arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10732cs.CV
收藏

基于形状感知的医学图像三维语义分割

Shape-aware Semi-supervised 3D Semantic Segmentation for Medical Images

ShanghaiTech University(上海科技大学);Shanghai Engineering Research Center of Intelligent Vision and Imaging(上海市智能视觉与成像工程技术研究中心)

Shuailin Li, Chuyu Zhang, Xuming He

摘要:

半监督学习在医学图像分割中引起了广泛关注,因为获取逐像素图像注释是构建高性能深度学习方法的关键步骤。大多数现有的半监督分割方法要么倾向于忽略对象分割中的几何约束,导致不完整的对象覆盖,要么强加强形状先验,需要额外的对齐。在这项工作中,我们提出了一种新的shapeware半监督分割策略,利用丰富的未标记的数据,并强制执行分割输出的几何形状约束。为了实现这一目标,我们开发了一个多任务深度网络,该网络联合预测对象表面的语义分割和符号距离图(SDM)。在训练过程中,我们在标记数据和未标记数据的预测SDM之间引入对抗性损失,以便我们的网络能够更有效地捕获形状感知特征。在心房分割挑战数据集上的实验表明,我们的方法优于当前最先进的方法,改进了形状估计,这验证了其有效性。代码可在https://github.com/kleinzcy/SASSnet上获得。

英文摘要:

Semi-supervised learning has attracted much attention in medical image segmentation due to challenges in acquiring pixel-wise image annotations, which is a crucial step for building high-performance deep learning methods. Most existing semi-supervised segmentation approaches either tend to neglect geometric constraint in object segments, leading to incomplete object coverage, or impose strong shape prior that requires extra alignment. In this work, we propose a novel shapeaware semi-supervised segmentation strategy to leverage abundant unlabeled data and to enforce a geometric shape constraint on the segmentation output. To achieve this, we develop a multi-task deep network that jointly predicts semantic segmentation and signed distance map(SDM) of object surfaces. During training, we introduce an adversarial loss between the predicted SDMs of labeled and unlabeled data so that our network is able to capture shape-aware features more effectively. Experiments on the Atrial Segmentation Challenge dataset show that our method outperforms current state-of-the-art approaches with improved shape estimation, which validates its efficacy. Code is available at https://github.com/kleinzcy/SASSnet.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑