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.

当大脑中的血管破裂时会发生颅内出血 (ICH)。这导致显着的发病率和死亡率，其可能性取决于出血事件的大小。X 射线计算机断层扫描 (CT) 扫描使临床医生和研究人员能够定性和定量地诊断出血性中风、指导干预措施并确定临床试验中患者的纳入标准。目前没有可用的开源、经过验证的工具来快速分割出血。使用自动化管道和 2D 和 3D 深度神经网络，我们表明我们可以快速准确地估计 ICH 体积，并与耗时的手动分割高度一致。训练和验证数据集包括病理学方面的显着异质性，例如是否存在脑室内 (IVH) 或硬膜下出血 (SDH) 以及可变的图像采集参数。我们表明，在网络感受野中用适当的解剖学背景训练的深度神经网络可以有效地执行 ICH 分割，但那些没有足够背景的人会高估沿颅骨和心室系统钙化周围的出血。我们使用来自多中心 II 期研究的所有数据进行训练（n = 112) 在 500 次样本外扫描中，从相应的多样本扫描中获得了 0.914 和 0.919 的最佳平均和中值 Dice 系数、0.979 的体积相关性和 1.7 毫升的平均体积差和 4.7 毫升的均方根误差。中心 III 期研究。具有适当解剖背景的 3D 网络优于 2D 和随机森林模型。我们的结果表明，经过精心开发的深度神经网络模型可以整合到 ICH 临床试验系列的工作流程中，以快速准确地分割 ICH，估计总出血量并最大限度地减少分割失败。用于部署的模型、权重和脚本位于 https://github.com/msharrock/deepbleed。这是第一个公开可用的用于 ICH 分割的神经网络模型，