Lu Yuzhe, Yang Haichun, Asad Zuhayr, Zhu Zheyu, Yao Tianyuan, Xu Jiachen, Fogo Agnes B, Huo Yuankai
Vanderbilt University, Department of Electrical Engineering and Computer Science, Nashville, United States.
Vanderbilt University Medical Center, Department of Pathology, Microbiology and Immunology, Nashville, United States.
J Med Imaging (Bellingham). 2022 Jan;9(1):014005. doi: 10.1117/1.JMI.9.1.014005. Epub 2022 Feb 17.
Recent studies have demonstrated the diagnostic and prognostic values of global glomerulosclerosis (GGS) in IgA nephropathy, aging, and end-stage renal disease. However, the fine-grained quantitative analysis of multiple GGS subtypes (e.g., obsolescent, solidified, and disappearing glomerulosclerosis) is typically a resource extensive manual process. Very few automatic methods, if any, have been developed to bridge this gap for such analytics. We present a holistic pipeline to quantify GGS (with both detection and classification) from a whole slide image in a fully automatic manner. In addition, we conduct the fine-grained classification for the subtypes of GGS. Our study releases the open-source quantitative analytical tool for fine-grained GGS characterization while tackling the technical challenges in unbalanced classification and integrating detection and classification. We present a deep learning-based framework to perform fine-grained detection and classification of GGS, with a hierarchical two-stage design. Moreover, we incorporate the state-of-the-art transfer learning techniques to achieve a more generalizable deep learning model for tackling the imbalanced distribution of our dataset. This way, we build a highly efficient WSI-to-results GGS characterization pipeline. Meanwhile, we investigated the largest fine-grained GGS cohort as of yet with 11,462 glomeruli and 10,619 nonglomeruli, which include 7841 globally sclerotic glomeruli of three distinct categories. With these data, we apply deep learning techniques to achieve (1) fine-grained GGS characterization, (2) GGS versus non-GGS classification, and (3) improved glomeruli detection results. For fine-grained GGS characterization, when pretrained on the larger dataset, our model can achieve a 0.778-macro- score, compared to a 0.746-macro- score when using the regular ImageNet-pretrained weights. On the external dataset, our best model achieves an area under the curve (AUC) score of 0.994 when tasked with differentiating GGS from normal glomeruli. Using our dataset, we are able to build algorithms that allow for fine-grained classification of glomeruli lesions and are robust to distribution shifts. Our study showed that the proposed methods consistently improve the detection and fine-grained classification performance through both cross validation and external validation. Our code and pretrained models have been released for public use at https://github.com/luyuzhe111/glomeruli.
最近的研究已经证明了全球肾小球硬化（GGS）在IgA肾病、衰老和终末期肾病中的诊断和预后价值。然而，对多种GGS亚型（如废弃型、固化型和消失型肾小球硬化）进行细粒度定量分析通常是一个资源消耗大的手动过程。几乎没有开发出自动方法来填补此类分析的这一空白。我们提出了一个整体流程，以全自动方式从全切片图像中量化GGS（包括检测和分类）。此外，我们对GGS的亚型进行细粒度分类。我们的研究发布了用于细粒度GGS特征描述的开源定量分析工具，同时解决了不平衡分类以及整合检测和分类方面的技术挑战。我们提出了一个基于深度学习的框架，用于对GGS进行细粒度检测和分类，采用分层两阶段设计。此外，我们纳入了最先进的迁移学习技术，以实现一个更具通用性的深度学习模型，来应对我们数据集的不平衡分布。通过这种方式，我们构建了一个高效的从全切片图像到结果的GGS特征描述流程。同时，我们研究了目前最大的细粒度GGS队列，其中有11462个肾小球和10619个非肾小球，包括7841个属于三个不同类别的全球硬化性肾小球。利用这些数据，我们应用深度学习技术来实现：（1）细粒度GGS特征描述；（2）GGS与非GGS分类；（3）改进肾小球检测结果。对于细粒度GGS特征描述，在更大的数据集上进行预训练时，我们的模型可以达到0.778的宏F1分数，而使用常规的ImageNet预训练权重时为0.746的宏F1分数。在外部数据集上，当我们的最佳模型用于区分GGS和正常肾小球时，其曲线下面积（AUC）分数达到0.994。利用我们的数据集，我们能够构建算法，实现对肾小球病变的细粒度分类，并且对分布变化具有鲁棒性。我们的研究表明，所提出的方法通过交叉验证和外部验证一致地提高了检测和细粒度分类性能。我们的代码和预训练模型已在https://github.com/luyuzhe111/glomeruli上发布供公众使用。
