论文标题
Cyclemix：从涂鸦监督中的医学图像分割的整体策略
CycleMix: A Holistic Strategy for Medical Image Segmentation from Scribble Supervision
论文作者
论文摘要
策划大量完全注释的培训数据可能会很昂贵，尤其是对于医疗图像分割的任务。在实践中，涂鸦是一种较弱的注释形式，更可以获得，但是对涂鸦有限监督的培训细分模型仍然具有挑战性。为了解决困难，我们提出了一个新的基于学习的医学图像分割的框架，该框架由混合增强和周期一致性组成，因此称为Cyclemix。为了增强监督，Cyclemix采用专门的随机遮挡设计采用混合策略，以执行涂鸦的增量和减少。对于监督的正规化，Cyclemix通过一致性损失加强了训练目标，以惩罚不一致的细分，从而显着改善了细分性能。在两个开放数据集（即ACDC和MSCMRSEG）上的结果表明，所提出的方法实现了令人振奋的性能，比完全监督的方法证明了相当甚至更好的准确性。 MSCMRSEG的代码和专家制作的涂鸦注释可在https://github.com/bwgzk/cyclemix上公开获得。
Curating a large set of fully annotated training data can be costly, especially for the tasks of medical image segmentation. Scribble, a weaker form of annotation, is more obtainable in practice, but training segmentation models from limited supervision of scribbles is still challenging. To address the difficulties, we propose a new framework for scribble learning-based medical image segmentation, which is composed of mix augmentation and cycle consistency and thus is referred to as CycleMix. For augmentation of supervision, CycleMix adopts the mixup strategy with a dedicated design of random occlusion, to perform increments and decrements of scribbles. For regularization of supervision, CycleMix intensifies the training objective with consistency losses to penalize inconsistent segmentation, which results in significant improvement of segmentation performance. Results on two open datasets, i.e., ACDC and MSCMRseg, showed that the proposed method achieved exhilarating performance, demonstrating comparable or even better accuracy than the fully-supervised methods. The code and expert-made scribble annotations for MSCMRseg are publicly available at https://github.com/BWGZK/CycleMix.
