Analyzing Image Segmentation for Connectomics.
Analyzing Image Segmentation for Connectomics.
复制标题
DOI：
10.3389/fncir.2018.00102
复制
发表时间：
2018
影响因子：
3.5
通讯作者：
Funke J
中科院分区：
文献类型：
--
作者：
Plaza SM;Funke J
自动图像分割是扩大电子显微镜（EM）连接体重建的关键。为此，存在分割竞赛，如CREMI和SNEMI，以帮助研究人员评估分割算法，以改进它们。由于生成地面实况非常耗时，这些竞赛通常无法捕捉到连接组学所需的分割较大数据集的挑战。更一般地，用于EM图像分割的通用度量不强调对下游分析的影响，并且通常对于分割中的问题区域的隔离不是非常有用。例如，它们不捕获连接信息，并且经常高估分割的质量，正如我们稍后演示的那样。为了解决这些问题，我们引入了一种新的策略，使大规模的分割评估在监督的设置，其中地面真相是可用的，或无监督的设置。为了实现这一目标，我们首先引入新的指标，更紧密地配合下游分析和重建中的分割使用。特别地，这些包括突触连接性和完整性度量，其提供分割质量的有意义和直观的解释，因为它涉及神经元连接性的保留。此外，我们提出的措施分割的正确性和完整性方面的百分比的“孤儿”片段和浓度的自我循环形成的分割失败，这是有帮助的分析，可以计算没有地面真相。引入新的指标旨在用于涉及大型数据集的实际应用，需要一个可扩展的软件生态系统，这是本文的一个关键贡献。为此，我们引入了一个可扩展的，灵活的软件框架，使几个不同的指标的集成，并提供机制，以评估和调试分割之间的差异。我们还引入了可视化软件，以帮助用户使用收集的各种指标。我们在两个相对较大的公共地面实况数据集上评估了我们的框架，为示例分割提供了新的见解。
Automatic image segmentation is critical to scale up electron microscope (EM) connectome reconstruction. To this end, segmentation competitions, such as CREMI and SNEMI, exist to help researchers evaluate segmentation algorithms with the goal of improving them. Because generating ground truth is time-consuming, these competitions often fail to capture the challenges in segmenting larger datasets required in connectomics. More generally, the common metrics for EM image segmentation do not emphasize impact on downstream analysis and are often not very useful for isolating problem areas in the segmentation. For example, they do not capture connectivity information and often over-rate the quality of a segmentation as we demonstrate later. To address these issues, we introduce a novel strategy to enable evaluation of segmentation at large scales both in a supervised setting, where ground truth is available, or an unsupervised setting. To achieve this, we first introduce new metrics more closely aligned with the use of segmentation in downstream analysis and reconstruction. In particular, these include synapse connectivity and completeness metrics that provide both meaningful and intuitive interpretations of segmentation quality as it relates to the preservation of neuron connectivity. Also, we propose measures of segmentation correctness and completeness with respect to the percentage of “orphan” fragments and the concentrations of self-loops formed by segmentation failures, which are helpful in analysis and can be computed without ground truth. The introduction of new metrics intended to be used for practical applications involving large datasets necessitates a scalable software ecosystem, which is a critical contribution of this paper. To this end, we introduce a scalable, flexible software framework that enables integration of several different metrics and provides mechanisms to evaluate and debug differences between segmentations. We also introduce visualization software to help users to consume the various metrics collected. We evaluate our framework on two relatively large public groundtruth datasets providing novel insights on example segmentations.
登录
查看更多内容
影响因子：
3.7
作者：
Parag T;Chakraborty A;Plaza S;Scheffer L
通讯作者：
Scheffer L
影响因子：
3.7
作者：
RAND, WM
通讯作者：
RAND, WM
影响因子：
7.7
作者：
Gerhard, Stephan;Andrade, Ingrid;Schneider-Mizell, Casey M.
通讯作者：
Schneider-Mizell, Casey M.
影响因子：
48
作者：
Januszewski, Michal;Kornfeld, Joergen;Jain, Viren
通讯作者：
Jain, Viren
影响因子：
7.7
作者：
Schneider-Mizell, Casey M.;Gerhard, Stephan;Cardona, Albert
通讯作者：
Cardona, Albert