精准无创预测乳腺癌病理完全缓解

　　对于乳腺癌术前新辅助化疗患者，精准预测术后能否获得病理完全缓解有助于制定合适的手术策略。不过，目前仍然缺乏术前精准预测病理完全缓解的无创方法。

　　2023年3月24日，英国《柳叶刀》旗下 《临床医学》在线发表广东省人民医院黄育鸿①、朱腾①、王坤✉️，中山大学附属第一医院张小玲①、林颖✉️，佛山市第一人民医院李巍①、叶国麟✉️，汕头市中心医院吴智勇✉️等学者的原创研究报告，根据时间动态多模态磁共振成像数据，开发了一种人工智能深度学习影像组学模型，可在术前精准预测乳腺癌术后病理完全缓解，对不同分子亚型乳腺癌都取得良好的预测效果，将有助于对乳腺癌患者进行个体化的手术分层管理。

　　该多中心回顾研究对2015年7月～2021年12月广东省人民医院、中山大学附属第一医院、佛山市第一人民医院、汕头市中心医院连续1262例完成新辅助化疗并进行手术的患者进行回顾分析，收集患者新辅助化疗前和新辅助化疗后的多模态磁共振成像数据，将广东省人民医院409例患者作为训练集，中山大学附属第一医院340例患者、佛山市第一人民医院343例患者、汕头市中心医院170例患者作为3个独立验证集。从乳腺癌多模态磁共振成像分别提取高通量PyRadiomics影像组学特征和ResNet-50深层神经网络迁移学习特征，并采用逻辑回归、随机森林、支持向量机、多层感知器等多种机器学习算法，根据3类特定分子亚型（HER2阳性、激素受体阳性HER2阴性、三阴性）分别构建深度学习影像组学模型，以预测乳腺癌术前新辅助化疗后能否获得病理完全缓解，从而有助于为乳腺癌患者制定合适的手术方案。

　　结果发现，对于3个独立验证集的不同分子亚型乳腺癌，人工智能深度学习影像组学模型预测病理完全缓解真假阳性率曲线下面积分别为：

• 激素受体阳性HER2阴性：0.882、0.904、0.908（95%置信区间：0.779～0.985、0.817～0.991、0.776～1.0）

• HER2阳性：0.896、0.920、0.929（95%置信区间：0.842～0.949、0.876～0.965、0.881～0.978）

• 三阴性：0.837、0.873、0.901（95%置信区间：0.725～0.949、0.735～1.0、0.755～1.0）

　　该研究还发现，对比仅用新辅助化疗前或新辅助化疗后磁共振成像构建的单时间节点深度学习影像组学模型，联合新辅助化疗前后双时间节点的深度学习影像组学模型在独立验证集的曲线下面积和准确度都显著提升：

• 新辅助化疗前＋后：曲线下面积0.891、0.895、0.918，准确度85.00%、88.92%、88.82%

• 新辅助化疗前：曲线下面积0.779、0.780、0.784，准确度82.94%、71.42%、77.35%

• 新辅助化疗后：曲线下面积0.809、0.835、0.838，准确度82.94%、83.67%、82.35%

　　此外，决策曲线分析表明，深度学习影像组学模型可以在临床相关风险阈值范围内提高保乳手术率，对于3个独立验证集，根据模型的预测结果，可对多达80.00%、85.31%、86.30%的乳腺癌患者进行保乳手术而病理结果为病理完全缓解。对未获得病理完全缓解的患者，人工智能深度学习影像组学模型预测的特异度分别为87.39%、90.72%、91.50%，也可辅助乳腺外科医师做出合适的手术决策。

　　因此，该研究结果表明，基于新辅助化疗前后磁共振成像的人工智能深度学习影像组学模型，可为乳腺癌个体化手术管理提供无创精准的术前预测工具。

EClinicalMedicine. 2023 Mar 24;58:101899. IF: 17.033

Longitudinal MRI-based fusion novel model predicts pathological complete response in breast cancer treated with neoadjuvant chemotherapy: a multicenter, retrospective study.

YuHong Huang, Teng Zhu, XiaoLing Zhang, Wei Li, XingXing Zheng, MinYi Cheng, Fei Ji, LiuLu Zhang, CiQiu Yang, ZhiYong Wu, GuoLin Ye, Ying Lin, Kun Wang.

Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, Guangdong, China; The First Affiliated Hospital, Sun Yat-sen University, Guangzhou, China; The First People's Hospital of Foshan, Foshan, Guangdong, China; Shantou Central Hospital, Shantou, China.

BACKGROUND: Accurate identification of pCR to neoadjuvant chemotherapy (NAC) is essential for determining appropriate surgery strategy and guiding resection extent in breast cancer. However, a non-invasive tool to predict pCR accurately is lacking. Our study aims to develop ensemble learning models using longitudinal multiparametric MRI to predict pCR in breast cancer.

METHODS: From July 2015 to December 2021, we collected pre-NAC and post-NAC multiparametric MRI sequences per patient. We then extracted 14,676 radiomics and 4096 deep learning features and calculated additional delta-value features. In the primary cohort (n = 409), the inter-class correlation coefficient test, U-test, Boruta and the least absolute shrinkage and selection operator regression were used to select the most significant features for each subtype of breast cancer. Five machine learning classifiers were then developed to predict pCR accurately for each subtype. The ensemble learning strategy was used to integrate the single-modality models. The diagnostic performances of models were evaluated in the three external cohorts (n = 343, 170 and 340, respectively).

FINDINGS: A total of 1262 patients with breast cancer from four centers were enrolled in this study, and pCR rates were 10.6% (52/491), 54.3% (323/595) and 37.5% (66/176) in HR /HER2-, HER2 and TNBC subtype, respectively. Finally, 20, 15 and 13 features were selected to construct the machine learning models in HR /HER2-, HER2 and TNBC subtypes, respectively. The multi-Layer Perception (MLP) yields the best diagnostic performances in all subtypes. For the three subtypes, the stacking model integrating pre-, post- and delta-models yielded the highest AUCs of 0.959, 0.974 and 0.958 in the primary cohort, and AUCs of 0.882–0.908, 0.896–0.929 and 0.837–0.901 in the external validation cohorts, respectively. The stacking model had accuracies of 85.0%–88.9%, sensitivities of 80.0%–86.3%, and specificities of 87.4%–91.5% in the external validation cohorts.

INTERPRETATION: Our study established a novel tool to predict the responses of breast cancer to NAC and achieve excellent performance. The models could help to determine post-NAC surgery strategy for breast cancer.

FUNDING: This study is supported by grants from the National Natural Science Foundation of China (82171898, 82103093), the Deng Feng project of high-level hospital construction (DFJHBF202109), the Guangdong Basic and Applied Basic Research Foundation (grant number, 2020A1515010346, 2022A1515012277), the Science and Technology Planning Project of Guangzhou City (202002030236), the Beijing Medical Award Foundation (YXJL-2020-0941-0758), and the Beijing Science and Technology Innovation Medical Development Foundation (KC2022-ZZ-0091-5). Funding sources were not involved in the study design, data collection, analysis and interpretation, writing of the report, or decision to submit the article for publication.

KEYWORDS: Breast cancer, Multi-parametric MRI, Neoadjuvant chemotherapy, Pathological complete response, Longitudinal radiomics, Deep learning

DOI: 10.1016/j.eclinm.2023.101899