Autonomous artificial intelligence in pediatric radiology: the use and perception of BoneXpert for bone age assessment.

Autonomous artificial intelligence in pediatric radiology: the use and perception of BoneXpert for bone age assessment.
复制标题

DOI:
10.1007/s00247-022-05295-w
复制
发表时间:
2022-06
影响因子:
2.3
通讯作者:
--
中科院分区:
医学3区
文献类型:
--
作者:

文献摘要

参考文献

被引文献

相似文献

自主人工智能(AI)骨龄评估系统(BoneXpert)被设计用于临床放射实践,作为人工智能替代工具,完全取代放射科医生。本研究的目的是调查该工具如何在临床实践中使用。放射科医生是否更倾向于使用BoneXpert来辅助而不是替代他们自己?节省了多少时间?我们向已经使用该软件的欧洲部门的282名放射科医生发送了一份由8个选择题组成的调查问卷。97名(34%)受访者来自18个国家。他们的回答显示,在安装自动化方法之前,83%(86%)的受访者花了2分钟以上的时间进行骨龄评估;安装后,这一比例降至20(21%)。只有17/97(18%)的受访者使用BoneXpert来完全替代放射科医生;其余的人则在不同程度上用它来协助放射科医生。例如,39/97(40%)从未否决过自动阅读,而9/97(9%)否决了超过5%的自动评分。大多数58/97(60%)的应答者自己检查x线片以排除潜在疾病的特征。BoneXpert显著减少了骨年龄测定的报告时间。然而,放射学分析涉及的不仅仅是确定骨龄。它还涉及异常的识别,因此,放射科医生不能被完全取代。最初为取代放射科医生而开发的人工智能系统可能更适合作为人工智能辅助工具,特别是如果它们尚未被验证能够自主工作,包括在图像超出有效范围时忽略评级的能力。在线版本包含补充材料,可在10.1007/s00247-022-05295-w获得。
The autonomous artificial intelligence (AI) system for bone age rating (BoneXpert) was designed to be used in clinical radiology practice as an AI-replace tool, replacing the radiologist completely. The aim of this study was to investigate how the tool is used in clinical practice. Are radiologists more inclined to use BoneXpert to assist rather than replace themselves, and how much time is saved? We sent a survey consisting of eight multiple-choice questions to 282 radiologists in departments in Europe already using the software. The 97 (34%) respondents came from 18 countries. Their answers revealed that before installing the automated method, 83 (86%) of the respondents took more than 2 min per bone age rating; this fell to 20 (21%) respondents after installation. Only 17/97 (18%) respondents used BoneXpert to completely replace the radiologist; the rest used it to assist radiologists to varying degrees. For instance, 39/97 (40%) never overruled the automated reading, while 9/97 (9%) overruled more than 5% of the automated ratings. The majority 58/97 (60%) of respondents checked the radiographs themselves to exclude features of underlying disease. BoneXpert significantly reduces reporting times for bone age determination. However, radiographic analysis involves more than just determining bone age. It also involves identification of abnormalities, and for this reason, radiologists cannot be completely replaced. AI systems originally developed to replace the radiologist might be more suitable as AI assist tools, particularly if they have not been validated to work autonomously, including the ability to omit ratings when the image is outside the range of validity. The online version contains supplementary material available at 10.1007/s00247-022-05295-w.
DOI: 10.1515/jpem.2011.420
发表时间: 2011-12-01
影响因子: 1.4
作者:
Martin, David D.;Meister, Kathrin;Binder, Gerhard
通讯作者: Binder, Gerhard
DOI: 10.1186/s41747-019-0139-9
发表时间: 2020-01-28
影响因子: 3.8
作者:
Booz, Christian;Yel, Ibrahim;Bodelle, Boris
通讯作者: Bodelle, Boris
DOI: 10.4067/s0370-41062018005000705
发表时间: 2018-10-01
期刊: Revista chilena de pediatría
影响因子: --
作者:
Pose Lepe, Georgette;Villacrés, Fabián;Guiloff, Stefan
通讯作者: Guiloff, Stefan
DOI: 10.1007/s00247-008-1114-4
发表时间: 2009-06-01
影响因子: 2.3
作者:
Martin, David D.;Deusch, Dorothee;Ranke, Michael B.
通讯作者: Ranke, Michael B.
DOI: 10.1016/j.acra.2010.06.007
发表时间: 2010-11-01
期刊: ACADEMIC RADIOLOGY
影响因子: 4.8
作者:
Thodberg, Hans Henrik;Savendahl, Lars
通讯作者: Savendahl, Lars