Multi-Class Micro-CT Image Segmentation Using Sparse Regularized Deep Networks
Multi-Class Micro-CT Image Segmentation Using Sparse Regularized Deep Networks
复制标题
DOI：
10.1109/ieeeconf51394.2020.9443322
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Amirsaeed Yazdani;Yun Sun;Nicholas B. Stephens;Timothy Ryan;V. Monga
中科院分区：
文献类型：
--
作者：
Amirsaeed Yazdani;Yun Sun;Nicholas B. Stephens;Timothy Ryan;V. Monga
在人类学和古生物学中，通过对微计算机断层扫描（mCT）中观察到的骨骼特征进行量化来解决现存和灭绝物种的问题是很常见的。在遗骸被掩埋的情况下，这些扫描中出现的灰色值可能被归类为属于空气、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为这些类别，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，科学家们求助于费力的人工分割，当要分析大量扫描时，这种方法在实践中并不适用。本文提出了一种新的领域丰富的三级图像分割网络，该网络利用了熟悉手工分割骨骼和污垢结构的专家的领域知识。更准确地说，我们的新结构由两部分组成：1)一个基于新设计的自定义损失项的特殊样本训练的表示网络，它提取了区别性的骨骼和污垢特征；2)一个利用这些提取的区别性特征的分割网络。为了优化分割性能，对这两个部分进行了联合训练。将我们的网络与当前最先进的U-NETs进行比较，可以证明我们的建议的好处，特别是当标记的训练图像数量有限时，这是mCT分割的必然情况。
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 (mCT) 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 mCT segmentation.