RSNA儿童骨龄机器学习挑战赛
该挑战赛由北美放射学会(RSNA)发起,旨在利用机器学习技术,基于整理好的儿童手部X线摄影数据集准确判定骨骼年龄,以平均绝对距离(MAD,月)为主要评价指标。共有14 236张手部X线摄影图像(训练集12 611张、验证集1 425张、测试集200张)供注册参赛者使用,260个个人或团队注册,48名不同用户在训练、验证和测试阶段共上传105份提交。表现最好的五个结果按MAD分别为4.2、4.4、4.4、4.5和4.5个月。
要点
- 挑战赛数据集含14 236张儿童手部X线摄影图像,其中训练集12 611张、验证集1 425张、测试集200张。
- 主要评价指标为平均绝对距离(MAD,月),即模型估计值与参考标准骨龄之差的绝对值的均值。
- 最佳五个结果的MAD分别为4.2、4.4、4.4、4.5和4.5个月。
核心结论
- RSNA儿童骨龄机器学习挑战赛表明,以协调一致的方式解决医学影像问题是能够成功实施的;未来的机器学习挑战赛将促进协作以及机器学习工具与方法的开发,这些工具与方法可能提高诊断准确性和患者照护。
研究设计与样本
- 由北美放射学会(RSNA)组织的机器学习挑战赛,使用整理好的儿童手部X线摄影数据集;数据集合计14 236张手部X线摄影图像(训练集12 611张、验证集1 425张、测试集200张),参考标准为骨龄。
诊断标准与关键数值
- 主要评价指标为平均绝对距离(MAD,月),计算为模型估计值与参考标准骨龄之差的绝对值的均值;最佳五个结果的MAD分别为4.2、4.4、4.4、4.5和4.5个月。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
Purpose The Radiological Society of North America (RSNA) Pediatric Bone Age Machine Learning Challenge was created to show an application of machine learning (ML) and artificial intelligence (AI) in medical imaging, promote collaboration to catalyze AI model creation, and identify innovators in medical imaging. Materials and Methods The goal of this challenge was to solicit individuals and teams to create an algorithm or model using ML techniques that would accurately determine skeletal age in a curated data set of pediatric hand radiographs. The primary evaluation measure was the mean absolute distance (MAD) in months, which was calculated as the mean of the absolute values of the difference between the model estimates and those of the reference standard, bone age. Results A data set consisting of 14 236 hand radiographs (12 611 training set, 1425 validation set, 200 test set) was made available to registered challenge participants. A total of 260 individuals or teams registered on the Challenge website. A total of 105 submissions were uploaded from 48 unique users during the training, validation, and test phases. Almost all methods used deep neural network techniques based on one or more convolutional neural networks (CNNs). The best five results based on MAD were 4.2, 4.4, 4.4, 4.5, and 4.5 months, respectively. Conclusion The RSNA Pediatric Bone Age Machine Learning Challenge showed how a coordinated approach to solving a medical imaging problem can be successfully conducted. Future ML challenges will catalyze collaboration and development of ML tools and methods that can potentially improve diagnostic accuracy and patient care. © RSNA, 2018 Online supplemental material is available for this article. See also the editorial by Siegel in this issue.
引用
- Halabi SS, Prevedello LM, Kalpathy-Cramer J, et al. The RSNA Pediatric Bone Age Machine Learning Challenge. Radiology. 2018. PMID: 30480490. doi:10.1148/radiol.2018180736
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。