The value of coarsely labeled datasets in learning transferable representations for medical images is investigated in this work. Compared to fine labels which require meticulous effort to annotate, coarse labels can be acquired at a significantly lower cost and can provide useful training signals for data-hungry deep neural networks. We consider coarse labels in the form of binary labels differentiating a normal (healthy) image from an abnormal (diseased) image and propose CAMContrast, a two-stage representation learning framework for medical images. Using class activation maps, CAMContrast makes use of the binary labels to generate heatmaps as positive views for contrastive representation learning. Specifically, the learning objective is optimized to maximize the agreement within fixed crops of image-heatmap pair to learn fine-grained representations that are generalizable to different downstream tasks. We empirically validate the transfer learning performance of CAMContrast on several public datasets, covering classification and segmentation tasks on fundus photographs and chest X-ray images. The experimental results showed that our method outperforms other self-supervised and supervised pretrain methods in terms of data efficiency and downstream performance.

中文翻译：

---

通过类激活图对医学图像进行从粗到细的视觉表示学习

这项工作研究了粗略标记的数据集在学习医学图像的可转移表示方面的价值。与需要精心注释的精细标签相比，粗标签可以以低得多的成本获取，并且可以为数据密集型深度神经网络提供有用的训练信号。我们考虑以二进制标签形式区分正常（健康）图像和异常（患病）图像的粗标签，并提出 CAMContrast，一种用于医学图像的两阶段表示学习框架。使用类激活图，CAMContrast 利用二进制标签生成热图，作为对比表示学习的积极视图。具体来说，学习目标被优化以最大化图像热图对的固定作物内的一致性，以学习可推广到不同下游任务的细粒度表示。我们根据经验验证了 CAMContrast 在多个公共数据集上的迁移学习性能，涵盖眼底照片和胸部 X 射线图像的分类和分割任务。实验结果表明，我们的方法在数据效率和下游性能方面优于其他自监督和监督预训练方法。