JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Development of a radiomics and clinical feature-based nomogram for preoperative prediction of pathological grade in bladder cancer

  • 0Department of Urology, The First Affiliated Hospital of Soochow University, Suzhou, China.
Frontiers in Oncology +

|

September 12, 2025

|

September 12, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed a CT-based model integrating radiomic and clinical data to predict bladder cancer grade. The integrated model accurately differentiates high-grade from low-grade urothelial carcinoma, aiding treatment decisions.

Area Of Science

  • Radiology
  • Oncology
  • Medical Imaging Analysis

Background

  • Accurate preoperative pathological grading of bladder urothelial carcinoma is crucial for treatment planning.
  • Current methods may have limitations in predicting tumor grade non-invasively.

Purpose Of The Study

  • To develop and validate a preoperative predictive model for bladder urothelial carcinoma pathological grading.
  • To integrate multi-parameter computed tomography (CT) texture features with clinical indicators.

Main Methods

  • Retrospective analysis of CT images and clinical data from 372 bladder urothelial carcinoma patients.
  • Extraction and selection of 1,223 texture features using radiomics analysis and LASSO regression.
  • Development of a logistic regression model incorporating selected radiomic and clinical features (age, proteinuria).

Main Results

  • Eleven radiomics features were significantly associated with bladder urothelial carcinoma pathological grade.
  • The integrated model achieved an area under the curve (AUC) of 0.864, outperforming models using only clinical or radiomic data.
  • Age and proteinuria were identified as independent predictors of tumor grade.

Conclusions

  • The study presents the first CT-based nomogram integrating multiparametric radiomic features and clinical indicators for preoperative prediction of bladder urothelial carcinoma grade.
  • This non-invasive model offers a robust and accurate tool for individualized treatment planning and clinical decision-making.

Keywords: