旨在研究和验证各种放射组学模型区分良性和恶性 BI-RADS 4A 病变的有效性。该研究共纳入了 936 例经病理证实的 4A 病变患者（训练队列：n = 655；测试队列：n = 281）。放射组学特征源自灰度美国图像。在降维和特征选择之后，使用逻辑回归（LR）、支持向量机（SVM）、随机森林（RF）、极限梯度提升（XGBoost）和多层感知器（MLP）算法开发了放射组学模型。采用单变量和多变量逻辑回归分析来研究临床放射学特征并确定用于创建临床模型的变量。使用每种算法构建了五个整合放射组学和临床参数的组合模型，并与放射科医生的表现进行比较。 SHapley Additive exPlanations (SHAP) 方法用于根据特征对评估的贡献对特征的重要性进行排序来阐明放射组学模型。总共提取了 1561 个放射组学特征。通过降维和选择，有 36 个特征被认为是重要的。放射组学模型在训练队列中表现出良好的性能，AUC 为 0.829-0.945；测试队列中为 0.805-0.857。使用 LR 开发的组合模型显示出最佳性能（AUC，训练队列：0.909；测试队列：0.905），优于放射科医生的表现。该组合模型的决策曲线分析（DCA）显示比临床和放射组学模型更好的临床疗效。整合放射组学和临床特征的组合模型在区分良性和恶性4A病变方面表现出优异的性能。它可以提供一种非侵入性且有效的方法来帮助临床决策。版权所有 © 2024 大学放射科医生协会。由爱思唯尔公司出版。保留所有权利。

To investigate and authenticate the effectiveness of various radiomics models in distinguishing between benign and malignant BI-RADS 4A lesions.A total of 936 patients with pathologically confirmed 4A lesions were included in the study (training cohort: n = 655; test cohort: n = 281). Radiomic features were derived from greyscale US images. Following dimensionality reduction and feature selection, radiomics models were developed using logistic regression (LR), support vector machine (SVM), random forest (RF), eXtreme gradient boosting (XGBoost) and multilayer perceptron (MLP) algorithms. Univariate and multivariable logistic regression analyses were employed to investigate clinical-radiological characteristics and determine variables for creating a clinical model. Five combined models integrating radiomic and clinical parameters were constructed by using each algorithm, and comparison with radiologists' performance was performed. SHapley Additive exPlanations (SHAP) approach was used to elucidate the radiomic model by ranking the significance of features based on their contribution to the evaluation.A total of 1561 radiomic features were extracted. Thirty-six features were deemed significant by dimensionality reduction and selection. The radiomic models showed good performance with AUCs of 0.829-0.945 in training cohort; and 0.805-0.857 in test cohort. The combined model developed by using LR showed the best performance (AUC, training cohort: 0.909; test cohort: 0.905), which is superior to radiologists' performance. Decision curve analysis (DCA) of this combined model indicated better clinical efficacy than clinical and radiomic models.The combined model integrating radiomic and clinical features demonstrated excellent performance in differentiating between benign and malignant 4A lesions. It may offer a non-invasive and efficient approach to aid in clinical decision-making.Copyright © 2024 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.