This study aims to establish an effective benign and malignant classification model for breast tumor ultrasound images by using conventional radiomics and transfer learning features. We collaborated with a local hospital and collected a base dataset (Dataset A) consisting of 1050 cases of single lesion 2D ultrasound images from patients, with a total of 593 benign and 357 malignant tumor cases. The experimental approach comprises three main parts: conventional radiomics, transfer learning, and feature fusion. Furthermore, we assessed the model's generalizability by utilizing multicenter data obtained from Datasets B and C. The results from conventional radiomics indicated that the SVM classifier achieved the highest balanced accuracy of 0.791, while XGBoost obtained the highest AUC of 0.854. For transfer learning, we extracted deep features from ResNet50, Inception-v3, DenseNet121, MNASNet, and MobileNet. Among these models, MNASNet, with 640-dimensional deep features, yielded the optimal performance, with a balanced accuracy of 0.866, AUC of 0.937, sensitivity of 0.819, and specificity of 0.913. In the feature fusion phase, we trained SVM, ExtraTrees, XGBoost, and LightGBM with early fusion features and evaluated them with weighted voting. This approach achieved the highest balanced accuracy of 0.964 and AUC of 0.981. Combining conventional radiomics and transfer learning features demonstrated clear advantages over using individual features for breast tumor ultrasound image classification. This automated diagnostic model can ease patient burden and provide additional diagnostic support to radiologists. The performance of this model encourages future prospective research in this domain.

中文翻译：

---

使用传统放射组学和迁移学习特征对乳腺肿瘤超声图像进行良性和恶性分类：多中心回顾性研究

本研究旨在利用常规放射组学和迁移学习特征，建立有效的乳腺肿瘤超声图像良恶性分类模型。我们与当地一家医院合作，收集了由 1050 例患者单病灶二维超声图像组成的基础数据集（数据集 A），其中良性肿瘤病例总数为 593 例，恶性肿瘤病例病例数为 357 例。实验方法包括三个主要部分：传统放射组学、迁移学习和特征融合。此外，我们利用从数据集 B 和 C 获得的多中心数据评估了模型的普适性。传统放射组学的结果表明，SVM 分类器实现了最高的平衡精度 0.791，而 XGBoost 获得了最高的 AUC 0.854。对于迁移学习，我们从 ResNet50、Inception-v3、DenseNet121、MNASNet 和 MobileNet 中提取深度特征。在这些模型中，具有 640 维深度特征的 MNASNet 表现最佳，平衡精度为 0.866，AUC 为 0.937，灵敏度为 0.819，特异性为 0.913。在特征融合阶段，我们用早期融合特征训练了SVM、ExtraTrees、XGBoost和LightGBM，并通过加权投票对其进行了评估。该方法实现了最高的平衡精度 0.964 和 AUC 0.981。与使用单个特征进行乳腺肿瘤超声图像分类相比，结合传统放射组学和迁移学习特征表现出明显的优势。这种自动化诊断模型可以减轻患者负担，并为放射科医生提供额外的诊断支持。该模型的性能鼓励该领域未来的前瞻性研究。