Glo-In-One-v2：人类和小鼠组织病理学中肾小球细胞、组织和病变的整体识别
Glo-In-One-v2: Holistic Identification of Glomerular Cells, Tissues, and Lesions in Human and Mouse Histopathology
AI总结：
针对肾小球组织和病变分割依赖专家评估且易变的问题，提出Glo-In-One-v2，升级工具包为细粒度分割，构建大规模数据集，用单一动态头架构分割14类，迁移学习提升精度，模型开源。
摘要：
传统上，肾小球内组织和病变的分割依赖于肾病病理专家的详细形态学评估，这是一个劳动密集型过程，易受观察者间差异影响。我们团队此前开发了用于肾小球综合检测与分割的Glo-In-One工具包。本研究将该工具包升级至版本2，使其具备细粒度分割能力，针对人类和小鼠组织病理学数据集中的23529个带注释肾小球，整理了涵盖组织区域、细胞和病变的14个不同标签。据我们所知，该数据集是目前同类数据集中规模最大的之一。本研究提出一种单一动态头深度学习架构，用于在人类和小鼠病理数据的部分标记图像中分割14个类别。我们的模型使用来自368张带注释肾脏全切片图像（WSIs）的训练集进行训练，以识别5种关键的肾小球内组织，包括鲍曼囊、肾小球丛、系膜、系膜细胞和足细胞。此外，该网络还分割9种肾小球病变类别，包括粘连、囊滴、全球硬化、透明变性、系膜溶解、微动脉瘤、结节性硬化、系膜扩张和节段性硬化。与基线相比，肾小球分割模型取得了不错的性能，平均Dice相似系数（DSC）达到76.5%。此外，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精度（以Dice分数衡量）提高了3%以上。Glo-In-One-v2模型及训练权重已在https://github.com/hrlblab/Glo-In-One_v2公开提供。
英文摘要：
Segmenting glomerular intraglomerular tissue and 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 detection and segmentation of glomeruli. In this study, we leverage the Glo-In-One toolkit to version 2 with fine-grained segmentation capabilities, curating 14 distinct labels for tissue regions, cells, and lesions across a dataset of 23,529 annotated glomeruli across human and mouse histopathology data. To our knowledge, this dataset is among the largest of its kind to date.In this study, we present a single dynamic head deep learning architecture designed to segment 14 classes within partially labeled images of human and mouse pathology data. Our model was trained using a training set derived from 368 annotated kidney whole-slide images (WSIs) to identify 5 key intraglomerular tissues covering Bowman's capsule, glomerular tuft, mesangium, mesangial cells, and podocytes. Additionally, the network segments 9 glomerular lesion classes including adhesion, capsular drop, global sclerosis, hyalinosis, mesangial lysis, microaneurysm, nodular sclerosis, mesangial expansion, and segmental sclerosis. The glomerulus segmentation model achieved a decent performance compared with baselines, and achieved a 76.5 % average Dice Similarity Coefficient (DSC). Additional, transfer learning from rodent to human for glomerular lesion segmentation model has enhanced the average segmentation accuracy across different types of lesions by more than 3 %, as measured by Dice scores. The Glo-In-One-v2 model and trained weight have been made publicly available at https: //github.com/hrlblab/Glo-In-One_v2.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
