From the Department of Radiology, Guangdong Provincial People’s Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, No. 106 Zhongshan Er Road, Guangzhou 510080, Guangdong, China (Z.S., Z.X., H.L., Chen Liu, X.C., Chunling Liu, C. Liang, C. Lu, Y.C., C.H., Z.L.); Guangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Guangdong, China (Z.S., Y.C.); Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application, Guangdong, China (Z.S., Z.X., H.L., Chen Liu, X.C., C. Liang, C. Lu, Y.C., C.H., Z.L.); Department of Medical Imaging, Nanfang Hospital, Southern Medical University, Guangzhou, China (X.H.); Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, Guangzhou, China (Z.C., J.S.); School of Medicine, South China University of Technology, Guangzhou, China (Z.X., H.L.); The Second School of Clinical Medicine, Southern Medical University, Guangzhou, China (Chen Liu, X.C.); Department of Radiology, Shanxi Cancer Hospital, Shanxi Medical University, Taiyuan, China (Y.C.); and Department of Radiology, The Affiliated Cancer Hospital of Zhengzhou University & Henan Cancer Hospital, Zhengzhou, China (J.Q.).
Radiology. 2023 Jul;308(1):e222830. doi: 10.1148/radiol.222830.
Background Breast cancer is highly heterogeneous, resulting in different treatment responses to neoadjuvant chemotherapy (NAC) among patients. A noninvasive quantitative measure of intratumoral heterogeneity (ITH) may be valuable for predicting treatment response. Purpose To develop a quantitative measure of ITH on pretreatment MRI scans and test its performance for predicting pathologic complete response (pCR) after NAC in patients with breast cancer. Materials and Methods Pretreatment MRI scans were retrospectively acquired in patients with breast cancer who received NAC followed by surgery at multiple centers from January 2000 to September 2020. Conventional radiomics (hereafter, C-radiomics) and intratumoral ecological diversity features were extracted from the MRI scans, and output probabilities of imaging-based decision tree models were used to generate a C-radiomics score and ITH index. Multivariable logistic regression analysis was used to identify variables associated with pCR, and significant variables, including clinicopathologic variables, C-radiomics score, and ITH index, were combined into a predictive model for which performance was assessed using the area under the receiver operating characteristic curve (AUC). Results The training data set was comprised of 335 patients (median age, 48 years [IQR, 42-54 years]) from centers A and B, and 590, 280, and 384 patients (median age, 48 years [IQR, 41-55 years]) were included in the three external test data sets. Molecular subtype (odds ratio [OR] range, 4.76-8.39 [95% CI: 1.79, 24.21]; all < .01), ITH index (OR, 30.05 [95% CI: 8.43, 122.64]; < .001), and C-radiomics score (OR, 29.90 [95% CI: 12.04, 81.70]; < .001) were independently associated with the odds of achieving pCR. The combined model showed good performance for predicting pCR to NAC in the training data set (AUC, 0.90) and external test data sets (AUC range, 0.83-0.87). Conclusion A model that combined an index created from pretreatment MRI-based imaging features quantitating ITH, C-radiomics score, and clinicopathologic variables showed good performance for predicting pCR to NAC in patients with breast cancer. © RSNA, 2023 See also the editorial by Rauch in this issue.
背景 乳腺癌具有高度异质性，导致患者对新辅助化疗（NAC）的治疗反应不同。一种肿瘤内异质性（ITH）的无创定量测量方法可能对预测治疗反应有价值。目的 开发一种基于预处理 MRI 扫描的 ITH 定量测量方法，并在多个中心接受 NAC 治疗后手术的乳腺癌患者中测试其对预测病理完全缓解（pCR）的性能。材料与方法 回顾性收集了 2000 年 1 月至 2020 年 9 月在多个中心接受 NAC 治疗后手术的乳腺癌患者的预处理 MRI 扫描。从 MRI 扫描中提取常规放射组学（以下简称 C-放射组学）和肿瘤内生态多样性特征，并使用基于成像的决策树模型的输出概率生成 C-放射组学评分和 ITH 指数。多变量逻辑回归分析用于确定与 pCR 相关的变量，将与 pCR 相关的变量（包括临床病理变量、C-放射组学评分和 ITH 指数）结合到预测模型中，使用受试者工作特征曲线下面积（AUC）评估其性能。结果 训练数据集由来自中心 A 和 B 的 335 名患者（中位年龄，48 岁[IQR，42-54 岁]）组成，三个外部测试数据集分别纳入 590、280 和 384 名患者（中位年龄，48 岁[IQR，41-55 岁]）。分子亚型（比值比范围，4.76-8.39[95%CI：1.79，24.21]；均<.01）、ITH 指数（比值比，30.05[95%CI：8.43，122.64]；<.001）和 C-放射组学评分（比值比，29.90[95%CI：12.04，81.70]；<.001）与实现 pCR 的几率独立相关。联合模型在训练数据集（AUC，0.90）和外部测试数据集（AUC 范围，0.83-0.87）中对预测 NAC 后的 pCR 具有良好的性能。结论 一种基于 MRI 扫描的成像特征创建的指数、C-放射组学评分和临床病理变量的组合模型，对预测乳腺癌患者接受 NAC 后的 pCR 具有良好的性能。
Quant Imaging Med Surg. 2025-9-1
BMC Med Imaging. 2025-7-4
Zotero 插件