Detecting cerebral microbleeds with transfer learning

  • Jin Hong
  • Hong Cheng
  • Yu-Dong ZhangEmail author
  • Jie LiuEmail author
Special Issue paper
Part of the following topical collections:
  1. Special Issue on Deep Learning Methods for Biomedical Information Analysis


Cerebral microbleeds (CMBs) are small perivascular hemosiderin deposits leaked from cerebral small vessels in normal (or near normal) tissue. It is important to detect CMBs accurately and reliably for diagnosing and researching some cerebrovascular diseases and cognitive dysfunctions. In the last decade, several approaches based on traditional machine learning and classical convolutional neural network (CNN) were developed for detecting CMBs semi-automatically and automatically. In recent years, numerous advanced variants of CNN with deeper structure have been developed for image recognition, showing better performances comparing with classical CNN. In particular, ResNet proposed recently won the championships on many important image recognition benchmarks because of its extremely deep representations. In view of this, we proposed a method based on ResNet-50 for exploring the possibility of further improving the accuracy of CMBs detection in this study. Due to our small CMB samples size, transfer learning was employed. Based on the transfer learning of ResNet-50, we achieved a high performance with a sensitivity of 95.71 ± 1.044%, a specificity of 99.21 ± 0.076%, and an accuracy of 97.46 ± 0.524% in format of average ± standard deviation, which outperformed three state-of-the-art methods.


Cerebral microbleeds detection Convolutional neural network ResNet-50 Transfer learning 



This paper is supported by National Natural Science Foundation of China (41574087), National Key Research and Development Plan (2017YFB1103202), Henan Key Research and Development Project (182102310629), and Natural Science Foundation of China (61602250).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Greenberg, S.M., et al.: Cerebral microbleeds: a guide to detection and interpretation. Lancet Neurol. 8(2), 165–174 (2009)CrossRefGoogle Scholar
  2. 2.
    Wu, Y., Chen, T.: An up-to-date review on cerebral microbleeds. J. Stroke Cerebrovasc. Dis. 25(6), 1301–1306 (2016)CrossRefGoogle Scholar
  3. 3.
    Roob, G., et al.: MRI evidence of past cerebral microbleeds in a healthy elderly population. Neurology 52(5), 991 (1999)CrossRefGoogle Scholar
  4. 4.
    Cordonnier, C., Wardlaw, J., Al-Shahi Salman, R.: Spontaneous brain microbleeds: systematic review, subgroup analyses and standards for study design and reporting. Brain 130(8), 1988–2003 (2007)CrossRefGoogle Scholar
  5. 5.
    Kato, H.: Silent cerebral microbleeds on T2*-weighted MRI; correlation with stroke type, stroke recurrence, and leukoaraiosis. Stroke 33, 1536–1540 (2002)CrossRefGoogle Scholar
  6. 6.
    Fan, Y.H., et al.: Cerebral microbleeds and white matter changes in patients hospitalized with lacunar infarcts. J. Neurol. 251(5), 537–541 (2004)CrossRefGoogle Scholar
  7. 7.
    Prins, N.D.: Cerebral small-vessel disease and decline in information processing speed, executive function and memory. Brain 128, 2034–2041 (2005)CrossRefGoogle Scholar
  8. 8.
    Werring, D.J., et al.: Cognitive dysfunction in patients with cerebral microbleeds on T2*-weighted gradient-echo MRI. Brain 127(10), 2265–2275 (2004)CrossRefGoogle Scholar
  9. 9.
    Haacke, E.M., et al.: Susceptibility-weighted imaging: technical aspects and clinical applications, part 1. AJNR Am. J. Neuroradiol. 30(1), 19 (2009)MathSciNetCrossRefGoogle Scholar
  10. 10.
    Gregoire, S.M., et al.: The microbleed anatomical rating scale (MARS): reliability of a tool to map brain microbleeds. Neurology 73(21), 1759–1766 (2009)CrossRefGoogle Scholar
  11. 11.
    Seghier, M.L., et al.: Microbleed detection using automated segmentation (MIDAS): a new method applicable to standard clinical MR images. PLoS ONE 6, e17547 (2011). CrossRefGoogle Scholar
  12. 12.
    Barnes, S., Haacke, E.M., Ayaz, M.: Semiautomated detection of cerebral microbleeds in magnetic resonance images. Magn. Reson. Imaging 29(6), 844–852 (2011)CrossRefGoogle Scholar
  13. 13.
    Kuijf, H.J., et al.: Efficient detection of cerebral microbleeds on 7.0 T MR images using the radial symmetry transform. Neuroimage 59(3), 2266–2273 (2012)CrossRefGoogle Scholar
  14. 14.
    Bian, W., et al.: Computer-aided detection of radiation-induced cerebral microbleeds on susceptibility-weighted MR images. Neuroimage Clin. 2(1), 282–290 (2013)CrossRefGoogle Scholar
  15. 15.
    Roy, S., et al.: Cerebral microbleed segmentation from susceptibility weighted images. In: SPIE Medical Imaging. SPIE (2015)Google Scholar
  16. 16.
    Fazlollahi, A., et al.: Computer-aided detection of cerebral microbleeds in susceptibility-weighted imaging. Comput. Med. Imaging Graph. 46, 269–276 (2015)CrossRefGoogle Scholar
  17. 17.
    Heuvel, T.L.A.V.D., et al.: Automated detection of cerebral microbleeds in patients with traumatic brain injury. Neuroimage Clin. 12(C), 241–251 (2016)CrossRefGoogle Scholar
  18. 18.
    Hou, X.X., et al.: Voxelwise detection of cerebral microbleed in CADASIL patients by leaky rectified linear unit and early stopping. Multimed. Tools Appl. 77(17), 21825–21845 (2018)CrossRefGoogle Scholar
  19. 19.
    Hou, X.X., et al.: Seven-layer deep neural network based on sparse autoencoder for voxelwise detection of cerebral microbleed. Multimed. Tools Appl. 77(9), 10521–10538 (2018)CrossRefGoogle Scholar
  20. 20.
    Jiang, Y.Y., et al.: Cerebral micro-bleed detection based on the convolution neural network with rank based average pooling. IEEE Access 5, 16576–16583 (2017)CrossRefGoogle Scholar
  21. 21.
    Cheng, H., et al.: Classification of cerebral microbleeds based on fully-optimized convolutional neural network. Multimed. Tools Appl. (2018).
  22. 22.
    Dou, Q., et al.: Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks. IEEE Trans. Med. Imaging 35(5), 1182–1195 (2016)CrossRefGoogle Scholar
  23. 23.
    Zeiler, M.D., Fergus, R.. Visualizing and understanding convolutional networks. In: Computer Vision—ECCV 2014. Springer, ChamGoogle Scholar
  24. 24.
    Han, D., Liu, Q., Fan, W.: A new image classification method using CNN transfer learning and web data augmentation. Expert Syst. Appl. 95, 43–56 (2018)CrossRefGoogle Scholar
  25. 25.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
  26. 26.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems (2012)Google Scholar
  27. 27.
    Szegedy, C., et al.: Going deeper with convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  28. 28.
    He, K., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2016)Google Scholar
  29. 29.
    Hong, J.: Classification of cerebral microbleeds based on fully-optimized convolutional neural network. Multimed. Tools Appl. (2018). Google Scholar
  30. 30.
    Zhou, X.-X., Sheng, H.: Combination of stationary wavelet transform and kernel support vector machines for pathological brain detection. Simulation 92(9), 827–837 (2016)CrossRefGoogle Scholar
  31. 31.
    Pan, H., Zhang, C., Tian, Y.: RGB-D image-based detection of stairs, pedestrian crosswalks and traffic signs. J. Vis. Commun. Image Represent. 25(2), 263–272 (2014)CrossRefGoogle Scholar
  32. 32.
    Atangana, A.: Application of stationary wavelet entropy in pathological brain detection. Multimed. Tools Appl. 77(3), 3701–3714 (2018)CrossRefGoogle Scholar
  33. 33.
    Lu, S., Lu, Z.: A pathological brain detection system based on kernel based ELM. Multimed. Tools Appl. 77(3), 3715–3728 (2018)CrossRefGoogle Scholar
  34. 34.
    Chen, Y., Chen, X.-Q.: Sensorineural hearing loss detection via discrete wavelet transform and principal component analysis combined with generalized eigenvalue proximal support vector machine and Tikhonov regularization. Multimed. Tools Appl. 77(3), 3775–3793 (2016)CrossRefGoogle Scholar
  35. 35.
    Wu, X.: Tea category identification based on optimal wavelet entropy and weighted k-nearest neighbors algorithm. Multimed. Tools Appl. 77(3), 3745–3759 (2018)CrossRefGoogle Scholar
  36. 36.
    Chen, Y.: Wavelet energy entropy and linear regression classifier for detecting abnormal breasts. Multimed. Tools Appl. 77(3), 3813–3832 (2018)CrossRefGoogle Scholar
  37. 37.
    Zhan, T.M., Chen, Y.: Multiple sclerosis detection based on biorthogonal wavelet transform, RBF kernel principal component analysis, and logistic regression. IEEE Access 4, 7567–7576 (2016)MathSciNetCrossRefGoogle Scholar
  38. 38.
    Chen, Y.: A feature-free 30-disease pathological brain detection system by linear regression classifier. CNS Neurol. Disord. Drug Targets 16(1), 5–10 (2017)CrossRefGoogle Scholar
  39. 39.
    Sui, Y.X.: Classification of Alzheimer’s disease based on eight-layer convolutional neural network with leaky rectified linear unit and max pooling. J. Med. Syst. 42(5), 85 (2018)CrossRefGoogle Scholar
  40. 40.
    Wang, S., Chen, Y.: Fruit category classification via an eight-layer convolutional neural network with parametric rectified linear unit and dropout technique. Multimed. Tools Appl. (2018). Google Scholar
  41. 41.
    Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (2011)Google Scholar
  42. 42.
    Boureau, Y.L., Ponce, J., Lecun, Y.: A theoretical analysis of feature pooling in visual recognition. In: ICML 2010—Proceedings, 27th International Conference on Machine Learning (2010)Google Scholar
  43. 43.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (2010)Google Scholar
  44. 44.
    Bengio, Y., Simard, P., Frasconi, P.: Learning long-term dependencies with gradient descent is difficult. IEEE Trans. Neural Netw. 5(2), 157–166 (1994)CrossRefGoogle Scholar
  45. 45.
    LeCun, Y., et al.: Efficient backprop in neural networks: tricks of the trade. Lect. Notes Comput. Sci. 1524(98), 111 (1998)Google Scholar
  46. 46.
    He, K., et al.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision (2015)Google Scholar
  47. 47.
    Saxe, A.M., McClelland, J.L., Ganguli, S.: Exact solutions to the nonlinear dynamics of learning in deep linear neural networks. arXiv preprint arXiv:1312.6120 (2013)
  48. 48.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
  49. 49.
    He, K., Sun, J.: Convolutional neural networks at constrained time cost. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)Google Scholar
  50. 50.
    Srivastava, R.K., Greff, K., Schmidhuber, J.: Highway networks. arXiv preprint arXiv:1505.00387 (2015)

Copyright information

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

Authors and Affiliations

  1. 1.School of Earth Sciences and EngineeringSun Yat-Sen UniversityGuangzhouPeople’s Republic of China
  2. 2.School of Computer Science and TechnologyHenan Polytechnic UniversityJiaozuoPeople’s Republic of China
  3. 3.Department of NeurologyFirst Affiliated Hospital of Nanjing Medical UniversityNanjingPeople’s Republic of China
  4. 4.Department of InformaticsUniversity of LeicesterLeicesterUK

Personalised recommendations