• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>SPIE Medical Imaging Conference >The Utility of Deep Learning: Evaluation of a Convolutional Neural Network for Detection of Intracranial Bleeds on Non-Contrast Head Computed Tomography Studies
【24h】

The Utility of Deep Learning: Evaluation of a Convolutional Neural Network for Detection of Intracranial Bleeds on Non-Contrast Head Computed Tomography Studies

机译：深度学习的效用：评价卷积神经网络，用于检测非对比头计算断层扫描研究的颅内出血

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

While rapid detection of intracranial hemorrhage (ICH) on computed tomography (CT) is a critical step in assessingpatients with acute neurological symptoms in the emergency setting, prioritizing scans for radiologic interpretation bythe acuity of imaging findings remains a challenge and can lead to delays in diagnosis at centers with heavy imagingvolumes and limited staff resources. Deep learning has shown promise as a technique in aiding physicians in performingthis task accurately and expeditiously and may be especially useful in a resource-constrained context. Our groupevaluated the performance of a convolutional neural network (CNN) model developed by Aidoc (Tel Aviv, Israel). Thismodel is one of the first artificial intelligence devices to receive FDA clearance for enabling radiologists to triagepatients after scan acquisition. The algorithm was tested on 7112 non-contrast head CTs acquired during 2016–2017from a two, large urban academic and trauma centers. Ground truth labels were assigned to the test data per PACS queryand prior reports by expert neuroradiologists. No scans from these two hospitals had been used during the algorithmtraining process and Aidoc staff were at all times blinded to the ground truth labels. Model output was reviewed by threeradiologists and manual error analysis performed on discordant findings. Specificity was 99%, sensitivity was 95%, andoverall accuracy was 98%.In summary, we report promising results of a scalable and clinically pragmatic deep learning model tested on a large setof real-world data from high-volume medical centers. This model holds promise for assisting clinicians in theidentification and prioritization of exams suspicious for ICH, facilitating both the diagnosis and treatment of an emergentand life-threatening condition.
机译：虽然在计算机断层扫描（CT）上快速检测颅内出血（ICH）是评估中的关键步骤急性神经系统症状在紧急情况下，优先考虑放射学解释的扫描成像结果的敏锐度仍然是一个挑战，可以导致患有重型成像的中心的诊断延迟卷和有限的员工资源。深入学习表明了承诺在执行医生中的技术此任务准确且迅速，并且可能在资源受限的上下文中特别有用。我们的组评估了AIDOC（特拉维夫，以色列）开发的卷积神经网络（CNN）模型的性能。这个模型是第一批人工智能设备之一，以获得FDA清除，以使放射科医生进行分类扫描后患者。在2016-2017期间获得的7112非对比度头CTS测试了该算法从两个，大型城市学术和创伤中心。地面真理标签被分配给每pacs查询的测试数据和专家神经系统学家的报告。在算法期间没有使用这两个医院的扫描培训过程和AIDOC工作人员始终蒙蔽了地面真理标签。模型输出由三次审查在不间断的调查结果上进行了放射科医生和手动误差分析。特异性为99％，敏感性为95％，而且整体准确性为98％。总之，我们报告了在大型套装上测试的可扩展和临床务实的深层学习模型的有希望的结果来自大批量生医疗中心的现实数据。该模型担任协助临床医生的承担考试对ICH可疑的识别和优先级，促进了紧急情况的诊断和治疗和生命威胁的病情。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号