Department of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands.
Department of Radiology, The Netherlands Cancer Institute, Amsterdam, The Netherlands.
J Magn Reson Imaging. 2023 Jan;57(1):97-110. doi: 10.1002/jmri.28273. Epub 2022 May 28.
Breast cancer response to neoadjuvant chemotherapy (NAC) is typically evaluated through the assessment of tumor size reduction after a few cycles of NAC. In case of treatment ineffectiveness, this results in the patient suffering potentially severe secondary effects without achieving any actual benefit.
To identify patients achieving pathologic complete response (pCR) after NAC by spatio-temporal radiomic analysis of dynamic contrast-enhanced (DCE) MRI images acquired before treatment.
Single-center, retrospective.
A total of 251 DCE-MRI pretreatment images of breast cancer patients.
FIELD STRENGTH/SEQUENCE: 1.5 T/3 T, T1-weighted DCE-MRI.
Tumor and peritumoral regions were segmented, and 348 radiomic features that quantify texture temporal variation, enhancement kinetics heterogeneity, and morphology were extracted. Based on subsets of features identified through forward selection, machine learning (ML) logistic regression models were trained separately with all images and stratifying on cancer molecular subtype and validated with leave-one-out cross-validation.
Feature significance was assessed using the Mann-Whitney U-test. Significance of the area under the receiver operating characteristics (ROC) curve (AUC) of the ML models was assessed using the associated 95% confidence interval (CI). Significance threshold was set to 0.05, adjusted with Bonferroni correction.
Nine features related to texture temporal variation and enhancement kinetics heterogeneity were significant in the discrimination of cases achieving pCR vs. non-pCR. The ML models achieved significant AUC of 0.707 (all cancers, n = 251, 59 pCR), 0.824 (luminal A, n = 107, 14 pCR), 0.823 (luminal B, n = 47, 15 pCR), 0.844 (HER2 enriched, n = 25, 11 pCR), 0.803 (triple negative, n = 72, 19 pCR).
Differences in imaging phenotypes were found between complete and noncomplete responders. Furthermore, ML models trained per cancer subtype achieved high performance in classifying pCR vs. non-pCR cases. They may, therefore, have potential to help stratify patients according to the level of response predicted before treatment, pending further validation with larger prospective cohorts.
4 TECHNICAL EFFICACY: Stage 4.
新辅助化疗（NAC）后乳腺癌的反应通常通过 NAC 几个周期后肿瘤大小缩小来评估。如果治疗无效，患者可能会遭受潜在的严重副作用，而没有任何实际获益。
通过对治疗前获取的动态对比增强（DCE）MRI 图像进行时空放射组学分析，识别 NAC 后达到病理完全缓解（pCR）的患者。
单中心、回顾性。
共 251 例乳腺癌患者的 DCE-MRI 预处理图像。
磁场强度/序列：1.5T/3T，T1 加权 DCE-MRI。
对肿瘤和肿瘤周围区域进行分割，提取 348 个定量纹理时空变化、增强动力学异质性和形态的放射组学特征。基于通过前向选择确定的特征子集，使用所有图像分别训练机器学习（ML）逻辑回归模型，并根据癌症分子亚型进行分层，使用留一法交叉验证进行验证。
使用曼-惠特尼 U 检验评估特征的显著性。使用相关的 95%置信区间（CI）评估 ML 模型的接收者操作特征（ROC）曲线下面积（AUC）的显著性。显著性阈值设为 0.05，使用 Bonferroni 校正进行调整。
在区分达到 pCR 与非 pCR 的病例中，有 9 个与纹理时空变化和增强动力学异质性相关的特征具有显著意义。ML 模型在所有癌症（n=251）、59 例 pCR）、0.824（luminal A，n=107，14 例 pCR）、0.823（luminal B，n=47，15 例 pCR）、0.844（HER2 富集，n=25，11 例 pCR）、0.803（三阴性，n=72，19 例 pCR）中均达到了显著的 AUC 值 0.707。
完全缓解者和非完全缓解者之间存在影像学表型差异。此外，根据癌症亚型训练的 ML 模型在区分 pCR 与非 pCR 病例方面表现出了较高的性能。因此，在更大的前瞻性队列中进一步验证之前，它们可能有助于根据治疗前预测的反应水平对患者进行分层。
4 级技术效能：4 级。
