Deep neural network improves fracture detection by clinicians.
Deep neural network improves fracture detection by clinicians.
复制标题
DOI：
10.1073/pnas.1806905115
复制
发表时间：
2018-11-06
影响因子：
11.1
通讯作者：
Potter H
中科院分区：
文献类型：
--
作者：
Lindsey R;Daluiski A;Chopra S;Lachapelle A;Mozer M;Sicular S;Hanel D;Gardner M;Gupta A;Hotchkiss R;Potter H
从历史上看，放射学中的计算机辅助检测（CAD）未能实现诊断准确性的提高，降低了临床医生的灵敏度，并导致不必要的进一步诊断测试。随着CAD深度学习方法的出现，人们对它在医学上的应用感到非常兴奋，但几乎没有证据表明在临床相关应用中提高了诊断准确性。我们训练了一个深度学习模型来检测X光片上的骨折，其诊断准确性与高级亚专业骨科医生相似。我们证明，当急诊医学临床医生提供的训练模型的帮助下，他们的能力，准确地检测骨折显着提高。疑似骨折是患者前往急诊室（ED）的最常见原因之一，X射线成像是临床医生用于评估患者骨折的主要诊断工具。在X光片中遗漏骨折通常会对患者造成严重后果，导致治疗延迟和功能恢复不良。然而，急诊室的X光片通常是由缺乏骨科专业知识的急诊医学临床医生阅读的，误诊的骨折占某些急诊室报告的诊断错误的五分之四以上。在这项工作中，我们开发了一个深度神经网络来检测和定位射线照片中的骨折。我们训练它准确地模仿18名高级亚专科骨科医生的专业知识，让他们注释135，409张X光片。然后，我们与急诊医学临床医生进行了一项对照实验，以评估他们在有和没有深度学习模型的帮助下检测手腕X光片中骨折的能力。临床医生的平均灵敏度为80.8%（95%CI，76.7 - 84.1%），无辅助和91.5%（95%CI，89.3 - 92.9%）辅助，特异性为87.5%（95%CI，85.3 - 89.5%），无辅助和93.9%（95%CI，92.9 - 94.9%）辅助。平均临床医生经历了47.0%（95%CI，37.4 - 53.9%）的误解率相对降低。我们在这项研究中观察到的诊断准确性的显著提高表明，深度学习方法是一种机制，高级医学专家可以通过这种机制将他们的专业知识传授给医学第一线的通才，从而为患者护理提供实质性的改善。
Historically, computer-assisted detection (CAD) in radiology has failed to achieve improvements in diagnostic accuracy, decreasing clinician sensitivity and leading to unnecessary further diagnostic tests. With the advent of deep learning approaches to CAD, there is great excitement about its application to medicine, yet there is little evidence demonstrating improved diagnostic accuracy in clinically-relevant applications. We trained a deep learning model to detect fractures on radiographs with a diagnostic accuracy similar to that of senior subspecialized orthopedic surgeons. We demonstrate that when emergency medicine clinicians are provided with the assistance of the trained model, their ability to accurately detect fractures significantly improves. Suspected fractures are among the most common reasons for patients to visit emergency departments (EDs), and X-ray imaging is the primary diagnostic tool used by clinicians to assess patients for fractures. Missing a fracture in a radiograph often has severe consequences for patients, resulting in delayed treatment and poor recovery of function. Nevertheless, radiographs in emergency settings are often read out of necessity by emergency medicine clinicians who lack subspecialized expertise in orthopedics, and misdiagnosed fractures account for upward of four of every five reported diagnostic errors in certain EDs. In this work, we developed a deep neural network to detect and localize fractures in radiographs. We trained it to accurately emulate the expertise of 18 senior subspecialized orthopedic surgeons by having them annotate 135,409 radiographs. We then ran a controlled experiment with emergency medicine clinicians to evaluate their ability to detect fractures in wrist radiographs with and without the assistance of the deep learning model. The average clinician’s sensitivity was 80.8% (95% CI, 76.7–84.1%) unaided and 91.5% (95% CI, 89.3–92.9%) aided, and specificity was 87.5% (95 CI, 85.3–89.5%) unaided and 93.9% (95% CI, 92.9–94.9%) aided. The average clinician experienced a relative reduction in misinterpretation rate of 47.0% (95% CI, 37.4–53.9%). The significant improvements in diagnostic accuracy that we observed in this study show that deep learning methods are a mechanism by which senior medical specialists can deliver their expertise to generalists on the front lines of medicine, thereby providing substantial improvements to patient care.
登录
查看更多内容
影响因子：
--
作者：
Espinosa, JA;Nolan, TW
通讯作者：
Nolan, TW
影响因子：
19.7
作者：
Whang, Jeremy S.;Baker, Stephen R.;Castro, Alejandro, III
通讯作者：
Castro, Alejandro, III
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S
影响因子：
6.2
作者：
Lufkin, KC;Smith, SW;Brunette, DD
通讯作者：
Brunette, DD
影响因子：
19.7
作者：
Doyle, AJ;Le Fevre, J;Anderson, GD
通讯作者：
Anderson, GD