Liang Ting, Shen Junhui, Wang Jiexin, Liao Weilin, Zhang Zhi, Liu Juanjuan, Feng Zhanwu, Pei Shufang, Liu Kebing
Department of Ultrasound, The First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou University of Chinese Medicine, Guangzhou, China.
Department of Ultrasound, Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, Guangzhou, China.
Quant Imaging Med Surg. 2023 Apr 1;13(4):2634-2646. doi: 10.21037/qims-22-877. Epub 2023 Mar 3.
The American College of Radiology Breast Imaging Reporting and Data System (ACR BI-RADS) used with ultrasonography cannot guide the individual management of solid breast tumors, but preoperative core biopsy categories (CBCs) can. We aimed to use machine learning to analyze clinical and ultrasonic features for predicting CBCs and to aid in the development of a new ultrasound (US) imaging reporting system for solid tumors of the breast.
This retrospective study included women with solid breast tumors who underwent US-guided core needle biopsy from March 1, 2019, to December 31, 2019. All patients were randomly assigned to a training or validation cohort (7:3 ratio). CBC was predicted using 5 machine learning models: random forest (RF), support vector machine (SVM), k-nearest-neighbor (KNN), multilayer perceptron (MLP), and ridge regression (RR). In the validation cohort, the area under the curve (AUC) and accuracy were ascertained for every algorithm. Based on AUC values, the optimal algorithm was determined, and the features' importance was depicted.
A total of 1,082 female patients were included (age range, 12-96 years; mean age ± standard deviation, 42.22±13.37 years). The proportion of the 4 CBCs was 4% (44/1,185) for the B1 group, 60% (714/1,185) for the B2 group, 5% (57/1,185) for the B3 group, and 31% (370/1,185) for the B5 group. In the validation cohort, AUCs of the optimal algorithm constructed RF were 0.78, 0.88, 0.64, and 0.92 for B1, B2, B3, and B5, respectively, with an accuracy of 0.82.
Machine learning could strongly predict CBC, particularly in B2 and B5 categories of solid breast tumors, with RF being the optimal machine learning model.
美国放射学会乳腺影像报告和数据系统（ACR BI-RADS）与超声检查联合使用时，无法指导实性乳腺肿瘤的个体化管理，但术前粗针活检分类（CBC）可以。我们旨在利用机器学习分析临床和超声特征以预测CBC，并助力开发一种针对乳腺实性肿瘤的新型超声（US）成像报告系统。
这项回顾性研究纳入了2019年3月1日至2019年12月31日期间接受US引导下粗针活检的乳腺实性肿瘤女性患者。所有患者被随机分配到训练或验证队列（比例为7:3）。使用5种机器学习模型预测CBC：随机森林（RF）、支持向量机（SVM）、k近邻（KNN）、多层感知器（MLP）和岭回归（RR）。在验证队列中，确定每种算法的曲线下面积（AUC）和准确率。基于AUC值，确定最优算法，并描述特征的重要性。
共纳入1082例女性患者（年龄范围12 - 96岁；平均年龄±标准差，42.22±13.37岁）。B1组4种CBC的比例为4%（44/1185），B2组为60%（714/1185），B3组为5%（57/1185），B5组为31%（370/1185）。在验证队列中，构建的最优算法RF的AUC在B1、B2、B3和B5组中分别为0.78、0.88、0.64和0.92，准确率为0.82。
机器学习能够有力地预测CBC，尤其是在乳腺实性肿瘤的B2和B5类别中，RF是最优的机器学习模型。
