Toward Automatic Detection of Radiation-Induced Cerebral Microbleeds Using a 3D Deep Residual Network
- 617 Downloads
Cerebral microbleeds, which are small focal hemorrhages in the brain that are prevalent in many diseases, are gaining increasing attention due to their potential as surrogate markers of disease burden, clinical outcomes, and delayed effects of therapy. Manual detection is laborious and automatic detection and labeling of these lesions is challenging using traditional algorithms. Inspired by recent successes of deep convolutional neural networks in computer vision, we developed a 3D deep residual network that can distinguish true microbleeds from false positive mimics of a previously developed technique based on traditional algorithms. A dataset of 73 patients with radiation-induced cerebral microbleeds scanned at 7 T with susceptibility-weighted imaging was used to train and evaluate our model. With the resulting network, we maintained 95% of the true microbleeds in 12 test patients and the average number of false positives was reduced by 89%, achieving a detection precision of 71.9%, higher than existing published methods. The likelihood score predicted by the network was also evaluated by comparing to a neuroradiologist’s rating, and good correlation was observed.
KeywordsDeep learning Susceptibility-weighted imaging Cerebral microbleeds Convolutional neural networks Automated-detection
This work was supported by the National Institute for Child Health and Human Development of the National Institutes of Health grant R01HD079568 and GE Healthcare.
Compliance with Ethical Standards
Conflict of Interest
The authors declare that they have no conflict of interest with regard to the content of this manuscript.
- 9.van den Heuvel TLA, Ghafoorian M, van der Eerden AW, Goraj BM, Andriessen TMJC, ter Haar Romeny BM, Platel B: Computer aided detection of brain micro-bleeds in traumatic brain injury. In: Medical Imaging 2015: Computer-Aided Diagnosis, Vol. 9414, 2015, p. 94142FGoogle Scholar
- 16.Ioffe S, Szegedy C: Batch normalization: accelerating deep network training by reducing internal covariate shift, arXiv preprint arXiv:1502.03167, 2015Google Scholar
- 21.Dahl GE, Sainath TN, Hinton GE: Improving deep neural networks for LVCSR using rectified linear units and dropout, Acoustics, Speech and Signal Processing (ICASSP), IEEE International Conference on, 2013, p 8609Google Scholar
- 22.F. Chollet and Others, Keras, 2015.Google Scholar
- 23.Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S: Tensorflow: Large-scale machine learning on heterogeneous distributed systems, arXiv preprint arXiv:1603.04467, 2016.Google Scholar
- 24.Kingma DP, Ba J: Adam: a method for stochastic optimization, arXiv preprint arXiv:1412.6980, 2014Google Scholar
- 25.Simonyan K, Zisserman A: Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv:1409.1556, 2014Google Scholar
- 26.Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A: Going deeper with convolutions. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp 1–9Google Scholar