Guided Proofreading of Automatic Segmentations for Connectomics
Guided Proofreading of Automatic Segmentations for Connectomics
复制标题
DOI：
10.1109/cvpr.2018.00971
复制
发表时间：
2017-04
期刊：
影响因子：
--
通讯作者：
D. Haehn;V. Kaynig;J. Tompkin;J. Lichtman;H. Pfister
中科院分区：
文献类型：
--
作者：
D. Haehn;V. Kaynig;J. Tompkin;J. Lichtman;H. Pfister
连接组学中的自动细胞图像分割方法产生合并和分裂错误，需要通过校对进行校正。先前的研究已经确定了这些错误的视觉搜索作为互动校对的瓶颈。为了帮助纠错，我们开发了两个分类器，自动推荐候选合并和分裂给用户。这些分类器使用卷积神经网络（CNN），该网络在自动分割中针对专家标记的地面事实进行了错误训练。我们的分类器通过考虑分割边界周围的大上下文区域来检测潜在的错误区域。然后，用户可以通过是/否决策进行更正，这比以前的校对方法快7.5倍，减少了信息的变化。我们还提出了一种全自动模式，使用概率阈值进行合并/拆分决策。使用自动方法进行的大量实验以及新手和专家用户的性能比较表明，我们的方法在不同的连接组学数据集上与最先进的校对方法相比表现良好。
Automatic cell image segmentation methods in connectomics produce merge and split errors, which require correction through proofreading. Previous research has identified the visual search for these errors as the bottleneck in interactive proofreading. To aid error correction, we develop two classifiers that automatically recommend candidate merges and splits to the user. These classifiers use a convolutional neural network (CNN) that has been trained with errors in automatic segmentations against expert-labeled ground truth. Our classifiers detect potentially-erroneous regions by considering a large context region around a segmentation boundary. Corrections can then be performed by a user with yes/no decisions, which reduces variation of information 7.5× faster than previous proofreading methods. We also present a fully-automatic mode that uses a probability threshold to make merge/split decisions. Extensive experiments using the automatic approach and comparing performance of novice and expert users demonstrate that our method performs favorably against state-of-the-art proofreading methods on different connectomics datasets.