文献速递乳腺技术与安全MR

跨空间尺度影像组学预测乳腺癌新辅助化疗病理完全缓解:多中心可解释MRI研究

Cross-Spatial-Scale Radiomics for Predicting Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer: A Multicenter, Interpretable MRI Study.
PubMed 文献 · Acad Radiol · 2026-08-08

本研究回顾性纳入4个中心658例接受新辅助化疗前动态增强T1加权MRI的乳腺癌患者,开发并外部验证TriSpace模型。该模型融合全瘤影像组学、瘤内异质性、瘤周浸润区及临床病理特征,预测病理完全缓解。TriSpace在各队列中均取得最高AUC,并显示出良好的校准度与净获益。

要点

  • 瘤内异质性单尺度预测效能最高,外部AUC达0.813和0.805。
  • 瘤周信号在3 mm处最强,随距离增加而衰减。
  • TriSpace融合多尺度信息,外部测试AUC为0.852和0.815。

核心结论

  • TriSpace通过整合跨空间尺度的互补肿瘤信息,提升了新辅助化疗前pCR预测效能,并在外部验证中表现稳定。

研究设计与样本

  • 回顾性四中心研究,纳入2018年2月至2025年4月接受新辅助化疗前动态增强T1加权MRI的658例乳腺癌患者。
  • 两个中心构成训练集276例和内部验证集117例,另两个中心构成外部测试集134例和131例。

关键影像表现/征象

  • 瘤内异质性是最强的单一空间尺度预测信号,外部AUC分别为0.813和0.805。
  • 瘤周信号在距肿瘤3 mm处预测效能最高,后随距离增加而下降。
  • 全瘤影像组学稳健性最低,外部AUC分别为0.628和0.597。

诊断标准与关键数值

  • TriSpace在训练、内部验证及两个外部测试队列中的AUC分别为0.946、0.887、0.852和0.815。
  • SHAP分析显示,在跨中心分布偏移导致临床病理变量效能减弱时,影像特征可起补偿作用。
  • TriSpace在9个亚组中保持判别能力,AUC范围为0.778至0.851。

临床应用与阅片要点

  • 瘤内异质性应是新辅助化疗疗效预测影像评估中的重点分析区域。
  • 瘤周3 mm范围内的影像特征可能包含与治疗反应相关的重要信息。
  • 全瘤影像组学单独用于pCR预测时稳健性有限,建议结合多尺度信息。

局限性

  • 研究为回顾性设计。
  • 仅使用治疗前动态增强T1加权MRI序列。

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)。

英文原文(摘要)· 点击展开

RATIONALE AND OBJECTIVES: Pathologic complete response (pCR) is a key endpoint after neoadjuvant chemotherapy (NAC) in breast cancer, but whole-tumor radiomics may dilute heterogeneous response signals. We developed and externally validated TriSpace, an interpretable MRI biomarker integrating global tumor, intratumoral, peritumoral, and clinicopathologic information for pretreatment pCR prediction.

METHODS: This retrospective four-center study included 658 patients who underwent pretreatment dynamic contrast-enhanced T1-weighted MRI before standard NAC (February 2018-April 2025). Patients from two centers formed training (n = 276) and internal validation (n = 117) sets; two other centers formed external test sets (n = 134 and n = 131). TriSpace fused whole-tumor radiomics, habitat-based intratumoral heterogeneity, the optimal peritumoral infiltration zone, and clinicopathologic features. Performance was evaluated using the area under the receiver operating characteristic curve (AUC), calibration, decision curve analysis, and SHAP.

RESULTS: Discrimination showed an inside-out hierarchy: intratumoral heterogeneity was the strongest single scale (external AUCs, 0.813 and 0.805), the peritumoral signal peaked at 3 mm and declined with distance, and whole-tumor radiomics was least robust (external AUCs, 0.628 and 0.597). TriSpace achieved the highest AUCs in all cohorts (0.946, 0.887, 0.852, and 0.815), with good calibration (all Hosmer-Lemeshow P >.05) and greater net benefit. SHAP indicated that imaging features compensated when clinicopathologic variables weakened under cross-center distribution shift; discrimination was maintained across nine subgroups (AUC range, 0.778-0.851).

CONCLUSION: TriSpace may improve interpretable pretreatment pCR prediction by integrating complementary tumor information across spatial scales, with consistent external performance.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Wang, Wang, Jie, et al. Cross-Spatial-Scale Radiomics for Predicting Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer: A Multicenter, Interpretable MRI Study. Acad Radiol. 2026. PMID: 42570910. doi:10.1016/j.acra.2026.07.038

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。