Abstract
Cerebral microbleeds (CMBs) are important imaging and diagnostic biomarkers for cerebrovascular diseases and cognitive dysfunctions. Reliable detection of the location and amount of CMBs in brain tissue is crucial for the diagnosis, prevention and treatment of related diseases, where traditional Convolutional Neural Network (CNN) has been applied but may fail to achieve high enough detection accuracy. To alleviate this issue, we utilize 3D Fully Convolutional Networks (FCN) and 3D AlexNet to establish a cascade coarse-to-fine detection manner. Specifically, CMBs candidates are first screened out using 3D FCN, followed by 3D AlexNet which extracts the spatial features of CMBs and distinguishes the false positive samples from candidate regions. Experimental results show that the proposed method can realize precise detection of CMBs in magnetic resonance images (MRI) by improving detection sensitivity and reducing false positive samples.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Dou, Q., Chen, H., Yu, L., et al.: Automatic cerebral microbleeds detection from MR images via Independent Subspace Analysis based hierarchical features. In: Proceedings of Annual International IEEE Engineering in Medicine Biology Society, pp. 7933–7936 (2015)
Fazlollahi, A., Meriaudeau, F., Villemagne, V.L., et al.: Efficient machine learning framework for computer-aided detection of cerebral microbleeds using the Radon transform. In: 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI). IEEE (2014)
Kuijf, H.J., Bresser, J.D., Geerlings, M.I., et al.: Efficient detection of cerebral microbleeds on 7.0 T MR images using the radial symmetry transform. Neuroimage 59(3), 2266–2273 (2012)
Ghafary, B., Lijn, F.V.D., Poels, M., et al.: A computer aided detection system for cerebral microbleeds in brain MRI. In: Proceedings/IEEE International Symposium on Biomedical Imaging: from nano to macro. IEEE International Symposium on Biomedical Imaging (2012)
Barnes, S.R.S., Haacke, E.M., Ayaz, M., et al.: Semiautomated detection of cerebral microbleeds in magnetic resonance images. Magn. Reson. Imaging 29(6), 844–852 (2011)
Chen, H., Dou, Q., Ni, D., et al.: Automatic fetal ultrasound standard plane detection using knowledge transferred recurrent neural networks (2015)
Dou, Qi., Chen, Hao., et al.: Automatic detection of cerebral microbleeds from MR images via 3D convolutional neural networks. IEEE Trans. Med. Imaging 3(5), 1182–1195 (2016)
Li, Xian, He, Jie: Application of 3D fully convolutional network in spine segmentation. Electron Technol. 31(11), 75–79 (2018). (in Chinese)
Wang, K.: Research on medical image segmentation method based on deep learning. University of Science and Technology of China (2018). (in Chinese)
Li, Y.: CT image recognition of lung cancer based on three-dimensional convolutional neural network model. Shanxi Normal University (2018). (in Chinese)
Chen, H., Yu, L., Dou, Q., et al.: Automatic detection of cerebral microbleeds via deep learning based on 3D feature representation. In: 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI). IEEE (2015)
Zhu, Wei., Jingyi, Qu, Renbiao, Wu: Image classification algorithm of straight-through convolutional neural network combined with batch normalization. J. Comput. Aided Des. Graph. 29(09), 1650–1657 (2017). (in Chinese)
Hillis, S.L., Chakraborty, D.P., Orton, C.G.: ROC or FROC? It depends on the research question. Med. Phys. 44(5), 1603 (2017)
Acknowledgements
This work is partially supported by National Natural Science Foundation of China (61972187, 61772254), Fujian Provincial Leading Project (2017H0030, 2019H0025), Government Guiding Regional Science and Technology Development (2019L3009), and Natural Science Foundation of Fujian Province (2017J01768 and 2019J01756).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhao, M., Jin, C., Jin, L., Teng, S., Li, Z. (2020). Cerebral Microbleeds Detection Based on 3D Convolutional Neural Network. In: Chen, X., Yan, H., Yan, Q., Zhang, X. (eds) Machine Learning for Cyber Security. ML4CS 2020. Lecture Notes in Computer Science(), vol 12486. Springer, Cham. https://doi.org/10.1007/978-3-030-62223-7_14
Download citation
DOI: https://doi.org/10.1007/978-3-030-62223-7_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-62222-0
Online ISBN: 978-3-030-62223-7
eBook Packages: Computer ScienceComputer Science (R0)