arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2002.02497eess.IVcs.LGq-bio.QMstat.ML
收藏

X射线自动预测中跨域综合的局限性

On the limits of cross-domain generalization in automated X-ray prediction

Mila(米拉研究所);Université de Montréal(蒙特利尔大学)

Joseph Paul Cohen, Mohammad Hashir, Rupert Brooks, Hadrien Bertrand

摘要:

这项大规模研究的重点是量化X射线诊断预测任务在多个不同数据集上的推广。我们提出的证据表明,泛化的问题不是由于图像的变化,而是标签的变化。我们研究了跨域性能,模型之间的协议,和模型表示。我们发现有趣的性能和协议之间的差异,既实现了良好的性能模型不同意在他们的预测,以及模型,同意但实现较差的性能。我们还通过规则化网络将多个数据集上的任务分组在一起并观察任务之间的变化来测试概念相似性。所有代码都可以在线获得,数据也可以公开获得:https://github.com/mlmed/torchxrayvision

英文摘要:

This large scale study focuses on quantifying what X-rays diagnostic prediction tasks generalize well across multiple different datasets. We present evidence that the issue of generalization is not due to a shift in the images but instead a shift in the labels. We study the cross-domain performance, agreement between models, and model representations. We find interesting discrepancies between performance and agreement where models which both achieve good performance disagree in their predictions as well as models which agree yet achieve poor performance. We also test for concept similarity by regularizing a network to group tasks across multiple datasets together and observe variation across the tasks. All code is made available online and data is publicly available: https://github.com/mlmed/torchxrayvision

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑