论文标题
我们可以为胸部X射线采用自我监督的预处理吗？
Can we Adopt Self-supervised Pretraining for Chest X-Rays?
论文作者
论文摘要
胸部X光片（或胸部X射线，CXR）是一种流行的医学成像方式，全世界的放射科医生使用，用于诊断心脏或肺部状况。在过去的十年中，卷积神经网络（CNN）在识别CXR图像中的病理方面取得了成功。通常，这些CNN在标准成像网分类任务上进行了预估计，但这假定大规模注释数据集的可用性。在这项工作中，我们使用各种算法和多种设置分析了在未标记的成像网或胸部X射线（CXR）数据集上进行预处理的实用性。我们作品的一些发现包括：（i）标有Imagenet的监督培训学习了很难击败的强烈表现； （ii）对成像网（〜1m图像）的自我监督预处理显示的性能类似于CXR数据集上的自我监督预处理（〜100K图像）； （iii）在有监督的Imagenet上训练的CNN可以通过自我监视的CXR图像进一步训练，导致改进，尤其是当下游数据集按几千张图像的顺序计算时。
Chest radiograph (or Chest X-Ray, CXR) is a popular medical imaging modality that is used by radiologists across the world to diagnose heart or lung conditions. Over the last decade, Convolutional Neural Networks (CNN), have seen success in identifying pathologies in CXR images. Typically, these CNNs are pretrained on the standard ImageNet classification task, but this assumes availability of large-scale annotated datasets. In this work, we analyze the utility of pretraining on unlabeled ImageNet or Chest X-Ray (CXR) datasets using various algorithms and in multiple settings. Some findings of our work include: (i) supervised training with labeled ImageNet learns strong representations that are hard to beat; (ii) self-supervised pretraining on ImageNet (~1M images) shows performance similar to self-supervised pretraining on a CXR dataset (~100K images); and (iii) the CNN trained on supervised ImageNet can be trained further with self-supervised CXR images leading to improvements, especially when the downstream dataset is on the order of a few thousand images.
