Zhu Yunpei, Dou Yanping, Qin Ling, Wang Hui, Wen Zhihong
Ultrasound Department, First Affiliated Hospital of Dalian Medical University, Dalian City, Liaoning Province, China.
Radiology Department, Dalian Fifth People's Hospital, Dalian City, Liaoning Province, China.
J Ultrasound Med. 2023 Feb;42(3):649-664. doi: 10.1002/jum.16061. Epub 2022 Jul 19.
The objective of this research was to develop and validate an ultrasound-based radiomics nomogram for the pre-operative assessment of Ki-67 in breast cancer (BC).
From December 2016 to December 2018, 515 patients with invasive ductal breast cancer who received two-dimensional (2D) ultrasound and Ki-67 examination were studied and analyzed retrospectively. The dataset was distributed at random into a training cohort (n = 360) and a test cohort (n = 155) in the ratio of 7:3. Each tumor region of interest was defined based on 2D ultrasound images and radiomics features were extracted. ANOVA, maximum correlation minimum redundancy (mRMR) algorithm, and minimum absolute shrinkage and selection operator (LASSO) were performed to pick features, and independent clinical predictors were integrated with radscore to construct the nomogram for predicting Ki-67 index by univariate and multivariate logistic regression analysis. The performance and utility of the models were evaluated by plotting receiver operating characteristic (ROC) curves, decision curve analysis (DCA), and calibration curves.
In the testing cohort, the area under the receiver characteristic curve (AUC) of the nomogram was 0.770 (95% confidence interval, 0.690-0.860). In both cohorts, the nomogram outperformed both the clinical model and the radiomics model (P < .05 according to the DeLong test). The analysis of DCA proved that the model has clinical utility.
The nomogram based on 2D ultrasound images offered an approach for predicting Ki-67 in BC.
本研究的目的是开发并验证一种基于超声的放射组学列线图，用于乳腺癌（BC）术前评估Ki-67。
回顾性研究并分析了2016年12月至2018年12月期间接受二维（2D）超声和Ki-67检测的515例浸润性导管癌患者。数据集按7:3的比例随机分为训练队列（n = 360）和测试队列（n = 155）。基于2D超声图像定义每个肿瘤感兴趣区域，并提取放射组学特征。采用方差分析、最大相关最小冗余（mRMR）算法和最小绝对收缩与选择算子（LASSO）进行特征选择，并将独立的临床预测因子与放射学评分相结合，通过单因素和多因素逻辑回归分析构建预测Ki-67指数的列线图。通过绘制受试者操作特征（ROC）曲线、决策曲线分析（DCA）和校准曲线来评估模型的性能和实用性。
在测试队列中，列线图的受试者特征曲线下面积（AUC）为0.770（95%置信区间，0.690 - 0.860）。在两个队列中，列线图的表现均优于临床模型和放射组学模型（根据DeLong检验，P < 0.05）。DCA分析证明该模型具有临床实用性。
基于2D超声图像的列线图为预测BC中的Ki-67提供了一种方法。
