Lu Guoxiu, Tian Ronghui, Yang Wei, Zhao Jiayi, Chen Wenjing, Xiang Zijie, Hao Shanhu, Zhang Guoxu
College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, Liaoning, China.
Department of Nuclear Medicine, General Hospital of Northern Theater Command, Shenyang, Liaoning, China.
Front Oncol. 2025 Aug 21;15:1621677. doi: 10.3389/fonc.2025.1621677. eCollection 2025.
To develop a deep learning radiomics(DLR)model integrating PET/CT radiomics, deep learning features, and clinical parameters for early prediction of bone oligometastases (≤5 lesions) in breast cancer.
We retrospectively analyzed 207 breast cancer patients with 312 bone lesions, comprising 107 benign and 205 malignant lesions, including 89 lesions with confirmed bone metastases. Radiomic features were extracted from computed tomography (CT), positron emission tomography (PET), and fused PET/CT images using PyRadiomics embedded in the uAI Research Portal. Standardized feature extraction and feature selection were performed using the Least Absolute Shrinkage and Selection Operator (LASSO) method. We developed and validated three models: a radiomics-based model, a deep learning model using BasicNet, and a deep learning radiomics (DLR) model incorporating clinical and metabolic parameters. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Statistical comparisons were conducted using the DeLong test.
Visual assessment of fused PET/CT images identified 227 (72.8%) abnormal lesions, demonstrating greater sensitivity than CT or PET alone. The complex radiomics model achieved a sensitivity of 98.9% [96.1%-99.4%], specificity of 98.2% [88.1%-99.6%], accuracy of 98.7% [89.6%-99.5%], and area under the curve (AUC) of 0.989. The BasicNet model outperformed other transfer learning models, achieving an AUC of 0.961. The DeLong test confirmed that the AUC of the BasicNet model was significantly higher than the traditional radiomics model. The DLR+Complex model with a random forest classifier achieved the highest overall performance, with an AUC of 0.990, sensitivity of 98.6%, specificity of 90.5%, and accuracy of 99.8%.
The BasicNet model significantly outperformed traditional radiomics approaches in predicting bone oligometastases in breast cancer patients. The DLR+Complex model demonstrated the best predictive performance across all metrics. Future strategies for precise diagnosis and treatment should incorporate histologic subtype, advanced imaging, and molecular biomarkers.
开发一种整合PET/CT影像组学、深度学习特征和临床参数的深度学习影像组学（DLR）模型，用于早期预测乳腺癌骨寡转移（≤5个病灶）。
我们回顾性分析了207例患有312处骨病灶的乳腺癌患者，其中包括107处良性病灶和205处恶性病灶，其中89处病灶确诊为骨转移。使用uAI研究门户中嵌入的PyRadiomics从计算机断层扫描（CT）、正电子发射断层扫描（PET）和融合的PET/CT图像中提取影像组学特征。使用最小绝对收缩和选择算子（LASSO）方法进行标准化特征提取和特征选择。我们开发并验证了三种模型：基于影像组学的模型、使用BasicNet的深度学习模型以及结合临床和代谢参数的深度学习影像组学（DLR）模型。使用受试者操作特征曲线（AUC）下面积、准确性、敏感性和特异性评估模型性能。使用DeLong检验进行统计比较。
融合PET/CT图像的视觉评估发现227处（72.8%）异常病灶，显示出比单独的CT或PET更高的敏感性。复杂影像组学模型的敏感性为98.9%[96.1%-99.4%]，特异性为98.2%[88.1%-99.6%]，准确性为98.7%[89.6%-99.5%]，曲线下面积（AUC）为0.989。BasicNet模型优于其他迁移学习模型，AUC为0.961。DeLong检验证实BasicNet模型的AUC显著高于传统影像组学模型。采用随机森林分类器的DLR+复杂模型实现了最高的总体性能，AUC为0.990，敏感性为98.6%，特异性为90.5%，准确性为99.8%。
在预测乳腺癌患者骨寡转移方面，BasicNet模型显著优于传统影像组学方法。DLR+复杂模型在所有指标上均表现出最佳的预测性能。未来精确诊断和治疗策略应纳入组织学亚型、先进影像学和分子生物标志物。
