arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.12640cs.CV
收藏

PGL:先验引导的局部自监督学习三维医学图像分割

PGL: Prior-Guided Local Self-supervised Learning for 3D Medical Image Segmentation

Northwestern Polytechnical University(西北工业大学);The University of Adelaide(阿德莱德大学)

Yutong Xie, Jianpeng Zhang, Zehui Liao, Yong Xia, Chunhua Shen

摘要:

人们已经广泛认识到,图像分割中的深度学习的成功主要依赖于大量密集注释的训练数据,然而,由于所需的巨大劳动力和专业知识,特别是对于注释3D医学图像,难以获得这些数据。虽然自监督学习(SSL)在解决这一问题上表现出了巨大的潜力,但大多数SSL方法只关注图像级的全局一致性,而忽略了局部一致性,而局部一致性在捕获密集预测任务(如分割)的结构信息方面起着关键作用。在本文中,我们提出了一个先验引导局部(PGL)自监督模型,学习潜在特征空间中的区域局部一致性。具体地说,我们使用的空间变换,产生不同的增强视图的同一图像,作为一个先验推导出两个视图之间的位置关系,然后用于对齐的特征地图的同一个局部区域,但被提取的两个视图。接下来,我们构建一个局部一致性损失,以最大限度地减少对齐的特征图之间的体素差异。因此,我们的PGL模型学习局部区域的独特表示,因此能够保留结构信息。这种能力有利于下游细分任务。我们对四个公共计算机断层扫描(CT)数据集进行了广泛的评估,涵盖了11种主要人体器官和两种肿瘤。结果表明,使用预训练的PGL模型初始化下游网络导致了显着的性能改善,无论是随机初始化和基于全局一致性的模型初始化。代码和预先训练的权重将在https://git.io/PGL上提供。

英文摘要:

It has been widely recognized that the success of deep learning in image segmentation relies overwhelmingly on a myriad amount of densely annotated training data, which, however, are difficult to obtain due to the tremendous labor and expertise required, particularly for annotating 3D medical images. Although self-supervised learning (SSL) has shown great potential to address this issue, most SSL approaches focus only on image-level global consistency, but ignore the local consistency which plays a pivotal role in capturing structural information for dense prediction tasks such as segmentation. In this paper, we propose a PriorGuided Local (PGL) self-supervised model that learns the region-wise local consistency in the latent feature space. Specifically, we use the spatial transformations, which produce different augmented views of the same image, as a prior to deduce the location relation between two views, which is then used to align the feature maps of the same local region but being extracted on two views. Next, we construct a local consistency loss to minimize the voxel-wise discrepancy between the aligned feature maps. Thus, our PGL model learns the distinctive representations of local regions, and hence is able to retain structural information. This ability is conducive to downstream segmentation tasks. We conducted an extensive evaluation on four public computerized tomography (CT) datasets that cover 11 kinds of major human organs and two tumors. The results indicate that using pre-trained PGL model to initialize a downstream network leads to a substantial performance improvement over both random initialization and the initialization with global consistency-based models. Code and pre-trained weights will be made available at: https://git.io/PGL.

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。

↑