一种用于优化放射科医生参与人工智能图像数据管理的用户界面。
A User Interface for Optimizing Radiologist Engagement in Image Data Curation for Artificial Intelligence.
作者信息
Demirer Mutlu, Candemir Sema, Bigelow Matthew T, Yu Sarah M, Gupta Vikash, Prevedello Luciano M, White Richard D, Yu Joseph S, Grimmer Rainer, Wels Michael, Wimmer Andreas, Halabi Abdul H, Ihsani Alvin, O'Donnell Thomas P, Erdal Barbaros S
机构信息
Department of Radiology, Laboratory for Augmented Intelligence in Imaging-Division of Medical Imaging Informatics, Ohio State University College of Medicine, OSU Wexner Medical Center, 395 W 12th Ave, Suite 452, Columbus, OH 43210 (M.D., S.C., M.T.B., S.M.Y., V.G., L.M.P., R.D.W., J.S.Y., B.S.E.); Siemens Healthineers, Erlangen, Germany (R.G., M.W., A.W.); NVIDIA, Santa Clara, Calif (A.H.H., A.I.); and Siemens Healthineers, Malvern, Pa (T.P.O.).
出版信息
Radiol Artif Intell. 2019 Nov 27;1(6):e180095. doi: 10.1148/ryai.2019180095. eCollection 2019 Nov.
PURPOSE
To delineate image data curation needs and describe a locally designed graphical user interface (GUI) to aid radiologists in image annotation for artificial intelligence (AI) applications in medical imaging.
MATERIALS AND METHODS
GUI components support image analysis toolboxes, picture archiving and communication system integration, third-party applications, processing of scripting languages, and integration of deep learning libraries. For clinical AI applications, GUI components included two-dimensional segmentation and classification; three-dimensional segmentation and quantification; and three-dimensional segmentation, quantification, and classification. To assess radiologist engagement and performance efficiency associated with GUI-related capabilities, image annotation rate (studies per day) and speed (minutes per case) were evaluated in two clinical scenarios of varying complexity: hip fracture detection and coronary atherosclerotic plaque demarcation and stenosis grading.
RESULTS
For hip fracture, 1050 radiographs were annotated over 7 days (150 studies per day; median speed: 10 seconds per study [interquartile range, 3-21 seconds per study]). A total of 294 coronary CT angiographic studies with 1843 arteries and branches were annotated for atherosclerotic plaque over 23 days (15.2 studies [80.1 vessels] per day; median speed: 6.08 minutes per study [interquartile range, 2.8-10.6 minutes per study] and 73 seconds per vessel [interquartile range, 20.9-155 seconds per vessel]).
CONCLUSION
GUI-component compatibility with common image analysis tools facilitates radiologist engagement in image data curation, including image annotation, supporting AI application development and evolution for medical imaging. When complemented by other GUI elements, a continuous integrated workflow supporting formation of an agile deep neural network life cycle results.Supplemental material is available for this article.© RSNA, 2019.
目的
明确图像数据管理需求，并描述一种本地设计的图形用户界面（GUI），以协助放射科医生对医学成像中的人工智能（AI）应用进行图像标注。
材料与方法
GUI组件支持图像分析工具箱、图像存档与通信系统集成、第三方应用程序、脚本语言处理以及深度学习库集成。对于临床AI应用，GUI组件包括二维分割与分类；三维分割与量化；以及三维分割、量化与分类。为评估与GUI相关功能相关的放射科医生参与度和性能效率，在两种不同复杂程度的临床场景中评估了图像标注率（每天的病例数）和速度（每例的分钟数）：髋部骨折检测以及冠状动脉粥样硬化斑块划定和狭窄分级。
结果
对于髋部骨折，在7天内标注了1050张X线片（每天150例；中位速度：每例10秒[四分位间距，每例3 - 21秒]）。在23天内，对总共294例冠状动脉CT血管造影研究中的1843条动脉和分支进行了动脉粥样硬化斑块标注（每天15.2例[80.1条血管]；中位速度：每例6.08分钟[四分位间距，每例2.8 - 10.6分钟]以及每条血管73秒[四分位间距，每条血管20.9 - 155秒]）。
结论
GUI组件与常见图像分析工具的兼容性有助于放射科医生参与图像数据管理，包括图像标注，支持医学成像AI应用的开发和演进。当与其他GUI元素互补时，可形成支持敏捷深度神经网络生命周期形成的连续集成工作流程。本文有补充材料。©RSNA，2019。
Zotero 插件