Diverse Multiple Prediction on Neuron Image Reconstruction
Diverse Multiple Prediction on Neuron Image Reconstruction
复制标题
神经元图像重建的多样化多重预测
DOI：
10.1007/978-3-030-32239-7_51
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
Chen, Chao
中科院分区：
文献类型：
--
作者：
Ye, Ze;Chen, Cong;Yuan, Changhe;Chen, Chao
从各向异性三维电子显微镜图像重建神经元是一个具有挑战性的问题。通常将输入图像视为2D图像切片的堆叠，并且考虑切片内和切片间片段信息。本文提出了一种新的分割算法，该算法建立了统一的能量函数，并对切片分割和切片间一致性进行了联合优化。为了从巨大的解空间中找到最优解，我们提出了一种新的多样性多重预测方法，该方法也鼓励部分解的多样性。我们在几个公共数据集中展示了我们方法的优势。
Neuron reconstruction from anisotropic 3D Electron Microscopy (EM) images is a challenging problem. One often considers an input image as a stack of 2D image slices, and consider both intra and inter slice segments information. In this paper, we present a new segmentation algorithm which builds a unified energy function and jointly optimize the per-slice segmentation and the inter-slice consistency. To find an optimal solution from the huge solution space, we propose a novel diverse multiple prediction method which also encourages diversity in partial solutions. We demonstrate the strength of our method in several public datasets.
影响因子：
5.8
作者：
Fakhry, Ahmed;Peng, Hanchuan;Ji, Shuiwang
通讯作者：
Ji, Shuiwang