Multimodal CT radiomics and 2.5D deep learning for preoperative grading of clear cell renal cell carcinoma in older patients: a multicenter study
Abstract
IntroductionTo develop and validate a multimodal CT-based model integrating intra-peritumoral radiomics, 2.5D deep learning (DL), and clinical-radiological features for preoperative prediction of World Health Organization/International Society of Urological Pathology (WHO/ISUP) grade in older patients with clear cell renal cell carcinoma (ccRCC).MethodsThis multicenter retrospective study included 1,103 patients older than 60 years with pathologically confirmed ccRCC from four hospitals. Patients were allocated to a training cohort (n=459), an internal validation cohort (n=198), and two independent external test cohorts (test1, n=227; test2, n=219). WHO/ISUP grades I–II were classified as low grade and grades III–IV as high grade. Radiomics features were extracted from corticomedullary-phase CT images using intratumoral and progressively expanded intra-peritumoral regions of 1, 2, and 3 mm. In parallel, 2D and 2.5D DL features were extracted using ImageNet-pretrained ResNet34 networks, with the 2.5D approach integrating axial, coronal, and sagittal tumor views. After feature selection, five machine learning classifiers were evaluated. The optimal radiomics model, DL model, and clinical model were integrated using stacking-based decision-level fusion. Model performance was assessed using receiver operating characteristic analysis, calibration curves, decision curve analysis (DCA), and SHapley Additive exPlanations (SHAP).ResultsThe random forest (RF) model based on intra-peritumoral 3-mm radiomics features achieved areas under the receiver operating characteristic curve (AUCs) of 0.754 (95% CI, 0.683–0.825) and 0.725 (95% CI, 0.655–0.794) in the test1 and test2 cohorts, respectively. The RF model based on 2.5D DL features achieved corresponding AUCs of 0.756 (95% CI, 0.682–0.830) and 0.713 (95% CI, 0.643–0.783). The multimodal combined model achieved numerically higher external AUCs than the selected single-modality models, reaching 0.775 (95% CI, 0.705–0.845) in test1 and 0.732 (95% CI, 0.664–0.800) in test2. DCA demonstrated favorable clinical net benefit for the combined model, while SHAP analysis identified the 2.5D DL component as the largest contributor to model predictions.DiscussionA multimodal CT-based framework integrating intra-peritumoral radiomics, 2.5D DL, and clinical-radiological information enabled noninvasive preoperative prediction of WHO/ISUP grade in older patients with ccRCC and maintained predictive performance across independent external cohorts. This approach may provide complementary imaging and clinical information for preoperative risk stratification and individualized treatment planning.
Related
- MRI-based preoperative WHO grade prediction in meningioma: development and comparison of deep learning, radiomics, clinical, and combined models in multicenter data.
- Development and Patient-Level Internal Validation of an MRI-Based Radiomics Machine Learning Model for Preoperative Prediction of Cervical Lymph Node Metastasis in Oral Squamous Cell Carcinoma: A Pilot Study.
- CT-based clinical deep learning radiomics nomogram for preoperative differentiation of pyelocaliceal upper tract urothelial carcinoma and xanthogranulomatous pyelonephritis
- Multiparametric MRI-based radiomics combined with deep learning for preoperative risk stratification of endometrial carcinoma
- Integrating Magnetic Resonance Imaging-Based Deep Learning and Radiomics to Predict Treatment Response in Hepatocellular Carcinoma Receiving Combined Systemic and Locoregional Therapies: A Multicenter Study.
BibTeX
@article{wang2026multimodal,
title = {{Multimodal CT radiomics and 2.5D deep learning for preoperative grading of clear cell renal cell carcinoma in older patients: a multicenter study}},
author = {Zhengkun Wang and Zixin Liang and Dingyang Lv and Shenyi Hu and Huiyu Zhou and Jinshuai Li and Xiaodong Bian and Jiacheng Gao and Tiantian Zhao and Bingxin Gong and Ying Qiao and Weibing Shuang},
journal = {Frontiers in Oncology},
year = {2026},
month = oct,
doi = {10.3389/fonc.2026.1982970},
url = {https://www.frontiersin.org/articles/10.3389/fonc.2026.1982970},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Multimodal CT radiomics and 2.5D deep learning for preoperative grading of clear cell renal cell carcinoma in older patients: a multicenter study
AU - Zhengkun Wang
AU - Zixin Liang
AU - Dingyang Lv
AU - Shenyi Hu
AU - Huiyu Zhou
AU - Jinshuai Li
AU - Xiaodong Bian
AU - Jiacheng Gao
AU - Tiantian Zhao
AU - Bingxin Gong
AU - Ying Qiao
AU - Weibing Shuang
PY - 2026
DA - 2026/10/30
JO - Frontiers in Oncology
DO - 10.3389/fonc.2026.1982970
UR - https://www.frontiersin.org/articles/10.3389/fonc.2026.1982970
AB - IntroductionTo develop and validate a multimodal CT-based model integrating intra-peritumoral radiomics, 2.5D deep learning (DL), and clinical-radiological features for preoperative prediction of World Health Organization/International Society of Urological Pathology (WHO/ISUP) grade in older patients with clear cell renal cell carcinoma (ccRCC).MethodsThis multicenter retrospective study included 1,103 patients older than 60 years with pathologically confirmed ccRCC from four hospitals. Patients were allocated to a training cohort (n=459), an internal validation cohort (n=198), and two independent external test cohorts (test1, n=227; test2, n=219). WHO/ISUP grades I–II were classified as low grade and grades III–IV as high grade. Radiomics features were extracted from corticomedullary-phase CT images using intratumoral and progressively expanded intra-peritumoral regions of 1, 2, and 3 mm. In parallel, 2D and 2.5D DL features were extracted using ImageNet-pretrained ResNet34 networks, with the 2.5D approach integrating axial, coronal, and sagittal tumor views. After feature selection, five machine learning classifiers were evaluated. The optimal radiomics model, DL model, and clinical model were integrated using stacking-based decision-level fusion. Model performance was assessed using receiver operating characteristic analysis, calibration curves, decision curve analysis (DCA), and SHapley Additive exPlanations (SHAP).ResultsThe random forest (RF) model based on intra-peritumoral 3-mm radiomics features achieved areas under the receiver operating characteristic curve (AUCs) of 0.754 (95% CI, 0.683–0.825) and 0.725 (95% CI, 0.655–0.794) in the test1 and test2 cohorts, respectively. The RF model based on 2.5D DL features achieved corresponding AUCs of 0.756 (95% CI, 0.682–0.830) and 0.713 (95% CI, 0.643–0.783). The multimodal combined model achieved numerically higher external AUCs than the selected single-modality models, reaching 0.775 (95% CI, 0.705–0.845) in test1 and 0.732 (95% CI, 0.664–0.800) in test2. DCA demonstrated favorable clinical net benefit for the combined model, while SHAP analysis identified the 2.5D DL component as the largest contributor to model predictions.DiscussionA multimodal CT-based framework integrating intra-peritumoral radiomics, 2.5D DL, and clinical-radiological information enabled noninvasive preoperative prediction of WHO/ISUP grade in older patients with ccRCC and maintained predictive performance across independent external cohorts. This approach may provide complementary imaging and clinical information for preoperative risk stratification and individualized treatment planning.
SN - 2234-943X
ER -