Shi Ruohua, Wang Wenyao, Li Zhixuan, He Liuyuan, Sheng Kaiwen, Ma Lei, Du Kai, Jiang Tingting, Huang Tiejun
Beijing Academy of Artificial Intelligence, Beijing, China.
National Engineering Research Center of Visual Technology, School of Computer Science, Peking University, Beijing, China.
Front Comput Neurosci. 2022 Apr 11;16:842760. doi: 10.3389/fncom.2022.842760. eCollection 2022.
Connectomics is a developing field aiming at reconstructing the connection of the neural system at the nanometer scale. Computer vision technology, especially deep learning methods used in image processing, has promoted connectomic data analysis to a new era. However, the performance of the state-of-the-art (SOTA) methods still falls behind the demand of scientific research. Inspired by the success of ImageNet, we present an annotated ultra-high resolution image segmentation dataset for cell membrane (U-RISC), which is the largest cell membrane-annotated electron microscopy (EM) dataset with a resolution of 2.18 nm/pixel. Multiple iterative annotations ensured the quality of the dataset. Through an open competition, we reveal that the performance of current deep learning methods still has a considerable gap from the human level, different from ISBI 2012, on which the performance of deep learning is closer to the human level. To explore the causes of this discrepancy, we analyze the neural networks with a visualization method, which is an attribution analysis. We find that the U-RISC requires a larger area around a pixel to predict whether the pixel belongs to the cell membrane or not. Finally, we integrate the currently available methods to provide a new benchmark (0.67, 10% higher than the leader of the competition, 0.61) for cell membrane segmentation on the U-RISC and propose some suggestions in developing deep learning algorithms. The U-RISC dataset and the deep learning codes used in this study are publicly available.
连接组学是一个正在发展的领域，旨在重建纳米尺度下神经系统的连接。计算机视觉技术，尤其是用于图像处理的深度学习方法，已将连接组数据分析推进到一个新时代。然而，当前最先进（SOTA）方法的性能仍落后于科研需求。受ImageNet成功的启发，我们提出了一个用于细胞膜的带注释超高分辨率图像分割数据集（U-RISC），它是分辨率为2.18纳米/像素的最大的带细胞膜注释的电子显微镜（EM）数据集。多次迭代注释确保了数据集的质量。通过一场公开竞赛，我们发现当前深度学习方法的性能与人类水平仍有相当大的差距，这与2012年国际生物医学图像分析学会（ISBI）竞赛不同，在那次竞赛中深度学习的性能更接近人类水平。为了探究这种差异的原因，我们用一种可视化方法（即归因分析）对神经网络进行分析。我们发现U-RISC数据集需要在一个像素周围有更大的区域来预测该像素是否属于细胞膜。最后，我们整合了当前可用的方法，为U-RISC数据集上的细胞膜分割提供了一个新的基准（0.67，比竞赛领先者0.61高出10%），并在开发深度学习算法方面提出了一些建议。本研究中使用的U-RISC数据集和深度学习代码已公开提供。
