BioSR: a biological image dataset for super-resolution microscopy

BioSR is a biological image dataset for super-resolution microscopy, currently including more than 2200 pairs of low-and-high resolution images covering four biology structures (CCPs, ER, MTs, F-actin), nine signal levels (15-600 average photon count), and two upscaling-factors (linear SIM and non-linear SIM). BioSR is now freely available, aiming to provide a high-quality dataset for the community of single bio-image super-resolution algorithm and advanced SIM reconstruction algorithm developers. For more information about BioSR, please see our Nature Methods manuscript, "Evaluation and development of deep neural networks for image super-resolution in optical microscopy" (DOI: 10.1038/s41592-020-01048-5).
Update 2022.10.04
Add <em>DataSet of rDL-SRM (Zenodo Link).xlsx</em> file, which includes descriptions and Zenodo links of BioSR+ (data extension of BioSR) and other data used in our Nature Biotechnology paper "Rationalized deep learning super-resolution microscopy for sustained live imaging of rapid subcellular processes" (DOI: 10.1038/s41587-022-01471-3 ).<br>

BioSR是一款面向超分辨率显微技术的生物图像数据集，目前包含超过2200对高低分辨率图像，涵盖四种生物结构（包被小凹(Clathrin-Coated Pits, CCPs)、内质网(Endoplasmic Reticulum, ER)、微管(Microtubules, MTs)、肌动蛋白丝(F-actin)）、九个信号等级（15至600个平均光子计数）以及两种上采样模式（线性结构照明显微镜(Structured Illumination Microscopy, SIM)与非线性结构照明显微镜(SIM)）。BioSR目前已免费开放，旨在为单生物图像超分辨率算法及先进SIM重构算法开发者社区提供高质量数据集。如需了解BioSR的更多信息，请参阅我们发表于《自然-方法学》的论文《光学显微镜图像超分辨率的深度学习神经网络评估与开发（Evaluation and development of deep neural networks for image super-resolution in optical microscopy）》（DOI: 10.1038/s41592-020-01048-5）。
2022年10月4日更新：新增<em>rDL-SRM数据集（Zenodo链接）.xlsx</em>文件，该文件包含BioSR扩展数据集BioSR+的相关说明及Zenodo链接，同时涵盖我们发表于《自然-生物技术》的论文《面向快速亚细胞过程持续活成像的合理化深度学习超分辨率显微技术（Rationalized deep learning super-resolution microscopy for sustained live imaging of rapid subcellular processes）》（DOI: 10.1038/s41587-022-01471-3）中使用的其他数据。