Yu Lining, Yin Mengmeng, Deng Ruining, Liu Quan, Yao Tianyuan, Cui Can, Guo Junlin, Wang Yu, Wang Yaohong, Zhao Shilin, Yang Haichun, Huo Yuankai
Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States.
Vanderbilt University Medical Center, Department of Pathology, Microbiology and Immunology, Nashville, Tennessee, United States.
J Med Imaging (Bellingham). 2025 Nov;12(6):061406. doi: 10.1117/1.JMI.12.6.061406. Epub 2025 Jul 28.
Segmenting intraglomerular tissue and glomerular lesions traditionally depends on detailed morphological evaluations by expert nephropathologists, a labor-intensive process susceptible to interobserver variability. Our group previously developed the Glo-In-One toolkit for integrated glomerulus detection and segmentation. We leverage the Glo-In-One toolkit to version 2 (Glo-In-One-v2), which adds fine-grained segmentation capabilities. We curated 14 distinct labels spanning tissue regions, cells, and lesions across 23,529 annotated glomeruli from human and mouse histopathology data. To our knowledge, this dataset is among the largest of its kind to date.
We present a single dynamic-head deep learning architecture for segmenting 14 classes within partially labeled images from human and mouse kidney pathology. The model was trained on data derived from 368 annotated kidney whole-slide images with five key intraglomerular tissue types and nine glomerular lesion types.
The glomerulus segmentation model achieved a decent performance compared with baselines and achieved a 76.5% average Dice similarity coefficient. In addition, transfer learning from rodent to human for the glomerular lesion segmentation model has enhanced the average segmentation accuracy across different types of lesions by more than 3%, as measured by Dice scores.
We introduce a convolutional neural network for multiclass segmentation of intraglomerular tissue and lesions. The Glo-In-One-v2 model and pretrained weight are publicly available at https://github.com/hrlblab/Glo-In-One_v2.
传统上，肾小球内组织和肾小球病变的分割依赖于肾脏病理专家进行的详细形态学评估，这是一个劳动密集型过程，容易受到观察者间差异的影响。我们团队之前开发了用于肾小球检测和分割一体化的Glo-In-One工具包。我们将Glo-In-One工具包升级到了版本2（Glo-In-One-v2），它增加了细粒度分割功能。我们从人类和小鼠组织病理学数据中的23529个注释肾小球中整理出了14种不同的标签，涵盖组织区域、细胞和病变。据我们所知，该数据集是迄今为止同类数据集中规模最大的之一。
我们提出了一种单一动态头深度学习架构，用于分割来自人类和小鼠肾脏病理的部分标记图像中的14个类别。该模型在来自368张注释肾脏全切片图像的数据上进行训练，这些图像包含五种关键的肾小球内组织类型和九种肾小球病变类型。
与基线相比，肾小球分割模型表现良好，平均骰子相似系数达到76.5%。此外，通过骰子分数衡量，肾小球病变分割模型从啮齿动物到人类的迁移学习使不同类型病变的平均分割准确率提高了3%以上。
我们引入了一种用于肾小球内组织和病变多类分割的卷积神经网络。Glo-In-One-v2模型和预训练权重可在https://github.com/hrlblab/Glo-In-One_v2上公开获取。
