Department of Scientific Research and Academic, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, China.
Department of Biomedical Engineering, China Medical University, Shenyang, China.
J Magn Reson Imaging. 2024 Feb;59(2):613-625. doi: 10.1002/jmri.28776. Epub 2023 May 18.
Radiomics has been applied for assessing lymphovascular invasion (LVI) in patients with breast cancer. However, associations between features from peritumoral regions and the LVI status were not investigated.
To investigate the value of intra- and peritumoral radiomics for assessing LVI, and to develop a nomogram to assist in making treatment decisions.
Retrospective.
Three hundred and sixteen patients were enrolled from two centers and divided into training (N = 165), internal validation (N = 83), and external validation (N = 68) cohorts.
FIELD STRENGTH/SEQUENCE: 1.5 T and 3.0 T/dynamic contrast-enhanced (DCE) and diffusion-weighted imaging (DWI).
Radiomics features were extracted and selected based on intra- and peritumoral breast regions in two magnetic resonance imaging (MRI) sequences to create the multiparametric MRI combined radiomics signature (RS-DCE plus DWI). The clinical model was built with MRI-axillary lymph nodes (MRI ALN), MRI-reported peritumoral edema (MPE), and apparent diffusion coefficient (ADC). The nomogram was constructed with RS-DCE plus DWI, MRI ALN, MPE, and ADC.
Intra- and interclass correlation coefficient analysis, Mann-Whitney U test, and least absolute shrinkage and selection operator regression were used for feature selection. Receiver operating characteristic and decision curve analyses were applied to compare performance of the RS-DCE plus DWI, clinical model, and nomogram.
A total of 10 features were found to be associated with LVI, 3 from intra- and 7 from peritumoral areas. The nomogram showed good performance in the training (AUCs, nomogram vs. clinical model vs. RS-DCE plus DWI, 0.884 vs. 0.695 vs. 0.870), internal validation (AUCs, nomogram vs. clinical model vs. RS-DCE plus DWI, 0.813 vs. 0.695 vs. 0.794), and external validation (AUCs, nomogram vs. clinical model vs. RS-DCE plus DWI, 0.862 vs. 0.601 vs. 0.849) cohorts.
The constructed preoperative nomogram might effectively assess LVI.
3 TECHNICAL EFFICACY: Stage 2.
放射组学已被应用于评估乳腺癌患者的淋巴管侵犯（LVI）。然而，瘤周区域特征与 LVI 状态之间的相关性尚未得到研究。
探讨瘤内和瘤周放射组学特征在评估 LVI 中的价值，并建立列线图以辅助治疗决策。
回顾性。
本研究纳入了来自两个中心的 316 名患者，并将其分为训练集（N=165）、内部验证集（N=83）和外部验证集（N=68）。
磁场强度/序列：1.5T 和 3.0T/动态对比增强（DCE）和弥散加权成像（DWI）。
在两个磁共振成像（MRI）序列中，基于瘤内和瘤周乳腺区域提取和选择放射组学特征，以创建多参数 MRI 联合放射组学特征（DCE 加 DWI）。使用 MRI-腋窝淋巴结（MRI ALN）、MRI 报告的瘤周水肿（MPE）和表观扩散系数（ADC）建立临床模型。使用 RS-DCE 加 DWI、MRI ALN、MPE 和 ADC 构建列线图。
使用组内和组间相关系数分析、Mann-Whitney U 检验和最小绝对值收缩和选择算子回归进行特征选择。应用接受者操作特征和决策曲线分析比较 RS-DCE 加 DWI、临床模型和列线图的性能。
共发现与 LVI 相关的 10 个特征，其中 3 个来自瘤内区域，7 个来自瘤周区域。列线图在训练集（AUC，列线图与临床模型与 RS-DCE 加 DWI，0.884 与 0.695 与 0.870）、内部验证集（AUC，列线图与临床模型与 RS-DCE 加 DWI，0.813 与 0.695 与 0.794）和外部验证集（AUC，列线图与临床模型与 RS-DCE 加 DWI，0.862 与 0.601 与 0.849）中均表现出良好的性能。
构建的术前列线图可能能够有效地评估 LVI。
3 级技术功效：2 级。
