Paper Info
Title
Toward Automatic Detection of Radiation-Induced Cerebral Microbleeds Using a 3D Deep Residual Network.
Abstract
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.
Year
DOI
Venue
2019
10.1007/s10278-018-0146-z
Journal of digital imaging
Keywords
Field
DocType
Automated-detection,Cerebral microbleeds,Convolutional neural networks,Deep learning,Susceptibility-weighted imaging
Residual,Computer vision,Pattern recognition,Convolutional neural network,Computer science,Correlation,Artificial intelligence,Deep learning,Neuroradiologist,False positive paradox,Susceptibility weighted imaging
Journal
Volume
Issue
ISSN
32.0
5.0
1618-727X
Citations 
PageRank 
References 
1
0.35
8
Authors
4
Name
Order
Citations
PageRank
Yicheng Chen110.35
Javier E Villanueva-Meyer210.69
Melanie A Morrison310.69
Janine M Lupo4355.22