School of Medical Imaging, Binzhou Medical University, No. 346 Guanhai Road, Yantai, Shandong, 264003, China; Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, Yantai, Shandong, 264000, China.
Department of Radiology, Yantai Yuhuangding Hospital, Qingdao University, Yantai, Shandong, 264000, China.
EBioMedicine. 2024 Sep;107:105311. doi: 10.1016/j.ebiom.2024.105311. Epub 2024 Aug 26.
The accurate evaluation of axillary lymph node (ALN) response to neoadjuvant chemotherapy (NAC) in breast cancer holds great value. This study aimed to develop an artificial intelligence system utilising multiregional dynamic contrast-enhanced MRI (DCE-MRI) and clinicopathological characteristics to predict axillary pathological complete response (pCR) after NAC in breast cancer.
This study included retrospective and prospective datasets from six medical centres in China between May 2018 and December 2023. A fully automated integrated system based on deep learning (FAIS-DL) was built to perform tumour and ALN segmentation and axillary pCR prediction sequentially. The predictive performance of FAIS-DL was assessed using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. RNA sequencing analysis were conducted on 45 patients to explore the biological basis of FAIS-DL.
1145 patients (mean age, 50 years ±10 [SD]) were evaluated. Among these patients, 506 were in the training and validation sets (axillary pCR rate of 40.3%), 127 in the internal test set (axillary pCR rate of 37.8%), 414 in the pooled external test set (axillary pCR rate of 48.8%), and 98 in the prospective test set (axillary pCR rate of 43.9%). For predicting axillary pCR, FAIS-DL achieved AUCs of 0.95, 0.93, and 0.94 in the internal test set, pooled external test set, and prospective test set, respectively, which were also significantly higher than those of the clinical model and deep learning models based on single-regional DCE-MRI (all P < 0.05, DeLong test). In the pooled external and prospective test sets, the FAIS-DL decreased the unnecessary axillary lymph node dissection rate from 47.9% to 6.8%, and increased the benefit rate from 52.2% to 86.5%. RNA sequencing analysis revealed that high FAIS-DL scores were associated with the upregulation of immune-mediated genes and pathways.
FAIS-DL has demonstrated satisfactory performance in predicting axillary pCR, which may guide the formulation of personalised treatment regimens for patients with breast cancer in clinical practice.
This study was supported by the National Natural Science Foundation of China (82371933), National Natural Science Foundation of Shandong Province of China (ZR2021MH120), Mount Taishan Scholars and Young Experts Program (tsqn202211378), Key Projects of China Medicine Education Association (2022KTM030), China Postdoctoral Science Foundation (314730), and Beijing Postdoctoral Research Foundation (2023-zz-012).
准确评估乳腺癌新辅助化疗（NAC）后腋窝淋巴结（ALN）的反应具有重要价值。本研究旨在开发一种利用多区域动态对比增强磁共振成像（DCE-MRI）和临床病理特征的人工智能系统，预测乳腺癌 NAC 后的腋窝病理完全缓解（pCR）。
本研究纳入了 2018 年 5 月至 2023 年 12 月期间中国六家医疗中心的回顾性和前瞻性数据集。建立了一个基于深度学习的全自动化集成系统（FAIS-DL），用于依次进行肿瘤和 ALN 分割以及腋窝 pCR 预测。使用接收者操作特征曲线下的面积（AUC）、准确性、敏感度和特异性评估 FAIS-DL 的预测性能。对 45 名患者进行 RNA 测序分析，以探讨 FAIS-DL 的生物学基础。
共评估了 1145 名患者（平均年龄 50 岁±10[标准差]）。其中，506 名患者在训练和验证集（腋窝 pCR 率为 40.3%），127 名患者在内测集（腋窝 pCR 率为 37.8%），414 名患者在汇总外部测试集（腋窝 pCR 率为 48.8%），98 名患者在前瞻性测试集（腋窝 pCR 率为 43.9%）。对于预测腋窝 pCR，FAIS-DL 在内部测试集、汇总外部测试集和前瞻性测试集的 AUC 分别为 0.95、0.93 和 0.94，均显著高于临床模型和基于单区域 DCE-MRI 的深度学习模型（均 P<0.05，DeLong 检验）。在汇总外部和前瞻性测试集中，FAIS-DL 将不必要的腋窝淋巴结清扫率从 47.9%降低到 6.8%，获益率从 52.2%提高到 86.5%。RNA 测序分析显示，高 FAIS-DL 评分与免疫介导基因和途径的上调有关。
FAIS-DL 在预测腋窝 pCR 方面表现出令人满意的性能，可能为乳腺癌患者的个体化治疗方案制定提供指导。
本研究得到了中国国家自然科学基金（82371933）、中国山东省自然科学基金（ZR2021MH120）、泰山学者和青年专家计划（tsqn202211378）、中国医学教育协会重点项目（2022KTM030）、中国博士后科学基金（314730）和北京博士后研究基金（2023-zz-012）的支持。
