College of Computer Science, Nankai University, Tianjin 300071, China.
Centre for Bioinformatics and Intelligent Medicine, Nankai University, Tianjin 300071, China.
Bioinformatics. 2024 Jun 28;40(Suppl 1):i79-i90. doi: 10.1093/bioinformatics/btae236.
Human epidermal growth factor receptor 2 (HER2) status identification enables physicians to assess the prognosis risk and determine the treatment schedule for patients. In clinical practice, pathological slides serve as the gold standard, offering morphological information on cellular structure and tumoral regions. Computational analysis of pathological images has the potential to discover morphological patterns associated with HER2 molecular targets and achieve precise status prediction. However, pathological images are typically equipped with high-resolution attributes, and HER2 expression in breast cancer (BC) images often manifests the intratumoral heterogeneity.
We present a phenotype-informed weakly supervised multiple instance learning architecture (PhiHER2) for the prediction of the HER2 status from pathological images of BC. Specifically, a hierarchical prototype clustering module is designed to identify representative phenotypes across whole slide images. These phenotype embeddings are then integrated into a cross-attention module, enhancing feature interaction and aggregation on instances. This yields a phenotype-based feature space that leverages the intratumoral morphological heterogeneity for HER2 status prediction. Extensive results demonstrate that PhiHER2 captures a better WSI-level representation by the typical phenotype guidance and significantly outperforms existing methods on real-world datasets. Additionally, interpretability analyses of both phenotypes and WSIs provide explicit insights into the heterogeneity of morphological patterns associated with molecular HER2 status.
Our model is available at https://github.com/lyotvincent/PhiHER2.
人表皮生长因子受体 2（HER2）状态的确定使医生能够评估预后风险，并为患者确定治疗方案。在临床实践中，病理切片是金标准，提供了关于细胞结构和肿瘤区域的形态学信息。对病理图像进行计算分析有可能发现与 HER2 分子靶标相关的形态学模式，并实现精确的状态预测。然而，病理图像通常具有高分辨率的属性，而乳腺癌（BC）图像中的 HER2 表达通常表现出肿瘤内异质性。
我们提出了一种基于表型信息的弱监督多实例学习架构（PhiHER2），用于从 BC 的病理图像预测 HER2 状态。具体来说，设计了一个层次原型聚类模块，以识别全幻灯片图像中的代表性表型。然后将这些表型嵌入集成到交叉注意模块中，增强实例上的特征交互和聚合。这产生了一个基于表型的特征空间，利用肿瘤内的形态学异质性来预测 HER2 状态。广泛的结果表明，PhiHER2 通过典型的表型指导更好地捕获了 WSI 级别的表示，并且在真实数据集上明显优于现有方法。此外，对表型和 WSI 的可解释性分析提供了与分子 HER2 状态相关的形态学模式异质性的明确见解。
我们的模型可在 https://github.com/lyotvincent/PhiHER2 上获得。
