anon-neuripsdb26/SenoMorph

SenoMorph是一个基于衰老条件的细胞形态学基准数据集，包含单细胞DAPI裁剪图像，并与连续的转录组衍生衰老分数配对。数据集包括真实细胞图像和生成的伴生细胞图像，图像为64×64灰度DAPI核染色图像。真实子集包含来自肺、前列腺和皮肤组织的87,391个细胞，每个细胞具有衰老分数、核面积和DAPI强度等属性。伴生子集为每个真实细胞生成10个不同衰老分数的图像，总计873,910个图像，用于下游增强任务。数据集支持多种配置加载，如按组织或类型划分，适用于图像分类和图像到图像任务。SenoMorph is a senescence-conditioned cell morphology benchmark of single-cell DAPI crops paired with continuous, transcriptome-derived senescence scores. The dataset includes real cell images and generated companion cell images, with images being 64×64 grayscale DAPI nuclear crops. The real subset consists of 87,391 cells from lung, prostate, and skin tissues, each with attributes such as senescence score, nuclear area, and DAPI intensity. The companion subset generates 10 score-conditioned images per real cell, totaling 873,910 images, intended for downstream augmentation tasks. The dataset supports multiple configurations for loading, such as by tissue or type, and is suitable for image classification and image-to-image tasks.