jianxin Wang.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interest regarding the publication of this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, L., Chen, S., Zhang, F. et al. Deep convolutional neural network for automatically segmenting acute ischemic stroke lesion in multi-modality MRI. Neural Comput & Applic 32, 6545–6558 (2020). https://doi.org/10.1007/s00521-019-04096-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-019-04096-x

Keywords

Search

Navigation