Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

3D Deep Neural Network Segmentation of Intracerebral Hemorrhage: Development and Validation for Clinical Trials

3D Deep Neural Network Segmentation of Intracerebral Hemorrhage: Development and Validation for... Intracranial hemorrhage (ICH) occurs when a blood vessel ruptures in the brain. This leads to significant morbidity and mortality, the likelihood of which is predicated on the size of the bleeding event. X-ray computed tomography (CT) scans allow clinicians and researchers to qualitatively and quantitatively diagnose hemorrhagic stroke, guide interventions and determine inclusion criteria of patients in clinical trials. There is no currently available open source, validated tool to quickly segment hemorrhage. Using an automated pipeline and 2D and 3D deep neural networks, we show that we can quickly and accurately estimate ICH volume with high agreement with time-consuming manual segmentation. The training and validation datasets include significant heterogeneity in terms of pathology, such as the presence of intraventricular (IVH) or subdural hemorrhages (SDH) as well as variable image acquisition parameters. We show that deep neural networks trained with an appropriate anatomic context in the network receptive field, can effectively perform ICH segmentation, but those without enough context will overestimate hemorrhage along the skull and around calcifications in the ventricular system. We trained with all data from a multi-center phase II study (n = 112) achieving a best mean and median Dice coefficient of 0.914 and 0.919, a volume correlation of 0.979 and an average volume difference of 1.7 ml and root mean squared error of 4.7 ml in 500 out-of-sample scans from the corresponding multi-center phase III study. 3D networks with appropriate anatomic context outperformed both 2D and random forest models. Our results suggest that deep neural network models, when carefully developed can be incorporated into the workflow of an ICH clinical trial series to quickly and accurately segment ICH, estimate total hemorrhage volume and minimize segmentation failures. The model, weights and scripts for deployment are located at https://github.com/msharrock/deepbleed. This is the first publicly available neural network model for segmentation of ICH, the only model evaluated with the presence of both IVH and SDH and the only model validated in the workflow of a series of clinical trials. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neuroinformatics Springer Journals

3D Deep Neural Network Segmentation of Intracerebral Hemorrhage: Development and Validation for Clinical Trials

Loading next page...
 
/lp/springer-journals/3d-deep-neural-network-segmentation-of-intracerebral-hemorrhage-CGm7K906Su
Publisher
Springer Journals
Copyright
Copyright © Springer Science+Business Media, LLC, part of Springer Nature 2020
ISSN
1539-2791
eISSN
1559-0089
DOI
10.1007/s12021-020-09493-5
Publisher site
See Article on Publisher Site

Abstract

Intracranial hemorrhage (ICH) occurs when a blood vessel ruptures in the brain. This leads to significant morbidity and mortality, the likelihood of which is predicated on the size of the bleeding event. X-ray computed tomography (CT) scans allow clinicians and researchers to qualitatively and quantitatively diagnose hemorrhagic stroke, guide interventions and determine inclusion criteria of patients in clinical trials. There is no currently available open source, validated tool to quickly segment hemorrhage. Using an automated pipeline and 2D and 3D deep neural networks, we show that we can quickly and accurately estimate ICH volume with high agreement with time-consuming manual segmentation. The training and validation datasets include significant heterogeneity in terms of pathology, such as the presence of intraventricular (IVH) or subdural hemorrhages (SDH) as well as variable image acquisition parameters. We show that deep neural networks trained with an appropriate anatomic context in the network receptive field, can effectively perform ICH segmentation, but those without enough context will overestimate hemorrhage along the skull and around calcifications in the ventricular system. We trained with all data from a multi-center phase II study (n = 112) achieving a best mean and median Dice coefficient of 0.914 and 0.919, a volume correlation of 0.979 and an average volume difference of 1.7 ml and root mean squared error of 4.7 ml in 500 out-of-sample scans from the corresponding multi-center phase III study. 3D networks with appropriate anatomic context outperformed both 2D and random forest models. Our results suggest that deep neural network models, when carefully developed can be incorporated into the workflow of an ICH clinical trial series to quickly and accurately segment ICH, estimate total hemorrhage volume and minimize segmentation failures. The model, weights and scripts for deployment are located at https://github.com/msharrock/deepbleed. This is the first publicly available neural network model for segmentation of ICH, the only model evaluated with the presence of both IVH and SDH and the only model validated in the workflow of a series of clinical trials.

Journal

NeuroinformaticsSpringer Journals

Published: Sep 27, 2020

Keywords: Clinical trials; Intracerebral hemorrhage; Deep neural networks

References