Yao Jiejie, Jia Xiaohong, Zhou Wei, Zhu Ying, Chen Xiaosong, Zhan Weiwei, Zhou Jianqiao
Department of Ultrasound, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
Department of Comprehensive Breast Health Center, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai, China.
iScience. 2024 Aug 13;27(9):110716. doi: 10.1016/j.isci.2024.110716. eCollection 2024 Sep 20.
To explore machine learning (ML)-based breast tumor peritumoral (P) and intratumoral ultrasound radiomics signatures (IURS) for predicting axillary response to neoadjuvant chemotherapy (NAC) in patients with breast cancer (BC) with node-positive. A total of 435 patients were divided into hormone receptor (HR)+/human epidermal growth factor receptor (HER)2-, HER2+, and triple-negative (TN) subtypes. ML classifiers including random forest (RF), support vector machine (SVM), and linear discriminant analysis (LDA) were applied to construct PURS, IURS, and the combined P-IURS radiomics models. SVM of the TN subtype obtained the most favorable performance with an AUC of 0.917 (95%CI: 0.859, 0.960) in PURS models, RF of the HER2+ subtype yielded the highest efficacy in IURS models [AUC = 0.935 (95%CI: 0.843, 0.976)]. The RF-based combined P-IURS model of the HER2+ subtype improved the efficacy to a maximum AUC of 0.952 (95%CI: 0.868, 0.994). ML-based US radiomics can be a promising biomarker to predict axillary response.
为探索基于机器学习（ML）的乳腺癌（BC）伴淋巴结阳性患者的瘤周（P）和瘤内超声放射组学特征（IURS），以预测新辅助化疗（NAC）后的腋窝反应。共435例患者被分为激素受体（HR）+/人表皮生长因子受体（HER）2-、HER2+和三阴性（TN）亚型。应用包括随机森林（RF）、支持向量机（SVM）和线性判别分析（LDA）在内的ML分类器构建PURS、IURS以及联合P-IURS放射组学模型。TN亚型的SVM在PURS模型中表现最佳，AUC为0.917（95%CI：0.859，0.960）；HER2+亚型的RF在IURS模型中疗效最高[AUC = 0.935（95%CI：0.843，0.976）]。HER2+亚型基于RF的联合P-IURS模型将疗效提高到最大AUC为0.952（95%CI：0.868，0.994）。基于ML的超声放射组学可能是预测腋窝反应的一种有前景的生物标志物。
