Helmholtz Gemeinschaft


BRAVE-NET: fully automated arterial brain vessel segmentation in patients with cerebrovascular disease

PDF (Preprint) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
PDF (Appendix: Model Card) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Item Type:Preprint
Title:BRAVE-NET: fully automated arterial brain vessel segmentation in patients with cerebrovascular disease
Creators Name:Hilbert, A. and Madai, V.I. and Akay, E.M. and Aydin, O.U. and Behland, J. and Sobesky, J. and Galinovic, I. and Khalil, A.A. and Taha, A.A. and Würfel, J. and Dusek, P. and Niendorf, T. and Fiebach, J.B. and Frey, D. and Livne, M.
Abstract:Introduction Arterial brain vessel assessment is crucial for the diagnostic process in patients with cerebrovascular disease. Noninvasive neuroimaging techniques such as time-of-flight (TOF) magnetic resonance angiography (MRA) imaging are applied in the clinical routine to depict arteries. They are, however, only visually assessed. Fully automated vessel segmentation integrated into the clinical routine could facilitate the time-critical diagnosis of vessel abnormalities and might facilitate the identification of valuable biomarkers for cerebrovascular events. In the present work, we developed and validated a new deep learning model for vessel segmentation, coined BRAVE-NET, on a large aggregated dataset of patients with cerebrovascular diseases. Methods BRAVE-NET is a multiscale 3-D convolutional neural network (CNN) model developed on a dataset of 264 patients from 3 different studies enrolling patients with cerebrovascular diseases. A context path, dually capturing high- and low-resolution volumes, and deep supervision were implemented. The BRAVE-NET model was compared to a baseline Unet model and variants with only context paths and deep supervision, respectively. The models were developed and validated using high-quality manual labels as ground truth. Next to precision and recall, the performance was assessed quantitatively by Dice coefficient (DSC); average Hausdorff distance (AVD); 95-percentile Hausdorff distance (95HD) and via visual qualitative rating. Results The BRAVE-NET performance surpassed the other models for arterial brain vessel segmentation with a DSC = 0.931, AVD = 0.165 and 95HD = 29.153. The BRAVE-NET model was also the most resistant towards false labelings as revealed by the visual analysis. The performance improvement is primarily attributed to the integration of the multiscaling context path into the 3-D Unet and to a lesser extent to the deep supervision architectural component. Discussion We present a new state-of-the-art of arterial brain vessel segmentation tailored to cerebrovascular pathology. We provide an extensive experimental validation of the model using a large aggregated dataset encompassing a large variability of cerebrovascular disease. The framework provides the technological foundation for improving the clinical workflow and can serve as a biomarker extraction tool in cerebrovascular diseases.
Keywords:Artificial Intelligence, Machine Learning, Segmentation, Cerebrovascular Disease, U-Net
Publisher:Cold Spring Harbor Laboratory Press
Article Number:2020.04.08.20057570
Official Publication:https://doi.org/10.1101/2020.04.08.20057570
Related to:
https://edoc.mdc-berlin.de/19400/Final version

Repository Staff Only: item control page


Downloads per month over past year

Open Access
MDC Library