Deep learning models for COVID-19 chest x-ray classification: Preventing shortcut learning using feature disentanglement.
Deep learning models for COVID-19 chest x-ray classification: Preventing shortcut learning using feature disentanglement.
复制标题
DOI：
10.1371/journal.pone.0274098
复制
发表时间：
2022
期刊：
影响因子：
3.7
通讯作者：
中科院分区：
文献类型：
--
作者：
为了应对COVID-19全球大流行，最近的研究提议创建基于深度学习的模型，在各种临床任务中使用胸部x光片（cxr）来帮助管理危机。然而，来自COVID-19+患者的现有CXR数据集的规模相对较小，研究人员经常汇集来自多个来源的CXR数据，例如，在不同的临床场景下，在不同的患者人群中使用不同的x光机。在这些数据集上训练的深度学习模型已经被证明会过度拟合错误的特征，而不是在一种被称为捷径学习的现象中学习肺部特征。我们建议在训练过程中加入特征解缠。该技术迫使模型从图像中识别肺部特征，并惩罚它们学习可以区分图像来自的原始数据集的特征。我们发现用这种方法训练的模型在未知数据上确实有更好的泛化性能；在最好的情况下，我们发现它将保留数据的AUC提高了0.13。我们进一步发现，这优于掩盖CXR的非肺部分和执行直方图均衡化，这两种方法都是最近提出的消除CXR数据集中偏差的方法。
In response to the COVID-19 global pandemic, recent research has proposed creating deep learning based models that use chest radiographs (CXRs) in a variety of clinical tasks to help manage the crisis. However, the size of existing datasets of CXRs from COVID-19+ patients are relatively small, and researchers often pool CXR data from multiple sources, for example, using different x-ray machines in various patient populations under different clinical scenarios. Deep learning models trained on such datasets have been shown to overfit to erroneous features instead of learning pulmonary characteristics in a phenomenon known as shortcut learning. We propose adding feature disentanglement to the training process. This technique forces the models to identify pulmonary features from the images and penalizes them for learning features that can discriminate between the original datasets that the images come from. We find that models trained in this way indeed have better generalization performance on unseen data; in the best case we found that it improved AUC by 0.13 on held out data. We further find that this outperforms masking out non-lung parts of the CXRs and performing histogram equalization, both of which are recently proposed methods for removing biases in CXR datasets.
登录
查看更多内容
影响因子：
3.9
作者：
Yoo, Seung Hoon;Geng, Hui;Lee, Ho
通讯作者：
Lee, Ho
影响因子：
6.1
作者：
Pereira, Rodolfo M.;Bertolini, Diego;Costa, Yandre M. G.
通讯作者：
Costa, Yandre M. G.
影响因子：
4.4
作者：
Apostolopoulos, Ioannis D.;Mpesiana, Tzani A.
通讯作者：
Mpesiana, Tzani A.
影响因子：
7.7
作者：
Ozturk, Tulin;Talo, Muhammed;Acharya, U. Rajendra
通讯作者：
Acharya, U. Rajendra