La Rocca Ludovica Rita, Caruso Martina, Stanzione Arnaldo, Rocco Nicola, Pellegrino Tommaso, Russo Daniela, Salatiello Maria, de Giorgio Andrea, Pastore Roberta, Maurea Simone, Brunetti Arturo, Cuocolo Renato, Romeo Valeria
Department of Advanced Biomedical Sciences, University of Naples Federico II, Naples, Italy.
Department of Advanced Biomedical Sciences, University of Naples Federico II, Naples, Italy.
Eur J Radiol. 2024 Dec;181:111795. doi: 10.1016/j.ejrad.2024.111795. Epub 2024 Oct 18.
To build and validate a combined radiomics and machine learning (ML) approach using B-mode US and SWE images to differentiate benign from malignant solid breast lesions (BLs) and compare its performance with that of an expert radiologist.
Patients with at least one BI-RADS 2-6 BL who performed breast US integrated with SWE were retrospectively included. B-mode US and SWE images were manually segmented to extract radiomics features. A multi-step feature selection process was performed and a predictive model built using the Logistic Regression algorithm. The diagnostic accuracy was evaluated with the AUC and Matthews Correlation Coefficient (MCC) metrics. The performance of the ML classifier was compared to that of an expert radiologist.
427 Bls were included and divided into a training (286 BLs, of which 127 benign and 159 malignant) and a test set (141 BLs, of which 59 benign and 82 malignant). Of 1098 features extracted from B-mode US and SWE images, 13 were finally selected. The ML classifier showed an AUC of 0.768 and 0.746, and an MCC of 0.403 and 0.423 in the training and test sets, respectively. The performance was higher than that of the expert radiologist assessing only B-mode US images, but significantly lower when SWE images were also provided.
A ML approach based on B-mode US and SWE images may represent a potential tool in the characterization of BLs. SWE still gives its most relevant contribution in the clinical setting rather than included in a radiomics pipeline.
构建并验证一种结合放射组学和机器学习（ML）的方法，使用B超和剪切波弹性成像（SWE）图像来鉴别乳腺实性病变（BLs）的良恶性，并将其性能与放射科专家的性能进行比较。
回顾性纳入至少有一个BI-RADS 2-6级BL且进行了乳腺超声联合SWE检查的患者。对B超和SWE图像进行手动分割以提取放射组学特征。进行多步骤特征选择过程，并使用逻辑回归算法建立预测模型。用AUC和马修斯相关系数（MCC）指标评估诊断准确性。将ML分类器的性能与放射科专家的性能进行比较。
纳入427个BLs，分为训练集（286个BLs，其中127个良性，159个恶性）和测试集（141个BLs，其中59个良性，82个恶性）。从B超和SWE图像中提取的1098个特征中，最终选择了13个。ML分类器在训练集和测试集中的AUC分别为0.768和0.746，MCC分别为0.403和0.423。该性能高于仅评估B超图像的放射科专家，但在同时提供SWE图像时显著降低。
基于B超和SWE图像的ML方法可能是表征BLs特征的潜在工具。在临床环境中，SWE仍然发挥着最相关的作用，而不是纳入放射组学流程。
