基于栖息地影像组学与投票算法提升乳腺癌腋窝淋巴结转移预测
回顾性纳入福建省肿瘤医院2016年4月至2022年12月246例T1/T2期乳腺癌患者(246个病灶),按197例训练集、49例测试集随机划分,以高斯混合模型将B型超声图像分为三个亚区,提取全肿瘤(B型超声和超声造影)及亚区(B型超声)影像组学特征,用投票算法整合栖息地影像组学、传统影像组学与临床信息。测试集上栖息地-超声造影-临床联合模型准确度87.76%(95%CI 0.775-0.944)、假阳性率7.41%(95%CI 0.019-0.202),准确度较单模型提高12.25%,传统全肿瘤-超声造影-临床模型准确度79.59%(95%CI 0.678-0.884),两模型差异有统计学意义(p<0.05)。
要点
- 测试集栖息地-超声造影-临床模型准确度87.76%,假阳性率7.41%,较单模型准确度提高12.25%。
- 传统全肿瘤-超声造影-临床模型测试集准确度79.59%,与栖息地联合模型差异有统计学意义(p<0.05)。
- B型超声图像经高斯混合模型分为三个亚区,每个ROI提取899个特征,含形状、一阶和纹理特征。
核心结论
- 栖息地影像组学比传统方法更有效地捕捉肿瘤异质性,双模态超声联合投票算法显著提升腋窝淋巴结转移预测,为乳腺癌计算机辅助术前规划提供可靠基础。
研究设计与样本
- 回顾性研究,纳入福建省肿瘤医院2016年4月至2022年12月246例T1/T2期乳腺癌患者共246个病灶,随机分为训练集197例和测试集49例。
关键影像表现/征象
- 以高斯混合模型将B型超声图像分割为三个肿瘤亚区,每个ROI提取899个特征,包括形状特征、一阶特征和纹理特征。
- 特征提取覆盖全肿瘤(B型超声和超声造影)及亚区(B型超声)ROI,肿瘤亚区特征增强预测稳健性。
- 采用硬投票整合栖息地影像组学、传统影像组学与临床信息构建栖息地-超声造影-临床模型。
诊断标准与关键数值
- 测试集栖息地-超声造影-临床模型(硬投票)准确度87.76%(95%CI 0.775-0.944),假阳性率7.41%(95%CI 0.019-0.202)。
- 测试集传统全肿瘤-超声造影-临床模型准确度79.59%(95%CI 0.678-0.884)。
- 栖息地-超声造影-临床模型准确度较单模型提高12.25%,与传统全肿瘤-超声造影-临床模型差异有统计学意义(p<0.05)。
- 诊断性能通过准确度、敏感度、特异度和F1分数评估。
临床应用与阅片要点
- 作者认为栖息地影像组学比传统方法更有效地捕捉肿瘤异质性,双模态超声联合投票算法显著提升腋窝淋巴结转移预测。
- 作者认为该模型为乳腺癌计算机辅助术前规划提供可靠基础。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: To develop a machine learning model integrating habitat-based radiomics and voting algorithms for predicting axillary lymph node metastasis (ALNM) in breast cancer using B-mode and contrast-enhanced ultrasound images.
METHODS: This retrospective study included 246 T1/T2 stage breast cancer patients (246 lesions) from Fujian Cancer Hospital (2016.04-2022.12). Lesions were randomly divided into training (n = 197) and testing (n = 49) datasets. A Gaussian Mixture Model partitioned B-mode ultrasound images into three subregions. Radiomics features, including shape features, first-order features, and texture features, were extracted from whole-tumor (B-mode and CEUS) and subregional (B-mode) ROIs. Multiple classifiers were applied to evaluate the model's diagnostic performance. Voting algorithms were used to integrate habitat-based radiomics, traditional radiomics, and clinical information for model optimization. Diagnostic performance was assessed via accuracy, sensitivity, specificity, and F1-score.
RESULTS: Feature extraction yielded 899 features per ROI, including tumor subregions, enhancing prediction robustness. On the testing set, the combined habitat-based model (Habitat-CEUS-Clinical model) achieved an accuracy of 87.76% (95% CI: 0.775, 0.944) and a false positive rate of 7.41% (95% CI: 0.019, 0.202) using hard voting, outperforming single models by 12.25% in terms of accuracy. In comparison, the traditional approach (Whole-CEUS-Clinical model) reached an accuracy of 79.59% (95% CI: 0.678, 0.884). The difference between the Habitat-CEUS-Clinical model and the Whole-CEUS-Clinical model was statistically significant (p < 0.05).
CONCLUSION: Habitat-based radiomics captures tumor heterogeneity more effectively than conventional methods. Dual-modality ultrasound combined with voting algorithms significantly improves ALNM prediction, providing a reliable foundation for computer-aided preoperative planning in breast cancer.
引用
- Chen Y, Liu N, Lin R, et al. Enhancing the Prediction of Axillary Lymph Node Metastasis in Breast Cancer through Habitat-Based Radiomics and Voting Algorithms. Ultrasound Med Biol. 2025. PMID: 41062358. doi:10.1016/j.ultrasmedbio.2025.09.001
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。