对深度学习软件标记为急性颅内出血的头颅CT扫描的分析
在学术医疗中心前瞻性分析Aidoc神经网络软件在非增强头颅CT上标记的急性颅内出血病例,2个月内2011次扫描中373次(18.5%)被标记,275次(72.4%)阳性,总体敏感度88.7%、特异度94.2%、阳性预测值73.7%、阴性预测值97.7%、准确率93.4%;急诊病例准确率96.5%高于住院病例89.4%。
要点
- 软件标记的373例中仅72.4%阳性,阳性预测值73.7%,需人工复核确认。
- 标记病例中62.5%为随访复查,其中95.6%为住院患者。
- 急诊病例检测准确率96.5%,高于住院病例的89.4%。
核心结论
- 深度学习软件对急性颅内出血的检测性能随患者就诊地点不同而变化。
- 被标记病例中相当比例为随访复查,且多数为住院检查。
研究设计与样本
- 前瞻性纳入学术医疗中心非增强头颅CT中Aidoc神经网络软件在神经放射学工作列表上标记为急性颅内出血阳性的病例。
- 2个月入组期间共分析2011次非增强头颅CT扫描,其中373次被标记。
关键影像表现/征象
- 被标记的373例中275例(72.4%)确认为颅内出血阳性。
- 290例(77.7%)为住院病例,75例(20.1%)为创伤/急诊病例,8例(2.1%)为门诊病例。
- 373例中229例(62.5%)为随访复查,其中219例(95.6%)为住院病例。
- 144例新发被标记病例中66例(44.4%)阳性,其中39例(58.2%)为创伤/急诊病例。
诊断标准与关键数值
- 总体敏感度88.7%、特异度94.2%、阳性预测值73.7%、阴性预测值97.7%、准确率93.4%。
- 颅内出血检测准确率急诊病例96.5% vs 住院病例89.4%,急诊病例高于住院病例。
临床应用与阅片要点
- 深度学习软件标记的病例需结合就诊地点和是否为随访复查进行人工判读。
- 软件标记的随访复查病例占比较高,解读时需注意区分新发出血与复查所见。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: To analyze the implementation of deep learning software for the detection and worklist prioritization of acute intracranial hemorrhage on non-contrast head CT (NCCT) in various clinical settings at an academic medical center.
METHODS: Urgent NCCT scans were reviewed by the Aidoc (Tel Aviv, Israel) neural network software. All cases flagged by the software as positive for acute intracranial hemorrhage on the neuroradiology worklist were prospectively included in this assessment. The scans were classified regarding presence and type of hemorrhage, whether these were initial or follow-up scans, and patient visit location, including trauma/emergency, inpatient, and outpatient departments.
RESULTS: During the 2 months of enrollment, 373 NCCT scans were flagged by the Aidoc software for possible intracranial hemorrhage out of 2011 scans analyzed (18.5%). Among the flagged cases, 275 (72.4%) were positive; 290 (77.7%) were inpatient cases, 75 (20.1%) were trauma/emergency cases, and eight (2.1%) were outpatient cases, and 229 of 373 (62.5%) were follow-up cases, of which 219 (95.6%) inpatient cases. Among the 144 new cases flagged for hemorrhage, 66 (44.4%) were positive, of which 39 (58.2%) were trauma/emergency cases. The overall sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 88.7%, 94.2% and 73.7%, 97.7%, and 93.4%, respectively. The accuracy of the intracranial hemorrhage detection was significantly higher for emergency cases than for inpatient cases (96.5% versus 89.4%).
CONCLUSION: This study reveals that the performance of the deep learning software for acute intracranial hemorrhage detection varies depending upon the patient visit location. Furthermore, a substantial portion of flagged cases were follow-up exams, the majority of which were inpatient exams. These findings can help optimize the artificial intelligence-driven clincical workflow.
引用
- Ginat DT. Analysis of head CT scans flagged by deep learning software for acute intracranial hemorrhage. Neuroradiology. 2019. PMID: 31828361. doi:10.1007/s00234-019-02330-w
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。