Image-based cell counting is a fundamental yet challenging task with wide applications in biological research. In this paper, we propose a novel unified deep network framework designed to solve this problem for various cell types in both 2D and 3D images. Specifically, we first propose SAU-Net for cell counting by extending the segmentation network U-Net with a Self-Attention module. Second, we design an extension of Batch Normalization (BN) to facilitate the training process for small datasets. In addition, a new 3D benchmark dataset based on the existing mouse blastocyst (MBC) dataset is developed and released to the community. Our SAU-Net achieves state-of-the-art results on four benchmark 2D datasets - synthetic fluorescence microscopy (VGG) dataset, Modified Bone Marrow (MBM) dataset, human subcutaneous adipose tissue (ADI) dataset, and Dublin Cell Counting (DCC) dataset, and the new 3D dataset, MBC. The BN extension is validated using extensive experiments on the 2D datasets, since GPU memory constraints preclude use of 3D datasets. The source code is available at https://github.com/mzlr/sau-net.

中文翻译：

---

SAU-Net：用于 2D 和 3D 显微图像细胞计数的统一网络


基于图像的细胞计数是一项基本但具有挑战性的任务，在生物研究中有着广泛的应用。在本文中，我们提出了一种新颖的统一深度网络框架，旨在解决 2D 和 3D 图像中各种细胞类型的这个问题。具体来说，我们首先通过使用自注意力模块扩展分割网络 U-Net 来提出用于细胞计数的 SAU-Net。其次，我们设计了批量归一化（BN）的扩展，以促进小数据集的训练过程。此外，还开发了基于现有小鼠囊胚（MBC）数据集的新3D基准数据集并向社区发布。我们的 SAU-Net 在四个基准 2D 数据集上取得了最先进的结果 - 合成荧光显微镜 (VGG) 数据集、改良骨髓 (MBM) 数据集、人类皮下脂肪组织 (ADI) 数据集和都柏林细胞计数 (DCC) ）数据集，以及新的 3D 数据集 MBC。由于 GPU 内存限制妨碍了 3D 数据集的使用，因此 BN 扩展通过对 2D 数据集进行大量实验进行了验证。源代码可在 https://github.com/mzlr/sau-net 获取。