Lin Li, Peng Linkai, He Huaqing, Cheng Pujin, Wu Jiewei, Wong Kenneth K Y, Tang Xiaoying
Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China; Department of Electrical and Electronic Engineering, the University of Hong Kong, Hong Kong, China; Jiaxing Research Institute, Southern University of Science and Technology, Jiaxing, China.
Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China.
Med Image Anal. 2023 Dec;90:102937. doi: 10.1016/j.media.2023.102937. Epub 2023 Aug 30.
Weakly-supervised learning (WSL) has been proposed to alleviate the conflict between data annotation cost and model performance through employing sparsely-grained (i.e., point-, box-, scribble-wise) supervision and has shown promising performance, particularly in the image segmentation field. However, it is still a very challenging task due to the limited supervision, especially when only a small number of labeled samples are available. Additionally, almost all existing WSL segmentation methods are designed for star-convex structures which are very different from curvilinear structures such as vessels and nerves. In this paper, we propose a novel sparsely annotated segmentation framework for curvilinear structures, named YoloCurvSeg. A very essential component of YoloCurvSeg is image synthesis. Specifically, a background generator delivers image backgrounds that closely match the real distributions through inpainting dilated skeletons. The extracted backgrounds are then combined with randomly emulated curves generated by a Space Colonization Algorithm-based foreground generator and through a multilayer patch-wise contrastive learning synthesizer. In this way, a synthetic dataset with both images and curve segmentation labels is obtained, at the cost of only one or a few noisy skeleton annotations. Finally, a segmenter is trained with the generated dataset and possibly an unlabeled dataset. The proposed YoloCurvSeg is evaluated on four publicly available datasets (OCTA500, CORN, DRIVE and CHASEDB1) and the results show that YoloCurvSeg outperforms state-of-the-art WSL segmentation methods by large margins. With only one noisy skeleton annotation (respectively 0.14%, 0.03%, 1.40%, and 0.65% of the full annotation), YoloCurvSeg achieves more than 97% of the fully-supervised performance on each dataset. Code and datasets will be released at https://github.com/llmir/YoloCurvSeg.
弱监督学习（WSL）已被提出，通过采用稀疏粒度（即逐点、逐框、逐涂鸦）监督来缓解数据标注成本与模型性能之间的冲突，并已显示出有前景的性能，特别是在图像分割领域。然而，由于监督有限，这仍然是一项非常具有挑战性的任务，尤其是当只有少量标记样本可用时。此外，几乎所有现有的WSL分割方法都是为星凸结构设计的，而星凸结构与血管和神经等曲线结构有很大不同。在本文中，我们提出了一种用于曲线结构的新型稀疏标注分割框架，名为YoloCurvSeg。YoloCurvSeg的一个非常重要的组件是图像合成。具体来说，一个背景生成器通过修复扩张的骨架来提供与真实分布紧密匹配的图像背景。然后，提取的背景与基于空间殖民算法的前景生成器生成的随机模拟曲线相结合，并通过一个多层逐块对比学习合成器。通过这种方式，以仅一个或几个噪声骨架标注为代价，获得了一个带有图像和曲线分割标签的合成数据集。最后，使用生成的数据集以及可能的未标记数据集训练一个分割器。所提出的YoloCurvSeg在四个公开可用的数据集（OCTA500、CORN、DRIVE和CHASEDB1）上进行了评估，结果表明YoloCurvSeg大幅优于当前最先进的WSL分割方法。仅使用一个噪声骨架标注（分别占完整标注的0.14%、0.03%、1.40%和0.65%），YoloCurvSeg在每个数据集上都实现了超过97%的全监督性能。代码和数据集将在https://github.com/llmir/YoloCurvSeg上发布。
