We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Toward Automatic Detection of Radiation-Induced Cerebral Microbleeds Using a 3D Deep Residual Network.
- Authors
Chen, Yicheng; Villanueva-Meyer, Javier E.; Morrison, Melanie A.; Lupo, Janine M.
- 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.
- Subjects
ALGORITHMS; CEREBRAL hemorrhage; STATISTICAL correlation; DATABASE management; DIAGNOSTIC errors; DIAGNOSTIC imaging; MAGNETIC resonance imaging; COMPUTERS in medicine; NEURORADIOLOGY; RADIATION injuries; THREE-dimensional imaging; ACCURACY; DESCRIPTIVE statistics
- Publication
Journal of Digital Imaging, 2019, Vol 32, Issue 5, p766
- ISSN
0897-1889
- Publication type
Article
- DOI
10.1007/s10278-018-0146-z