文献速递乳腺癌妇科肿瘤

深度学习人工智能从组织学切片预测同源重组缺陷及铂类治疗反应

Deep Learning Artificial Intelligence Predicts Homologous Recombination Deficiency and Platinum Response From Histologic Slides.
PubMed 文献 · J Clin Oncol · 2024-07-31

研究利用TCGA乳腺癌(n=1008)和卵巢癌(n=459)训练深度学习平台DeepHRD,从H&E染色切片预测同源重组缺陷(HRD)。在多个独立队列中验证,预测HRD的乳腺癌患者接受铂类治疗后完全缓解率更高、无进展生存期更长,且该模型分类出的HRD患者数量比分子检测多1.8至3.1倍。

要点

  • DeepHRD从H&E切片预测乳腺癌HRD的AUC为0.81(95%CI 0.77-0.85),两个独立乳腺癌队列验证AUC为0.76。
  • 在铂类治疗的转移性乳腺癌中,预测为HRD者中位无进展生存期延长3.7倍(14.4 vs 3.9个月;P=0.0019),HR为0.45(P=0.0047)。
  • DeepHRD在高级别浆液性卵巢癌中预测的HRD患者一线铂类治疗后总生存期更优(HR 0.46;P=0.030)。

核心结论

  • DeepHRD可从常规H&E切片直接预测乳腺癌和卵巢癌的HRD,并在多个外部队列、切片扫描仪和组织固定变量中验证。
  • 与分子检测相比,DeepHRD分类出多1.8至3.1倍的HRD患者,这些患者在高级别浆液性卵巢癌中总生存期更优,在转移性乳腺癌中铂类特异性无进展生存期更优。

研究设计与样本

  • 研究使用癌症基因组图谱(TCGA)原发乳腺癌(n=1008)和卵巢癌(n=459)训练深度学习平台DeepHRD,从H&E染色组织病理切片预测HRD。
  • 在来自多个独立数据集的乳腺癌(n=349)和卵巢癌(n=141)中,将DeepHRD与四种标准HRD分子检测进行比较,包括接受铂类治疗的临床队列,终点为RECIST无进展生存期、完全缓解和总生存期。

主要发现

  • 在TCGA留出的H&E染色乳腺癌切片中,DeepHRD预测HRD的AUC为0.81(95%CI 0.77至0.85)。
  • 在两个独立原发乳腺癌队列中验证,AUC为0.76(95%CI 0.71至0.82)。
  • 在一个外部铂类治疗的转移性乳腺癌队列中,预测为HRD的样本完全缓解率更高(AUC 0.76,95%CI 0.54至0.93),中位无进展生存期延长3.7倍(14.4 vs 3.9个月;P=0.0019),HR为0.45(P=0.0047)。
  • 在三个乳腺癌队列中,非铂类治疗结局按预测HRD状态无显著差异,包括紫杉类治疗的转移性乳腺癌的完全缓解(AUC 0.39)和无进展生存期(HR 0.98,P=0.95)。
  • 通过迁移学习至高级别浆液性卵巢癌,在两个队列中DeepHRD预测的HRD样本一线铂类治疗后总生存期更优(HR 0.46;P=0.030),新辅助铂类治疗后总生存期更优(HR 0.49;P=0.015)。

关键数值与推荐

  • DeepHRD预测乳腺癌HRD的AUC为0.81(95%CI 0.77至0.85)。
  • 铂类治疗的转移性乳腺癌中,预测HRD者中位无进展生存期14.4个月 vs 3.9个月(P=0.0019),HR 0.45(P=0.0047)。
  • 高级别浆液性卵巢癌一线铂类治疗后总生存期HR 0.46(P=0.030),新辅助铂类治疗后HR 0.49(P=0.015)。

临床怎么用

  • DeepHRD可从常规H&E切片预测乳腺癌和卵巢癌的HRD,在多个外部队列、切片扫描仪和组织固定变量中验证。
  • 与分子检测相比,DeepHRD分类出多1.8至3.1倍的HRD患者。

局限性

  • 原文未报告局限性

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

PURPOSE: Cancers with homologous recombination deficiency (HRD) can benefit from platinum salts and poly(ADP-ribose) polymerase inhibitors. Standard diagnostic tests for detecting HRD require molecular profiling, which is not universally available. METHODS: We trained DeepHRD, a deep learning platform for predicting HRD from hematoxylin and eosin (H&E)-stained histopathological slides, using primary breast (n = 1,008) and ovarian (n = 459) cancers from The Cancer Genome Atlas (TCGA). DeepHRD was compared with four standard HRD molecular tests using breast (n = 349) and ovarian (n = 141) cancers from multiple independent data sets, including platinum-treated clinical cohorts with RECIST progression-free survival (PFS), complete response (CR), and overall survival (OS) endpoints. RESULTS: DeepHRD predicted HRD from held-out H&E-stained breast cancer slides in TCGA with an AUC of 0.81 (95% CI, 0.77 to 0.85). This performance was confirmed in two independent primary breast cancer cohorts (AUC, 0.76 [95% CI, 0.71 to 0.82]). In an external platinum-treated metastatic breast cancer cohort, samples predicted as HRD had higher complete CR (AUC, 0.76 [95% CI, 0.54 to 0.93]) with 3.7-fold increase in median PFS (14.4 v 3.9 months; P = .0019) and hazard ratio (HR) of 0.45 (P = .0047). There were no significant differences in nonplatinum treatment outcome by predicted HRD status in three breast cancer cohorts, including CR (AUC, 0.39) and PFS (HR, 0.98, P = .95) in taxane-treated metastatic breast cancer. Through transfer learning to high-grade serous ovarian cancer, DeepHRD-predicted HRD samples had better OS after first-line (HR, 0.46; P = .030) and neoadjuvant (HR, 0.49; P = .015) platinum therapy in two cohorts. CONCLUSION: DeepHRD can predict HRD in breast and ovarian cancers directly from routine H&E slides across multiple external cohorts, slide scanners, and tissue fixation variables. When compared with molecular testing, DeepHRD classified 1.8- to 3.1-fold more patients with HRD, which exhibited better OS in high-grade serous ovarian cancer and platinum-specific PFS in metastatic breast cancer.

来源:J Clin Oncol,查看原文。版权归原作者所有。

引用

  1. Bergstrom EN, Abbasi A, Díaz-Gay M, et al. Deep Learning Artificial Intelligence Predicts Homologous Recombination Deficiency and Platinum Response From Histologic Slides. J Clin Oncol. 2024. PMID: 39083703. doi:10.1200/JCO.23.02641

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。