Automated deep-neural-network surveillance of cranial images for acute neurologic events
Automated deep-neural-network surveillance of cranial images for acute neurologic events
复制标题
DOI：
10.1038/s41591-018-0147-y
复制
发表时间：
2018-09-01
期刊：
影响因子：
82.9
通讯作者：
Oermann, Eric K.
中科院分区：
文献类型：
--
作者：
Titano, Joseph J.;Badgeley, Marcus;Oermann, Eric K.
快速诊断和治疗急性神经系统疾病，如中风、出血和脑积水，对于获得积极的结果和保护神经功能至关重要-“时间就是大脑”（1-5）。虽然这些疾病通常可以通过症状识别，但其诊断的关键手段是快速成像（6-10）。颅脑成像中急性神经系统事件的计算机辅助监测有可能对放射学工作流程进行分类，从而缩短治疗时间并改善结局。大量的临床工作集中在计算机辅助诊断（CAD），而在体积图像分析的技术工作主要集中在分割。3D卷积神经网络（3D-CNN）主要用于3D建模和光探测与测距（LiDAR）数据的监督分类（11-15）。在这里，我们展示了一个3D-CNN架构，该架构执行弱监督分类，以筛选头部CT图像中的急性神经系统事件。从包括37，236个头部CT的临床放射学数据集中自动学习特征，并使用半监督自然语言处理（NLP）框架进行注释（16）。我们通过在模拟临床环境中进行的随机、双盲、前瞻性试验，证明了我们的方法对放射学工作流程进行分诊的有效性，并将诊断时间从几分钟缩短到几秒钟。
Rapid diagnosis and treatment of acute neurological illnesses such as stroke, hemorrhage, and hydrocephalus are critical to achieving positive outcomes and preserving neurologic function-'time is brain'(1-5). Although these disorders are often recognizable by their symptoms, the critical means of their diagnosis is rapid imaging(6-10). Computer-aided surveillance of acute neurologic events in cranial imaging has the potential to triage radiology workflow, thus decreasing time to treatment and improving outcomes. Substantial clinical work has focused on computer-assisted diagnosis (CAD), whereas technical work in volumetric image analysis has focused primarily on segmentation. 3D convolutional neural networks (3D-CNNs) have primarily been used for supervised classification on 3D modeling and light detection and ranging (LiDAR) data(11-15). Here, we demonstrate a 3D-CNN architecture that performs weakly supervised classification to screen head CT images for acute neurologic events. Features were automatically learned from a clinical radiology dataset comprising 37,236 head CTs and were annotated with a semisupervised natural-language processing (NLP) framework(16). We demonstrate the effectiveness of our approach to triage radiology workflow and accelerate the time to diagnosis from minutes to seconds through a randomized, double-blinded, prospective trial in a simulated clinical environment.