基于深度学习和栖息地影像组学综合评估膀胱癌肿瘤间质异质性
本研究回顾性纳入两个中心477例膀胱尿路上皮癌患者,基于术前增强CT提取影像组学特征,采用K均值聚类划分肿瘤亚区,构建常规模型、多亚区栖息地模型及单亚区模型,并开发基于最大肿瘤截面的深度迁移学习模型,用于术前预测肿瘤间质比;深度迁移学习模型预测准确性优于所有影像组学模型,联合临床变量的列线图可有效预测无复发生存、CD8+ T细胞浸润及免疫治疗反应。
要点
- 基于术前增强CT的栖息地影像组学和深度学习模型可无创定量评估膀胱癌肿瘤间质比。
- 深度迁移学习模型在预测准确性上优于所有影像组学模型。
- 联合深度迁移学习模型与临床变量的列线图可有效预测无复发生存、CD8+ T细胞浸润和免疫治疗反应。
核心结论
- 基于CT的栖息地影像组学和深度学习模型能够无创、定量评估膀胱癌肿瘤间质比,深度迁移学习模型具有更优的诊断和预后价值,支持个体化治疗决策和免疫治疗反应预测。
研究设计与样本
- 回顾性研究,纳入两个中心共477例膀胱尿路上皮癌患者,于术前增强CT上分割肿瘤并提取影像组学特征,采用K均值聚类将肿瘤划分为亚区,构建常规模型(Intra)、多亚区模型(Habitat)和单亚区模型(HabitatH1/H2/H3),并基于最大肿瘤截面开发深度迁移学习模型(DeepL)。
诊断标准与关键数值
- HabitatH1模型表现出稳健的诊断性能,且校准良好、临床实用性佳。
- DeepL模型在预测准确性上优于所有影像组学模型。
- 影像预测的肿瘤间质比与肿瘤免疫微环境及治疗结局存在显著关联。
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: Tumor stromal heterogeneity plays a pivotal role in bladder cancer progression. The tumor-stroma ratio (TSR) is a key pathological marker reflecting stromal heterogeneity. This study aimed to develop a preoperative, CT-based machine learning model for predicting TSR in bladder cancer, comparing various radiomic approaches, and evaluating their utility in prognostic assessment and immunotherapy response prediction.
METHODS: A total of 477 bladder urothelial carcinoma patients from two centers were retrospectively included. Tumors were segmented on preoperative contrast-enhanced CT, and radiomic features were extracted. K-means clustering was used to divide tumors into subregions. Radiomics models were constructed: a conventional model (Intra), a multi-subregion model (Habitat), and single-subregion models (HabitatH1/H2/H3). A deep transfer learning model (DeepL) based on the largest tumor cross-section was also developed. Model performance was evaluated in training, testing, and external validation cohorts, and associations with recurrence-free survival, CD8+ T cell infiltration, and immunotherapy response were analyzed.
RESULTS: The HabitatH1 model demonstrated robust diagnostic performance with favorable calibration and clinical utility. The DeepL model surpassed all radiomics models in predictive accuracy. A nomogram combining DeepL and clinical variables effectively predicted recurrence-free survival, CD8+ T cell infiltration, and immunotherapy response. Imaging-predicted TSR showed significant associations with the tumor immune microenvironment and treatment outcomes.
CONCLUSION: CT-based habitat radiomics and deep learning models enable non-invasive, quantitative assessment of TSR in bladder cancer. The DeepL model provides superior diagnostic and prognostic value, supporting personalized treatment decisions and prediction of immunotherapy response.
引用
- Du Y, Sui Y, Tao Y, et al. Comprehensive Assessment of Tumor Stromal Heterogeneity in Bladder Cancer by Deep Learning and Habitat Radiomics. Acad Radiol. 2025. PMID: 40987672. doi:10.1016/j.acra.2025.08.029
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。