Using CNN with Bayesian optimization to identify cerebral micro-bleeds


This article studies the problem of detecting cerebral micro-bleeds (CMBs) using a convolutional neural network (CNN). Cerebral micro-bleeds (CMBs) are increasingly recognized neuroimaging findings, occurring with cerebrovascular diseases, dementia, and normal aging. Naturally enough, it becomes necessary to detect CMBs in the early stages of life. The focus of this article is to infuse new techniques like Bayesian optimization to find the optimum set of hyper-parameters efficiently, making even the simplest of CNN architectures perform well on the problem. Experimentally, we observe our CNN (five layers, i.e., two convolution, two pooling, and one fully connected) achieves accuracy = 98.97%, sensitivity = 99.66%, specificity = 98.14%, and precision = 98.54% on the test set (hold-out validation) when calculated over an average of ten runs. The proposed model outperformed state-of-the-art methods.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11


  1. 1.

    Yates, P., Sirisriro, R., Villemagne, V., Farquharson, S., Masters, C., Rowe, C., et al.: Cerebral microhemorrhage and brain \(\beta \)-amyloid in aging and Alzheimer disease. Neurology 77(1), 48–54 (2011)

    Article  Google Scholar 

  2. 2.

    Fiehler, J.: Cerebral microbleeds: old leaks and new haemorrhages. Int. J. Stroke 1(3), 122–130 (2006)

    Article  Google Scholar 

  3. 3.

    Nakata-Kudo, Y., Mizuno, T., Yamada, K., et al.: Microbleeds in Alzheimer disease are more related to cerebral amyloid angiopathy than cerebrovascular disease. Dement. Geriatr. Cogn. Disord. 22(1), 8–14 (2006)

    Article  Google Scholar 

  4. 4.

    Martinez-Ramirez, S., Greenberg, S.M., Viswanathan, A.: Cerebral microbleeds: overview and implications in cognitive impairment. Alzheimer’s Res. Ther. 6, 33 (2014).

    Article  Google Scholar 

  5. 5.

    Noorbakhsh-Sabet, N., Pulakanti, V.C., Zand, R.: Uncommon causes of cerebral microbleeds. J. Stroke Cerebrovasc. Dis. 26, 2043–2049 (2017).

    Article  Google Scholar 

  6. 6.

    Roberts, T.P., Mikulis, D.: Neuro MR: principles. J. Magn. Reson. Imaging 26, 823–837 (2007).

    Article  Google Scholar 

  7. 7.

    Vernooij, M.W., Ikram, M.A., Wielopolski, P.A., Krestin, G.P., Breteler, M.M., van der Lugt, A.: Cerebral microbleeds: accelerated 3D T2*-weighted GRE MR imaging versus conventional 2D T2*-weighted GRE MR imaging for detection. Radiology 248, 272–277 (2008).

    Article  Google Scholar 

  8. 8.

    Haacke, E.M., Xu, Y., Cheng, Y.C., Reichenbach, J.R.: Susceptibility weighted imaging (SWI). Magn. Reson. Med. 52, 612–618 (2004).

    Article  Google Scholar 

  9. 9.

    Naka, H., Nomura, E., Wakabayashi, S., Kajikawa, H., Kohriyama, T., Mimori, Y., Nakamura, S., Matsumoto, M.: Frequency of asymptomatic microbleeds on T2*-weighted MR images of patients with recurrent stroke: association with combination of stroke subtypes and leukoaraiosis. AJNR Am. J. Neuroradiol. 25, 714–719 (2004)

    Google Scholar 

  10. 10.

    Tsushima, Y., Aoki, J., Endo, K.: Brain microhemorrhages detected on T2*-weighted gradient-echo MR images. AJNR Am. J. Neuroradiol. 24, 88–96 (2003)

    Google Scholar 

  11. 11.

    Lee, S.H., Bae, H.J., Kwon, S.J., Kim, H., Kim, Y.H., Yoon, B.W., Roh, J.K.: Cerebral microbleeds are regionally associated with intracerebral hemorrhage. Neurology 62, 72–76 (2004).

    Article  Google Scholar 

  12. 12.

    Cordonnier, C., van der Flier, W.M., Sluimer, J.D., Leys, D., Barkhof, F., Scheltens, P.: Prevalence and severity of microbleeds in a memory clinic setting. Neurology 66, 1356–1360 (2006).

    Article  Google Scholar 

  13. 13.

    Ateeq, T., Majeed, M.N., Anwar, S.M., et al.: Ensemble-classifiers-assisted detection of cerebral microbleeds in brain MRI. Comput. Electr. Eng. 69, 768–781 (2018)

    Article  Google Scholar 

  14. 14.

    Cordonnier, C., Salman, R., Wardlaw, J.: Spontaneous brain microbleeds: systematic review, subgroup analyses and standards for study design and reporting. Brain 130(8), 1988–2003 (2007)

    Article  Google Scholar 

  15. 15.

    Barnes, S.R.S., Haacke, E.M., Ayaz, M., Boikov, A.S., Kirsch, W., Kido, D.: Semiautomated detection of cerebral microbleeds in magnetic resonance images. Magn. Reson. Imaging 29(6), 844–852 (2011)

    Article  Google Scholar 

  16. 16.

    Bian, W., Hess, C.P., Chang, S.M., Nelson, S.J., Lupo, J.M.: Computer-aided detection of radiation-induced cerebral microbleeds on susceptibility-weighted MR images. NeuroImage Clin. 2, 282–290 (2013)

    Article  Google Scholar 

  17. 17.

    Fazlollahi, A., Meriaudeau, F., Villemagne, V.L.: Efficient machine learning framework for computer-aided detection of cerebral microbleeds using the Radon transform. Paper presented at, et al.: In: IEEE 11th International Symposium on Biomedical Imaging (ISBI); 2014. Beijing, China (2014)

  18. 18.

    Fazlollahi, A., Meriaudeau, F., Giancardo, L., et al.: Computer-aided detection of cerebral microbleeds in susceptibility-weighted imaging. Comput. Med. Imaging Graph. 46(Part 3), 269–276 (2015)

    Article  Google Scholar 

  19. 19.

    Chen, H., Yu, L., Dou, Q., Shi, L., Mok, V.C., Heng, P.A.: Automatic detection of cerebral microbleeds via deep learning based 3D feature representation. Paper presented at: 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI); New York, NY (2015)

  20. 20.

    Van den Heuvel, T.L.A., van der Eerden, A.W., Manniesing, R., et al.: Automated detection of cerebral microbleeds in patients with traumatic brain injury. NeuroImage Clin. 12, 241–251 (2016)

    Article  Google Scholar 

  21. 21.

    Kaaouana, T., Bertrand, A., Ouamer, F., et al.: Improved cerebral microbleeds detection using theirmagnetic signature on T2*-phase-contrast: a comparison study in a clinical setting. NeuroImage Clin. 15, 274–283 (2017)

    Article  Google Scholar 

  22. 22.

    Wang, Shuihua, Jiang, Yongyan, Hou, Xiaoxia, Cheng, Hong, Sidan, Du: Cerebral micro-bleed detection based on the convolution neural network with rank based average pooling. IEEE Access 5, 16576–16583 (2017)

    Article  Google Scholar 

  23. 23.

    Hong, Jin, Zhihai, Lu: Cerebral microbleeds detection via discrete wavelet transform and back propagation neural network. Adv. Soc. Sci. Educ. Hum. Res. 196, 228–232 (2019)

    Google Scholar 

  24. 24.

    Liu, J., et al.: Detecting cerebral microbleeds with transfer learning. Mach. Vis. Appl. (2019).

    Article  Google Scholar 

  25. 25.

    Tang C., et al.: Cerebral micro-bleeding detection based on densely connected neural network. Front. Neurosci. 2019, 13, Article ID: 422 (2019)

  26. 26.

    Kingma, Diederik P., Ba, Jimmy: Adam: A Method for Stochastic Optimization. In: 3rd International Conference for Learning Representations, San Diego, (2015). arXiv:1412.6980v9

  27. 27.

    Zhang, Y-D., Hou, X-X., Lv, YD., Chen, H., Zhang, Y., Wang, SH.: Sparse Autoencoder based deep neural network for voxelwise detection of cerebral microbleed. In: 22nd International Conference on Parallel and Distributed Systems: Wuhan, pp. 1229–1232. IEEE, China (2016)

  28. 28.

    Zhang, Y.-D., Zhang, Y., Hou, X.-X., Chen, H., Wang, S.H.: Seven-layer deep neural network based on sparse autoencoder for voxelwise detection of cerebral microbleed. Multimed. Tools Appl. 77(9), 10521–10538 (2018)

    Article  Google Scholar 

  29. 29.

    Lu, Siyuan, Lu, Zhihai, Hou, Xiaoxia, Cheng, Hong, Wang, Shuihua: Detection of cerebral microbleeding based on deep convolutional neural network. In: 14th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP): Chengdu, pp. 93–96. IEEE, China (2017)

  30. 30.

    Chen, Y., et al.: Cerebral micro-bleeding identification based on nine-layer convolutional neural network with stochastic pooling. Concurr. Comput. Pract. Exp. (2019).

    Article  Google Scholar 

  31. 31.

    Al-Qurishi, M., Rahman, S.M.M., Alamri, A., et al.: SybilTrap: a graph-based semi-supervised Sybil defense scheme for online social networks. Concurr. Comput. Pract. Exp. 30(5), e4276 (2018)

    Article  Google Scholar 

Download references


This work was supported by Natural Science Foundation of China (61602250), Natural Science Foundation of Jiangsu Province (BK20150983), National Key Research and Development Plan (2017YFB1103202), Henan Key Research and Development Project (182102310629), Royal Society International Exchanges Cost Share Award UK (RP202G0230), Medical Research Council Confidence in Concept (MRC CIC) Award UK (MC_PC_17171), and Hope Foundation for Cancer Research UK (RM60G0680).

Author information



Corresponding author

Correspondence to Yu-Dong Zhang.

Additional information

Publisher's Note

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

Basic Research Program of Jiangsu Province (BK20150983); National Key Research and Development Plan (2017YFB1103202); Henan Key Research and Development Project (182102310629); Royal Society International Exchanges Cost Share Award, UK (RP202G0230); Medical Research Council Confidence in Concept (MRC-CIC) Award; Medical Research Council Confidence in Concept Award, UK (MC_PC_17171); Hope Foundation for Cancer Research, UK (RM60G0680). Fundamental Research Funds for the Central Universities (CDLS-2020-03) and Key Laboratory of Child Development and Learning Science (Southeast University), Ministry of Education.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Doke, P., Shrivastava, D., Pan, C. et al. Using CNN with Bayesian optimization to identify cerebral micro-bleeds. Machine Vision and Applications 31, 36 (2020).

Download citation


  • Cerebral micro-bleeding
  • CNN
  • Convolution filters
  • ReLU
  • Softmax
  • Max pooling
  • Batch normalization
  • Bayesian optimization
  • Gaussian process regression
  • Acquisition function
  • Image augmentation