Automated Critical Test Findings Identification and Online Notification System Using Artificial Intelligence in Imaging
Automated Critical Test Findings Identification and Online Notification System Using Artificial Intelligence in Imaging
复制标题
DOI：
10.1148/radiol.2017162664
复制
发表时间：
2017-12-01
期刊：
影响因子：
19.7
通讯作者：
White, Richard D.
中科院分区：
文献类型：
--
作者：
Prevedello, Luciano M.;Erdal, Barbaros S.;White, Richard D.
目的：评估人工智能（AI）工具使用深度学习算法在非造影剂增强头部计算机断层扫描（CT）检查中检测出血、占位效应或脑积水（HMH）的性能，并确定疑似急性梗死（SAI）检测的算法性能。材料和方法：这项符合HIPAA的回顾性研究在机构审查委员会批准后完成。获得了非对比增强头部CT检查的训练和验证数据集，其中包括100次HMH检查，22次SAI检查和124次非关键发现，得到2583张代表性图像。使用卷积神经网络（深度学习）处理检查，使用两种不同的窗口和水平配置（脑窗和中风窗）。AI算法性能在一个单独的数据集上进行了测试，该数据集包含50个具有HMH结果的检查，15个具有SAI结果的检查，以及35个具有非关键结果的检查。（45/50）的灵敏度（95%置信区间[CI]：78%，97%）和85%（68/80）的特异性（95% CI：76%，92%），接受者工作特征曲线（AUC）下的面积为0.91，脑窗。对于SAI，最佳性能是卒中窗口显示62%（13/21）的灵敏度（95% CI：38%，82%）和96%（27/28）的特异性（95% CI：82%，100%），AUC为0.81。结论：使用深度学习的AI有望在非对比增强头部CT中检测关键发现。需要专用算法来检测SAI。与HMH的检测相比，SAI的检测显示出较低的灵敏度，但显示出合理的性能。研究结果支持在受控和前瞻性临床环境中对该算法进行进一步研究，以确定其是否可以独立筛选非对比增强头部CT检查并通知解释放射科医生关键发现。(C)RSNA，2017
Purpose: To evaluate the performance of an artificial intelligence (AI) tool using a deep learning algorithm for detecting hemorrhage, mass effect, or hydrocephalus (HMH) at non-contrast material-enhanced head computed tomographic (CT) examinations and to determine algorithm performance for detection of suspected acute infarct (SAI).Materials and Methods: This HIPAA-compliant retrospective study was completed after institutional review board approval. A training and validation dataset of noncontrast-enhanced head CT examinations that comprised 100 examinations of HMH, 22 of SAI, and 124 of noncritical findings was obtained resulting in 2583 representative images. Examinations were processed by using a convolutional neural network (deep learning) using two different window and level configurations (brain window and stroke window). AI algorithm performance was tested on a separate dataset containing 50 examinations with HMH findings, 15 with SAI findings, and 35 with noncritical findings.Results: Final algorithm performance for HMH showed 90% (45 of 50) sensitivity (95% confidence interval [CI]: 78%, 97%) and 85% (68 of 80) specificity (95% CI: 76%, 92%), with area under the receiver operating characteristic curve (AUC) of 0.91 with the brain window. For SAI, the best performance was achieved with the stroke window showing 62% (13 of 21) sensitivity (95% CI: 38%, 82%) and 96% (27 of 28) specificity (95% CI: 82%, 100%), with AUC of 0.81.Conclusion: AI using deep learning demonstrates promise for detecting critical findings at noncontrast-enhanced head CT. A dedicated algorithm was required to detect SAI. Detection of SAI showed lower sensitivity in comparison to detection of HMH, but showed reasonable performance. Findings support further investigation of the algorithm in a controlled and prospective clinical setting to determine whether it can independently screen noncontrast-enhanced head CT examinations and notify the interpreting radiologist of critical findings. (C) RSNA, 2017