Phase contrast images of bacteria and ground truth segmentations

<strong>Name</strong>: Phase contrast images of bacteria <strong>Data type</strong>: Paired microscopy images and corresponding labels/masks used for model training, organized as recommended by the DenoiSeg documentation. <strong>Microscopy data type</strong>: Light microscopy (Phase Contrast) <strong>Manual annotations</strong>: Labels/masks obtained via manual segmentation. For each region, all cells were annotated manually. Uncertain objects were left unannotated. <strong>Microscope</strong>: Zeiss Axio Imager M2 epi-fluorescence microscope with a Zeiss Plan-Apochromat; 100x/1.4 oil DIC objective <strong>File format</strong>: .tif (float 32-bits for phase contrast and 16-bit for mask images) <strong>Image size</strong>: 256x256 pixels (Pixel size: 64.5 nm) Content: train - raw (33 files) - masks (33 files) test - raw (11 files) - masks (11 files) All images available in the raw folders were normalized by dividing the original images with a gaussian blurred version or the original image (200 pixels). A groovy code working within ImageJ/Fiji corresponding to this operation is as follow: <pre><code class="language-java">ImagePlus normalize(ImagePlus input_image) { flatfield = (new Duplicator()).run(input_image) (new GaussianBlur()).blur(flatfield.getProcessor(), 200) return ImageCalculator.run(input_image, flatfield, "Divide create 32-bit") } import ij.ImagePlus import ij.plugin.Duplicator import ij.plugin.ImageCalculator import ij.plugin.filter.GaussianBlur</code></pre><strong>数据集名称</strong>: 细菌相差显微图像 <strong>数据类型</strong>: 用于模型训练的成对显微图像与对应标签/掩码，遵循DenoiSeg文档的推荐格式进行组织。 <strong>显微数据类型</strong>: 光学相差显微（Phase Contrast） <strong>人工标注</strong>: 通过手动分割生成标签与掩码。针对每个区域，所有细菌细胞均经人工标注，存在歧义的目标未予标注。 <strong>显微镜</strong>: 蔡司Axio Imager M2落射荧光显微镜，搭配蔡司Plan-Apochromat 100x/1.4油浸DIC物镜。 <strong>文件格式</strong>: .tif格式，其中相差显微图像为32位浮点型，掩码图像为16位整型。 <strong>图像尺寸</strong>: 256×256像素（像素尺寸：64.5 nm）。 <strong>数据集内容</strong>: 训练集 - 原始图像文件夹（含33个文件） - 掩码文件夹（含33个文件） 测试集 - 原始图像文件夹（含11个文件） - 掩码文件夹（含11个文件） 所有原始图像文件夹中的图像均通过以下方式归一化：将原始图像除以其自身的高斯模糊版本（模糊半径为200像素）。适配该操作、可在ImageJ/Fiji平台运行的Groovy代码如下： <pre><code class="language-java">ImagePlus normalize(ImagePlus input_image) { flatfield = (new Duplicator()).run(input_image) (new GaussianBlur()).blur(flatfield.getProcessor(), 200) return ImageCalculator.run(input_image, flatfield, "Divide create 32-bit") } import ij.ImagePlus import ij.plugin.Duplicator import ij.plugin.ImageCalculator import ij.plugin.filter.GaussianBlur</code></pre>