Abstract
我们旨在开发一种在胸部X线片上检测10个常见异常(DLAD-10)的深度学习算法,并评估其对诊断准确性,报告及工作流程效果的影响。
Dlad-10培训,由108 053患者使用Reset34的神经网络培训,使用Reset34的神经网络具有病变特异性通道,用于10个常见的放射学异常(气胸,纵隔扩展,气孔,结节/质量,固结,胸腔积液,线性的Atelectasis,纤维化,钙化和心脏肿大)。对于外部验证,将DLAD-10的性能在同日CT确认的数据集(正常:异常,53:147)和开源数据集(填充;正常:异常,339:334)进行了相同的三位放射科医生。在急诊部门调整到现实世界疾病患病率的另一个数据集上进行了单独的模拟读数测试,包括四个临界,52次紧急和146个非迫切案件。六位放射科医生参与了模拟阅读会话,没有DLAD-10。
DLAD-10展出的是as under the receiver-operating characteristic curves (AUROCs) of 0.895–1.00 in the CT-confirmed dataset and 0.913–0.997 in the PadChest dataset. DLAD-10 correctly classified significantly more critical abnormalities (95.0% [57/60]) than pooled radiologists (84.4% [152/180]; p=0.01). In simulated reading tests for emergency department patients, pooled readers detected significantly more critical (70.8% [17/24]与29.2%[7/24];p = 0.006)和紧急(82.7%[258/312]与78.2% [244/312]; p=0.04) abnormalities when aided by DLAD-10. DLAD-10 assistance shortened the mean time-to-report critical and urgent radiographs (640.5±466.3与3.3.71.0±1352.5 s and 1840.3±1141.1与2127.1±1468.2分别;p值<0.01)并降低平均解释时间(20.5±22.8与23.。5±23.7 s; p<0.001).
Dlad-10表现出优异的性能,提高放射科医师的性能,并缩短了关键和紧急情况的报告时间。
Footnotes
This manuscript has recently been accepted for publication in theEuropean Respiratory Journal。它在汇款和排版的抄本之前在此处发布于其已接受的表单。在这些生产过程完成后,作者已批准所产生的证据,这篇文章将转向最新问题ERJonline. Please open or download the PDF to view this article.
利益冲突:NAM博士报告由科学和信息通信技术部资助的韩国国家研究基金会(MSIT)资助的国家研究基金会(Grant Numbers:NRF-2018R1A5A1060031),来自首尔国立大学医院研究基金的补助金(授予号码:03-2019-0190),在研究期间。
Conflict of interest: Dr. Kim reports other from Employee of Lunit Incorporated, during the conduct of the study.
Conflict of interest: Dr. Park reports grants from National Research Foundation of Korea (NRF) grant funded by the Ministry of Science and ICT (MSIT) (grant number: NRF-2018R1A5A1060031), grants from Seoul National University Hospital Research Fund (grant number: 03-2019-0190), during the conduct of the study.
Conflict of interest: Dr. Hwang has nothing to disclose.
Conflict of interest: Dr. Lee has nothing to disclose.
利益冲突:洪博士没有披露。
Conflict of interest: Dr. Goo has nothing to disclose.
Conflict of interest: Dr. Park reports grants from National Research Foundation of Korea (NRF) grant funded by the Ministry of Science and ICT (MSIT) (grant number: NRF-2018R1A5A1060031), grants from Seoul National University Hospital Research Fund (grant number: 03-2019-0190), during the conduct of the study.
- ReceivedAugust 7, 2020.
- 公认11月3日,2020年11月3日。
- 版权所有©ers 2020