Liao Jiayi, Xu Zeyan, Xie Yu, Liang Yanting, Hu Qingru, Liu Chunling, Yan Lifen, Diao Wenjun, Liu Zaiyi, Wu Lei, Liang Changhong
Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China.
Department of Radiology, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
J Magn Reson Imaging. 2025 Mar;61(3):1221-1231. doi: 10.1002/jmri.29554. Epub 2024 Aug 22.
Pathological axillary lymph node (pALN) burden is an important factor for treatment decision-making in clinical T1-T2 (cT1-T2) stage breast cancer. Preoperative assessment of the pALN burden and prognosis aids in the individualized selection of therapeutic approaches.
To develop and validate a machine learning (ML) model based on clinicopathological and MRI characteristics for assessing pALN burden and survival in patients with cT1-T2 stage breast cancer.
Retrospective.
A total of 506 females (range: 24-83 years) with cT1-T2 stage breast cancer from two institutions, forming the training (N = 340), internal validation (N = 85), and external validation cohorts (N = 81), respectively.
FIELD STRENGTH/SEQUENCE: This study used 1.5-T, axial fat-suppressed T2-weighted turbo spin-echo sequence and axial three-dimensional dynamic contrast-enhanced fat-suppressed T1-weighted gradient echo sequence.
Four ML methods (eXtreme Gradient Boosting [XGBoost], Support Vector Machine, k-Nearest Neighbor, Classification and Regression Tree) were employed to develop models based on clinicopathological and MRI characteristics. The performance of these models was evaluated by their discriminative ability. The best-performing model was further analyzed to establish interpretability and used to calculate the pALN score. The relationships between the pALN score and disease-free survival (DFS) were examined.
Chi-squared test, Fisher's exact test, univariable logistic regression, area under the curve (AUC), Delong test, net reclassification improvement, integrated discrimination improvement, Hosmer-Lemeshow test, log-rank, Cox regression analyses, and intraclass correlation coefficient were performed. A P-value <0.05 was considered statistically significant.
The XGB II model, developed based on the XGBoost algorithm, outperformed the other models with AUCs of 0.805, 0.803, and 0.818 in the three cohorts. The Shapley additive explanation plot indicated that the top variable in the XGB II model was the Node Reporting and Data System score. In multivariable Cox regression analysis, the pALN score was significantly associated with DFS (hazard ratio: 4.013, 95% confidence interval: 1.059-15.207).
The XGB II model may allow to evaluate pALN burden and could provide prognostic information in cT1-T2 stage breast cancer patients.
3 TECHNICAL EFFICACY: Stage 2.
病理性腋窝淋巴结（pALN）负荷是临床T1-T2（cT1-T2）期乳腺癌治疗决策的重要因素。术前评估pALN负荷和预后有助于个体化选择治疗方法。
开发并验证一种基于临床病理和MRI特征的机器学习（ML）模型，用于评估cT1-T2期乳腺癌患者的pALN负荷和生存率。
回顾性研究。
来自两个机构的共506名女性（年龄范围：24-83岁），她们患有cT1-T2期乳腺癌，分别组成训练队列（N = 340）、内部验证队列（N = 85）和外部验证队列（N = 81）。
场强/序列：本研究使用1.5-T、轴向脂肪抑制T2加权快速自旋回波序列和轴向三维动态对比增强脂肪抑制T1加权梯度回波序列。
采用四种ML方法（极端梯度提升[XGBoost]、支持向量机、k近邻、分类与回归树）基于临床病理和MRI特征开发模型。通过这些模型的判别能力评估其性能。对表现最佳的模型进行进一步分析以建立可解释性，并用于计算pALN评分。研究pALN评分与无病生存期（DFS）之间的关系。
进行卡方检验、Fisher精确检验、单变量逻辑回归、曲线下面积（AUC）、德龙检验、净重新分类改善、综合判别改善、Hosmer-Lemeshow检验、对数秩检验、Cox回归分析和组内相关系数分析。P值<0.05被认为具有统计学意义。
基于XGBoost算法开发的XGB II模型在三个队列中的AUC分别为0.805、0.803和0.818，优于其他模型。Shapley加性解释图表明，XGB II模型中的首要变量是淋巴结报告和数据系统评分。在多变量Cox回归分析中，pALN评分与DFS显著相关（风险比：4.013，95%置信区间：1.059-15.207）。
XGB II模型可用于评估cT1-T2期乳腺癌患者的pALN负荷，并能提供预后信息。
3 技术疗效：2级
