Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks With Learned Shape Features
Supervoxel-Based Segmentation of Mitochondria in EM Image Stacks With Learned Shape Features
复制标题
DOI：
10.1109/tmi.2011.2171705
复制
发表时间：
2012-02-01
影响因子：
10.6
通讯作者：
Fua, Pascal
中科院分区：
文献类型：
--
作者：
Lucchi, Aurelien;Smith, Kevin;Fua, Pascal
越来越清楚的是，线粒体在神经功能中起着重要作用。最近的研究表明，线粒体形态是至关重要的细胞生理和突触功能和线粒体缺陷和神经退行性疾病之间的联系是强烈怀疑。电子显微镜（EM）在所有三个方向上都具有非常高的分辨率，是更仔细研究这些问题的关键工具之一，但它产生的大量数据使自动分析成为必要。设计用于自然2-D图像的最先进的计算机视觉算法在应用于EM数据时往往表现不佳，原因有很多。首先，典型EM体积的绝对大小使得大多数现代分割方案难以处理。此外，大多数方法忽略了重要的形状线索，仅依赖于局部统计数据，当面对数据中固有的噪声和纹理时，这些统计数据很容易混淆。最后，强图像梯度总是对应于对象边界的传统假设被分散注意力的膜的杂乱所违背。在这项工作中，我们提出了一个自动化的图分区方案，解决这些问题。它通过对超体素而不是体素进行操作来降低计算复杂度，结合能够描述目标对象的3-D形状的形状特征，并学习识别真实边界的独特外观。我们的实验表明，我们的方法是能够分割线粒体的性能水平接近人类注释，并优于一个国家的最先进的3-D分割技术。
It is becoming increasingly clear that mitochondria play an important role in neural function. Recent studies show mitochondrial morphology to be crucial to cellular physiology and synaptic function and a link between mitochondrial defects and neuro-degenerative diseases is strongly suspected. Electron microscopy (EM), with its very high resolution in all three directions, is one of the key tools to look more closely into these issues but the huge amounts of data it produces make automated analysis necessary. State-of-the-art computer vision algorithms designed to operate on natural 2-D images tend to perform poorly when applied to EM data for a number of reasons. First, the sheer size of a typical EM volume renders most modern segmentation schemes intractable. Furthermore, most approaches ignore important shape cues, relying only on local statistics that easily become confused when confronted with noise and textures inherent in the data. Finally, the conventional assumption that strong image gradients always correspond to object boundaries is violated by the clutter of distracting membranes. In this work, we propose an automated graph partitioning scheme that addresses these issues. It reduces the computational complexity by operating on supervoxels instead of voxels, incorporates shape features capable of describing the 3-D shape of the target objects, and learns to recognize the distinctive appearance of true boundaries. Our experiments demonstrate that our approach is able to segment mitochondria at a performance level close to that of a human annotator, and outperforms a state-of-the-art 3-D segmentation technique.