arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.10705eess.IVcs.CV
收藏

基于稀疏正则化深度网络的多类Micro-CT图像分割

Multi-Class Micro-CT Image Segmentation Using Sparse Regularized Deep Networks

The Pennsylvania State University(宾夕法尼亚州立大学)

Amirsaeed Yazdani, Yung-Chen Sun, Nicholas B. Stephens, Timothy Ryan, Vishal Monga

摘要:

在人类学和古生物学中,通过对显微计算机断层扫描(micro-CT)中可观察到的骨骼学特征进行量化来解决有关现存和灭绝物种的问题是很常见的。在遗体被掩埋的情况下,这些扫描中存在的灰度值可以被分类为属于空气、泥土或骨头。虽然已经提出了各种基于强度的方法来将扫描分割成这些类别,但通常情况下,污垢和骨骼的强度值几乎无法区分。在这些情况下,科学家们诉诸于费力的手动分割,当要分析大量扫描时,这种方法在实践中无法很好地扩展。在这里,我们提出了一个新的领域丰富的网络三类图像分割,它利用领域知识的专家熟悉手动分割骨骼和污垢结构。更确切地说,我们的新结构由两个组成部分组成:1)基于新设计的自定义损失项在特殊样本上训练的表示网络,它提取有区别的骨骼和污垢特征,2)以及利用这些提取的有区别的特征的分割网络。这两个部分联合训练,以优化分割性能。我们的网络与当前最先进的U-NET的比较表明了我们的建议的好处,特别是当标记的训练图像的数量有限时,这是微CT分割的必然情况。

英文摘要:

It is common in anthropology and paleontology to address questions about extant and extinct species through the quantification of osteological features observable in micro-computed tomographic (micro-CT) scans. In cases where remains were buried, the grey values present in these scans may be classified as belonging to air, dirt, or bone. While various intensity-based methods have been proposed to segment scans into these classes, it is often the case that intensity values for dirt and bone are nearly indistinguishable. In these instances, scientists resort to laborious manual segmentation, which does not scale well in practice when a large number of scans are to be analyzed. Here we present a new domain-enriched network for three-class image segmentation, which utilizes the domain knowledge of experts familiar with manually segmenting bone and dirt structures. More precisely, our novel structure consists of two components: 1) a representation network trained on special samples based on newly designed custom loss terms, which extracts discriminative bone and dirt features, 2) and a segmentation network that leverages these extracted discriminative features. These two parts are jointly trained in order to optimize the segmentation performance. A comparison of our network to that of the current state-of-the-art U-NETs demonstrates the benefits of our proposal, particularly when the number of labeled training images are limited, which is invariably the case for micro-CT segmentation.

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。

↑