MoNuSeg

此挑战的数据集是通过仔细注释几名患有不同器官肿瘤且在多家医院被诊断的患者的组织图像而获得的。该数据集是通过从TCGA档案中下载以40倍放大倍率捕获的H & E染色组织图像创建的。H & E染色是增强组织切片对比度的常规方案，通常用于肿瘤评估 (分级，分期等)。鉴于跨多个器官和患者的细胞核外观的多样性，以及在多家医院采用的染色方案的丰富性，培训数据集将使能够开发强大且可推广的细胞核分割技术，这些技术将开箱即用。

The dataset for this challenge is obtained by carefully annotating histologic tissue images of patients diagnosed with tumors in various organs across multiple hospitals. This dataset is constructed by downloading H&E-stained histologic tissue images captured at 40× magnification from the TCGA repository. Hematoxylin and Eosin (H&E) staining is a standard routine protocol that enhances the contrast of tissue sections, and is widely utilized for tumor assessment such as grading, staging and other relevant evaluations. Given the diversity of nuclear morphological features across different organs and patient cohorts, as well as the variability of staining protocols adopted by various hospitals, the training dataset will enable the development of robust and generalizable nuclear segmentation techniques that can be used out-of-the-box.

搜集汇总

背景与挑战

背景概述

MoNuSeg是一个用于细胞核分割的医学图像数据集，包含从TCGA档案获取的40倍放大H&E染色组织图像，覆盖多名不同器官肿瘤患者的多家医院数据。该数据集旨在通过多样化的细胞核外观和染色方案，支持开发鲁棒、可推广的细胞核分割技术，适用于肿瘤评估等医疗应用。