基因表达可用于乳腺癌亚型,与使用常规免疫组织化学(IHC)获得的预测相比,对复发风险和治疗反应性的预测有所改善。然而,在诊所里,分子谱分析主要用于ER+乳腺癌,这是昂贵的,组织破坏性,需要专门的平台,需要几个星期才能得到结果。深度学习算法可以有效提取数字组织病理学图像中的形态学模式,以快速且经济高效地预测分子表型。我们提出了一个新的,计算有效的方法称为hist2RNA,其灵感来自大量RNA测序技术,以预测138个基因的表达(从6个市售分子谱分析测试中纳入),包括腔PAM50亚型,来自苏木精和曙红(H&E)染色的整个载玻片图像(WSI)。训练阶段涉及从预先训练的模型中汇总每位患者的提取特征,以使用来自癌症基因组图谱(TCGA,n=335)。我们在坚持的测试集上证明了成功的基因预测(n=160,corr=0.82,不同基因的corr=0.29),并在具有已知IHC和生存信息的外部组织微阵列(TMA)数据集(n=498)上进行探索性分析。我们的模型能够预测TMA数据集上的基因表达和管腔PAM50亚型(管腔A与管腔B),在单变量分析中对总生存期具有预后意义(c指数=0.56,风险比=2.16(95%CI1.12-3.06),p<5×10-3),在纳入标准临床病理变量的多变量分析中具有独立意义(c指数=0.65,风险比=1.87(95%CI1.30-2.68),p<5×10-3)。所提出的策略实现了卓越的性能,同时需要更少的培训时间,与基于补丁的模型相比,能耗和计算成本更低。此外,hist2RNA预测的基因表达有可能决定与总生存期相关的腔分子亚型,不需要昂贵的分子测试。
Gene expression can be used to subtype breast cancer with improved prediction of risk of recurrence and treatment responsiveness over that obtained using routine immunohistochemistry (IHC). However, in the clinic, molecular profiling is primarily used for ER+ breast cancer, which is costly, tissue destructive, requires specialised platforms, and takes several weeks to obtain a result. Deep learning algorithms can effectively extract morphological patterns in digital histopathology images to predict molecular phenotypes quickly and cost-effectively. We propose a new, computationally efficient approach called hist2RNA inspired by bulk RNA sequencing techniques to predict the expression of 138 genes (incorporated from 6 commercially available molecular profiling tests), including luminal PAM50 subtype, from hematoxylin and eosin (H&E)-stained whole slide images (WSIs). The training phase involves the aggregation of extracted features for each patient from a pretrained model to predict gene expression at the patient level using annotated H&E images from The Cancer Genome Atlas (TCGA, n = 335). We demonstrate successful gene prediction on a held-out test set (n = 160, corr = 0.82 across patients, corr = 0.29 across genes) and perform exploratory analysis on an external tissue microarray (TMA) dataset (n = 498) with known IHC and survival information. Our model is able to predict gene expression and luminal PAM50 subtype (Luminal A versus Luminal B) on the TMA dataset with prognostic significance for overall survival in univariate analysis (c-index = 0.56, hazard ratio = 2.16 (95% CI 1.12-3.06), p < 5 × 10-3), and independent significance in multivariate analysis incorporating standard clinicopathological variables (c-index = 0.65, hazard ratio = 1.87 (95% CI 1.30-2.68), p < 5 × 10-3). The proposed strategy achieves superior performance while requiring less training time, resulting in less energy consumption and computational cost compared to patch-based models. Additionally, hist2RNA predicts gene expression that has potential to determine luminal molecular subtypes which correlates with overall survival, without the need for expensive molecular testing.