SlideGraph+ : Whole slide image level graphs to predict HER2 status in breast cancer
SlideGraph+ : Whole slide image level graphs to predict HER2 status in breast cancer
复制标题
DOI：
10.1016/j.media.2022.102486
复制
发表时间：
2022-05-28
影响因子：
10.9
通讯作者：
Minhas, Fayyaz
中科院分区：
文献类型：
--
作者：
Lu, Wenqi;Toss, Michael;Minhas, Fayyaz
人表皮生长因子受体 2 (HER2) 是一种重要的预后和预测因子，在 15-20% 的乳腺癌 (BCa) 中过度表达。其状态的确定是选择治疗方案和预测预后的关键临床决策步骤。 HER2 状态通过原位杂交 (ISH) 使用转录组学或免疫组织化学 (IHC) 进行评估，这会产生额外的成本和组织负担，并且在评分时容易出现手动观察偏差的分析变异。在本研究中，我们提出了一种基于图神经网络 (GNN) 的新型模型（Slide Graph(+)），可直接从常规苏木精和曙红 (H & E) 染色载玻片的全载玻片图像预测 HER2 状态。除了两个独立的测试数据集之外，该网络还在癌症基因组图谱 (TCGA) 的幻灯片上进行了训练和测试。我们证明，所提出的模型优于最先进的方法，TCGA 上的 ROC 曲线下面积 (AUC) 值 > 0.75，独立测试集上的 ROC 曲线下面积 (AUC) 值 > 0.80。我们的实验表明，所提出的方法可用于病例分类以及在诊断环境中预先订购诊断测试。它还可用于计算病理学中的其他弱监督预测问题。 SlideGraph(+) 代码存储库可从 https://github.com/wenqi006/SlideGraph 获取，同时还可以在 https://github.com/TissueImageAnalytics/tiatoolbox/blob/develop/examples/full-pipelines/slide-graph.ipynb 上查看显示端到端用例的 IPython 笔记本。 (C) 2022 作者。由 Elsevier B.V. 出版
Human epidermal growth factor receptor 2 (HER2) is an important prognostic and predictive factor which is overexpressed in 15-20% of breast cancer (BCa). The determination of its status is a key clinical decision making step for selection of treatment regimen and prognostication. HER2 status is evaluated using transcriptomics or immunohistochemistry (IHC) through in-situ hybridisation (ISH) which incurs additional costs and tissue burden and is prone to analytical variabilities in terms of manual observational biases in scoring. In this study, we propose a novel graph neural network (GNN) based model (Slide Graph( +) ) to predict HER2 status directly from whole-slide images of routine Haematoxylin and Eosin (H & E) stained slides. The network was trained and tested on slides from The Cancer Genome Atlas (TCGA) in addition to two independent test datasets. We demonstrate that the proposed model outperforms the state-of-the-art methods with area under the ROC curve (AUC) values > 0.75 on TCGA and 0.80 on independent test sets. Our experiments show that the proposed approach can be utilised for case triaging as well as pre-ordering diagnostic tests in a diagnostic setting. It can also be used for other weakly supervised prediction problems in computational pathology. The SlideGraph(+) code repository is available at https://github.com/wenqi006/SlideGraph along with an IPython notebook showing an end-to end use case at https://github.com/TissueImageAnalytics/tiatoolbox/blob/develop/examples/full-pipelines/ slide-graph.ipynb . (C) 2022 The Authors. Published by Elsevier B.V.