Xie Li, Liu Zhen, Pei Chong, Liu Xiao, Cui Ya-Yun, He Nian-An, Hu Lei
Department of Ultrasound, The First Affiliated Hospital of University of Science and Technology of China (USTC), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China.
Department of Computing, Hebin Intelligent Robots Co., LTD., Hefei, China.
Front Oncol. 2023 Feb 14;13:1099650. doi: 10.3389/fonc.2023.1099650. eCollection 2023.
Our aim was to develop dual-modal CNN models based on combining conventional ultrasound (US) images and shear-wave elastography (SWE) of peritumoral region to improve prediction of breast cancer.
We retrospectively collected US images and SWE data of 1271 ACR- BIRADS 4 breast lesions from 1116 female patients (mean age ± standard deviation, 45.40 ± 9.65 years). The lesions were divided into three subgroups based on the maximum diameter (MD): ≤15 mm; >15 mm and ≤25 mm; >25 mm. We recorded lesion stiffness (SWV1) and 5-point average stiffness of the peritumoral tissue (SWV5). The CNN models were built based on the segmentation of different widths of peritumoral tissue (0.5 mm, 1.0 mm, 1.5 mm, 2.0 mm) and internal SWE image of the lesions. All single-parameter CNN models, dual-modal CNN models, and quantitative SWE parameters in the training cohort (971 lesions) and the validation cohort (300 lesions) were assessed by receiver operating characteristic (ROC) curve.
The US + 1.0 mm SWE model achieved the highest area under the ROC curve (AUC) in the subgroup of lesions with MD ≤15 mm in both the training (0.94) and the validation cohorts (0.91). In the subgroups with MD between15 and 25 mm and above 25 mm, the US + 2.0 mm SWE model achieved the highest AUCs in both the training cohort (0.96 and 0.95, respectively) and the validation cohort (0.93 and 0.91, respectively).
The dual-modal CNN models based on the combination of US and peritumoral region SWE images allow accurate prediction of breast cancer.
我们的目标是开发基于结合肿瘤周围区域的传统超声（US）图像和剪切波弹性成像（SWE）的双模态卷积神经网络（CNN）模型，以改善乳腺癌的预测。
我们回顾性收集了1116例女性患者（平均年龄±标准差，45.40±9.65岁）的1271个美国放射学会（ACR）乳腺影像报告和数据系统（BIRADS）4类乳腺病变的US图像和SWE数据。根据最大直径（MD）将病变分为三个亚组：≤15mm；>15mm且≤25mm；>25mm。我们记录了病变硬度（SWV1）和肿瘤周围组织的5点平均硬度（SWV5）。基于不同宽度（0.5mm、1.0mm、1.5mm、2.0mm）的肿瘤周围组织分割和病变内部SWE图像构建了CNN模型。通过受试者操作特征（ROC）曲线评估训练队列（971个病变）和验证队列（300个病变）中的所有单参数CNN模型、双模态CNN模型和定量SWE参数。
在MD≤15mm的病变亚组中，US + 1.0mm SWE模型在训练队列（0.94）和验证队列（0.91）中均达到了ROC曲线下面积（AUC）的最大值。在MD介于15至25mm之间和大于25mm的亚组中，US + 2.0mm SWE模型在训练队列（分别为0.96和0.95）和验证队列（分别为0.93和0.91）中均达到了最高的AUC。
基于US和肿瘤周围区域SWE图像相结合的双模态CNN模型能够准确预测乳腺癌。
