Engineering Research Center of Health Emergency, From the Medical Imaging College, Nanjing Medical University, Nanjing, China; Department of Radiology, The First Affiliated Hospital with Nanjing Medical University, Nanjing, China.
Department of Radiology, The First Affiliated Hospital with Nanjing Medical University, Nanjing, China.
Urol Oncol. 2025 Jan;43(1):63.e7-63.e17. doi: 10.1016/j.urolonc.2024.09.025. Epub 2024 Oct 5.
To develop and validate a clinicoradiomics model based on intratumoral habitat imaging for preoperatively predicting of progression-free survival (PFS) of clear cell renal cell carcinoma (ccRCC) and analyzing progression-associated genes expression.
This retrospective study included 691 ccRCC patients from multicenter databases. Entire tumor segmentation was performed with handcrafted process to generate habitat subregions based on a pixel-wise gray-level co-occurrence matrix analysis. Cox regression models for PFS prediction were constructed using conventional volumetric radiomics features (Radiomics), habitat subregions-derived radiomics (Rad-Habitat), and an integration of habitat radiomics and clinical characteristics (Hybrid Cox). Training (n = 393) and internal validation (n = 118) was performed in a Nanjing cohort, external validation was performed in a Wuhan and Zhejiang cohort (n = 227) and in a TCGA-KIRC (n =71) with imaging-genomic correlation. Statistical analysis included the area-under-ROC curve analysis, C-index, decision curve analysis (DCA) and Kaplan-Meier survival analysis.
Hybrid Cox model resulted in a C-index of 0.83 (95% CI, 0.73-0.93) in internal validation and 0.79 (95% CI, 0.74-0.84) in external validation for PFS prediction, higher than Radiomics and Rad-Habitat model. Patients stratified by Hybrid Cox model presented with significant difference survivals between high-risk and low-risk group in 3 data sets (all P < 0.001 at Log-rank test). TCGA-KIRC data analysis revealed 37 upregulated and 81 downregulated genes associated with habitat imaging features of ccRCC. Differentially expressed genes likely play critical roles in protein and mineral metabolism, immune defense, and cellular polarity maintenance.
开发并验证一种基于肿瘤内生态位成像的临床放射组学模型，用于术前预测透明细胞肾细胞癌（ccRCC）的无进展生存期（PFS），并分析与进展相关的基因表达。
本回顾性研究纳入了来自多中心数据库的 691 例 ccRCC 患者。采用手工过程对整个肿瘤进行分割，基于像素灰度共生矩阵分析生成生态位亚区。使用传统容积放射组学特征（Radiomics）、基于生态位亚区的放射组学（Rad-Habitat）和生态位放射组学与临床特征的整合（Hybrid Cox）构建用于 PFS 预测的 Cox 回归模型。在南京队列中进行了训练（n=393）和内部验证（n=118），在武汉和浙江队列（n=227）以及 TCGA-KIRC 队列（n=71）中进行了外部验证，同时进行了影像学-基因组相关性分析。统计分析包括 ROC 曲线下面积分析、C 指数、决策曲线分析（DCA）和 Kaplan-Meier 生存分析。
Hybrid Cox 模型在内部分验证中的 C 指数为 0.83（95%CI，0.73-0.93），在外部分验证中的 C 指数为 0.79（95%CI，0.74-0.84），均高于 Radiomics 和 Rad-Habitat 模型。在 3 个数据集（Log-rank 检验，均 P<0.001）中，根据 Hybrid Cox 模型分层的患者高低风险组之间的生存差异有统计学意义。TCGA-KIRC 数据分析显示，与 ccRCC 肿瘤内生态位成像特征相关的基因有 37 个上调和 81 个下调。差异表达基因可能在蛋白质和矿物质代谢、免疫防御和细胞极性维持中发挥关键作用。
