先进深度学习、图像到文本模型与影像组学在乳腺超声预测浸润性导管癌肿瘤出芽及肿瘤间质比的比较评价
本研究纳入153例病理诊断为浸润性导管癌的患者,基于术前超声图像分别构建图像分类深度学习、图像到文本深度学习及影像组学机器学习模型,预测肿瘤出芽与肿瘤间质比的高低分组。结果显示影像组学XGBoost模型在验证集和测试集上对肿瘤出芽(验证集AUC 0.87、测试集AUC 0.76)和肿瘤间质比(验证集AUC 0.92、测试集AUC 0.84)均表现最优。
要点
- 影像组学XGBoost模型预测肿瘤出芽:验证集AUC 0.87、准确率0.87;测试集AUC 0.76、准确率0.78。
- 影像组学XGBoost模型预测肿瘤间质比:验证集AUC 0.92、准确率0.92;测试集AUC 0.84、准确率0.85。
- 图像分类深度学习模型在验证集预测肿瘤出芽AUC 0.55–0.71、预测肿瘤间质比AUC 0.54–0.75,均低于影像组学模型。
核心结论
- 影像组学机器学习模型在利用超声图像无创预测乳腺癌肿瘤出芽和肿瘤间质比方面显示出潜力,其临床整合可能有助于制定浸润性导管癌的个体化治疗策略并改善患者管理。
研究设计与样本
- 研究纳入153例病理诊断为浸润性导管癌的患者,将肿瘤出芽和肿瘤间质比分别分为低组和高组,并针对每个数据集分别开发模型;采用三种方法:先进图像分类深度学习模型(YOLOv11x-cls、DINOv2、Vision Transformer)、将图像转换为文本的BLIP-2模型、以及基于影像组学特征的机器学习算法(KNN、SVM、XGBoost);所有模型在训练集上训练,并在验证集和测试集上评估性能。
诊断标准与关键数值
- 肿瘤出芽预测:XGBoost模型验证集AUC 0.87、准确率0.87,测试集AUC 0.76、准确率0.78。
- 肿瘤出芽预测:图像分类深度学习模型验证集AUC 0.55–0.71,BLIP-2模型AUC 0.67。
- 肿瘤间质比预测:XGBoost模型验证集AUC 0.92、准确率0.92,测试集AUC 0.84、准确率0.85。
- 肿瘤间质比预测:图像分类深度学习模型验证集AUC 0.54–0.75,BLIP-2模型AUC 0.65。
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
RATIONALE AND OBJECTIVES: This study aimed to predict tumor budding (TB) and tumor-stromal ratio (TSR), which are important parameters of the tumor microenvironment in invasive ductal carcinoma, from preoperative ultrasound images. To this end, image classification-based deep learning (DL), image-to-text-based DL, and radiomics-based machine learning (ML) approaches were compared.
MATERIALS AND METHODS: We included 153 patients diagnosed with histopathologically invasive ductal carcinoma. TB and TSR were classified into two groups, "low" and "high," and separate models were developed for each dataset. Three different methodological approaches were applied: (1) advanced image classification DL models (YOLOv11x-cls, DINOv2, Vision Transformer [ViT]), (2) the Bootstrapping Language-Image Pre-training (BLIP-2) model that converts images to text, and (3) ML algorithms with radiomic features (KNN, SVM, XGBoost). All models were trained on the training set, and their performance was then evaluated on the validation and test sets.
RESULTS: In TB prediction, the XGBoost model demonstrated the most superior performance (AUC: 0.87, accuracy: 0.87 on the validation set; AUC: 0.76, accuracy: 0.78 on the test set). In contrast, image classification-based DL models yielded lower AUC values ranging from 0.55 to 0.71 on the validation set, while the BLIP-2 model achieved an AUC value of 0.67. In the TSR prediction, XGBoost showed the highest discriminatory ability (AUC: 0.92, accuracy: 0.92 in the validation set; AUC: 0.84, accuracy: 0.85 in the test set). In contrast, image classification-based DL models exhibited AUC values ranging from 0.54 to 0.75 in the validation set, while the BLIP-2 model exhibited an AUC of 0.65.
CONCLUSION: The findings obtained indicate that radiomics-based ML models show promise in non-invasive TB and TSR prediction using ultrasound images in breast cancer. The clinical integration of these approaches could significantly contribute to the development of personalized treatment strategies for invasive ductal carcinoma and enhance patient management.
引用
- Kaba E, Tören M, Asan B, et al. Comparative Evaluation of Advanced Deep Learning, Image-to-Text Models, and Radiomics for Predicting Tumor Budding and Tumor-Stroma Ratio from Breast Ultrasound in Invasive Ductal Carcinoma. Acad Radiol. 2025. PMID: 41176437. doi:10.1016/j.acra.2025.10.020
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。