期刊
RADIOLOGY
卷 295, 期 1, 页码 4-15出版社
RADIOLOGICAL SOC NORTH AMERICA
DOI: 10.1148/radiol.2020192224
关键词
-
资金
- Intramural Research Program of the National Institutes of Health (NIH) Clinical Center
- National Library of Medicine of the NIH [R01LM012966]
- Stanford Child Health Research Institute (Stanford NIH-National Center for Advancing Translational Sciences Clinical and Translational Science Awards) [UL1 TR001085]
- National Cancer Institute of the NIH [U01CA142555, 1U01CA190214, 1U01CA187947, 1U01CA242879]
Artificial intelligence (AI) continues to garter substantial interest in medical imaging. The potential applications are vast and include the entirety of the. medical imaging life cycle from image exertion to diagnosis to outcome prediction. The chief obstacles to development and clinical implementation of AI algorithms include availability of sufficiently large, curated, and representative training data that includes expert labeling (eg, annotations). Current supervised AI methods require a curation proem for data to optimally train, validate, and test algorithms. Currently, most and research group industry have limited data access based on small sample sizes from small geographic areas. In addition, die preparation of data is a costly and time-intensive process, the results of which ate algorithms with limited utility and poor generalization. In this article, the authors describe fundamental steps for preparing medical imaging data in AI algorithm development, explain current limitations to data curation, and explore new approaches to address the problem of data availability. (C) RSNA, 2020
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据