文献速递胸部技术与安全DR

使用较少数据的胸部X线摄影模型简化迁移学习

Simplified Transfer Learning for Chest Radiography Models Using Less Data.
PubMed 文献 · Radiology · 2022-07-19

研究利用监督对比学习从821544张胸部X线片生成胸部X线网络,作为10个预测任务的起点,在五个数据集共684955张胸片上测试三种模型开发设置。多数任务中,与从非医学数据集迁移学习相比,监督对比学习将标签需求降低最多688倍,并在匹配数据集大小时改善AUC;仅用45张胸片训练的小型非线性模型在外部验证中分类微生物学确诊结核的AUC为0.95(非劣于放射科医生表现)。

要点

  • 监督对比学习可从大规模胸片生成网络,作为下游任务起点,减少标签需求最多688倍。
  • 仅45张胸片训练的小型非线性模型分类微生物学确诊结核的AUC为0.95,非劣于放射科医生。
  • 528张胸片训练的小型非线性模型预测重症COVID-19结局的AUC为0.75。

核心结论

  • 监督对比学习使模型仅用45张图像即在多个临床任务中达到与先进深度学习模型相当的性能,是小数据集预测建模及患者人群变化时预测结局的有前景方法。

研究设计与样本

  • 利用来自印度和美国的821544张胸片通过监督对比学习生成胸部X线网络,作为10个预测任务(如气腔模糊、骨折、结核和COVID-19结局)的起点,使用来自印度、美国和中国五个数据集共684955张胸片,测试三种模型开发设置(线性分类器、非线性分类器和微调整个网络)及从8到85的不同数据集大小。

诊断标准与关键数值

  • 极端低数据方案下,仅用45张胸片训练小型非线性模型,在外部验证中分类微生物学确诊结核的AUC为0.95,非劣于放射科医生表现。
  • 更适中的数据方案下,仅用528张胸片训练小型非线性模型预测重症COVID-19结局的AUC为0.75。
  • 多数任务中,与从非医学数据集迁移学习相比,监督对比学习在匹配数据集大小时改善AUC,并将标签需求降低最多688倍。

临床应用与阅片要点

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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

Background Developing deep learning models for radiology requires large data sets and substantial computational resources. Data set size limitations can be further exacerbated by distribution shifts, such as rapid changes in patient populations and standard of care during the COVID-19 pandemic. A common partial mitigation is transfer learning by pretraining a "generic network" on a large nonmedical data set and then fine-tuning on a task-specific radiology data set. Purpose To reduce data set size requirements for chest radiography deep learning models by using an advanced machine learning approach (supervised contrastive [SupCon] learning) to generate chest radiography networks. Materials and Methods SupCon helped generate chest radiography networks from 821 544 chest radiographs from India and the United States. The chest radiography networks were used as a starting point for further machine learning model development for 10 prediction tasks (eg, airspace opacity, fracture, tuberculosis, and COVID-19 outcomes) by using five data sets comprising 684 955 chest radiographs from India, the United States, and China. Three model development setups were tested (linear classifier, nonlinear classifier, and fine-tuning the full network) with different data set sizes from eight to 85. Results Across a majority of tasks, compared with transfer learning from a nonmedical data set, SupCon reduced label requirements up to 688-fold and improved the area under the receiver operating characteristic curve (AUC) at matching data set sizes. At the extreme low-data regimen, training small nonlinear models by using only 45 chest radiographs yielded an AUC of 0.95 (noninferior to radiologist performance) in classifying microbiology-confirmed tuberculosis in external validation. At a more moderate data regimen, training small nonlinear models by using only 528 chest radiographs yielded an AUC of 0.75 in predicting severe COVID-19 outcomes. Conclusion Supervised contrastive learning enabled performance comparable to state-of-the-art deep learning models in multiple clinical tasks by using as few as 45 images and is a promising method for predictive modeling with use of small data sets and for predicting outcomes in shifting patient populations. © RSNA, 2022 Online supplemental material is available for this article.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Sellergren, Chen, Nabulsi, et al. Simplified Transfer Learning for Chest Radiography Models Using Less Data. Radiology. 2022. PMID: 35852426. doi:10.1148/radiol.212482

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。