Howard Frederick M, Dolezal James, Hieromnimon Hanna, Venters Sara, Kochanny Sara, Li Anran, Borowsky Alexander, Symmans W Fraser, Wolf Denise, Brown-Swigart Lamorna, Sun Anthony, Basu Amrita, Hirst Gillian, Nguyen Long C, Asare Adam, Kanaparthi Sai, Khramtsova Galina, Blenman Kim, Shan Naing Lin, Fan Cheng, Tolaney Sara M, Somlo George, Hudis Clifford A, Sikov William, McCart Linda, Watson Mark, Carey Lisa, Stover Daniel G, Veer Laura Van't, Esserman Laura J, Perou Charles M, Pusztai Lajos, Olopade Olofunmilayo I, Huo Dezheng, Nanda Rita, Pearson Alexander T
Department of Medicine, University of Chicago, Chicago, IL, USA.
Geisinger Cancer Institute, Danville, PA, USA.
medRxiv. 2025 Aug 27:2025.08.25.25334393. doi: 10.1101/2025.08.25.25334393.
Deep learning models applied to digital histology can predict gene expression signatures (GES) and offer a low-cost, rapidly available alternative to molecular testing at the time of diagnosis. We optimized transformer-based models to infer GES results and applied this approach to pre-treatment H&E-stained biopsies from 1,940 breast cancer patients treated with neoadjuvant chemotherapy in clinical trial and real-world cohorts. The most predictive histology-derived GES for pathologic complete response (pCR) in the I-SPY2 trial was validated in four external cohorts: CALGB 40601, CALGB 40603, a trial of durvalumab plus CT, and standard-of-care CT-treated patients from the University of Chicago. Among HER2-negative patients, a transformer-based model trained using a signature composed of estrogen-regulated genes, proliferation, apoptosis, and interferon response genes predicted pCR with an AUC of 0.794, outperforming models based on clinical features alone (AUC 0.704, p = 0.001), pathologist TIL assessment, and a model trained directly to predict response from I-SPY2 cases. Tertiles of this signature stratify patients into clinically relevant groups with increasing likelihood of complete response, with pCR rates ≥50% in the top tertile regardless of treatment or hormone receptor status. Additional transformer-based signature models predicted response to specific therapies (but not chemotherapy alone), including a HER2 signaling signature in IO-treated patients, and a claudin-low signature in bevacizumab treated patients. In HER2- cohorts with available gene expression data and histology, models trained on expression data performed similarly to digital histology predictions, but the combination of gene expression and histology outperformed histology alone. These findings suggest that histology-based GES provides additive information to RNA sequencing data and can inform precision treatment selection across breast cancer subtypes.
应用于数字组织学的深度学习模型可以预测基因表达特征（GES），并在诊断时提供一种低成本、快速可用的分子检测替代方法。我们优化了基于Transformer的模型以推断GES结果，并将此方法应用于来自1940例在临床试验和真实世界队列中接受新辅助化疗的乳腺癌患者的治疗前苏木精-伊红（H&E）染色活检样本。在I-SPY2试验中，对病理完全缓解（pCR）最具预测性的组织学衍生GES在四个外部队列中得到验证：CALGB 40601、CALGB 40603、一项度伐利尤单抗联合化疗的试验以及芝加哥大学接受标准治疗化疗的患者。在人表皮生长因子受体2（HER2）阴性患者中，使用由雌激素调节基因、增殖、凋亡和干扰素反应基因组成的特征训练的基于Transformer的模型预测pCR的曲线下面积（AUC）为0.794，优于仅基于临床特征的模型（AUC 0.704，p = 0.001）、病理学家肿瘤浸润淋巴细胞（TIL）评估以及直接训练以预测I-SPY2病例反应的模型。该特征的三分位数将患者分层为具有越来越高完全缓解可能性的临床相关组，无论治疗或激素受体状态如何，最高三分位数的pCR率≥50%。其他基于Transformer的特征模型预测了对特定疗法（但不包括单独化疗）的反应，包括免疫肿瘤（IO）治疗患者中的HER2信号特征以及贝伐单抗治疗患者中的claudin低表达特征。在具有可用基因表达数据和组织学的HER2阴性队列中，基于表达数据训练的模型与数字组织学预测表现相似，但基因表达和组织学的组合优于单独的组织学。这些发现表明，基于组织学的GES为RNA测序数据提供了补充信息，并可为乳腺癌各亚型的精准治疗选择提供参考。
