Related Experiment Video
Updated: Jul 8, 2026
05:19
Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors
Published on: March 29, 2019
Development of multiphasic CT-based delta-radiomics model for predicting postoperative recurrence risk in bladder
Weiwei Liu1,2,3, Bingxin Gong1,2,3, Guilin Zhang1,2,3
1Department of Radiology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Jiefang Avenue #1277, Wuhan, 430022, China.
BMC Medical Imaging
|July 6, 2026
Summary
A new CT-based delta-radiomics model accurately predicts bladder cancer recurrence after surgery. This non-invasive approach, combined with muscle invasion data, improves personalized prognosis assessment.
Area of Science:
- Radiology
- Oncology
- Medical Imaging
Background:
- Bladder cancer recurrence poses a significant challenge to patient prognosis.
- Accurate prediction of postoperative outcomes is crucial for personalized treatment strategies.
Purpose of the Study:
- To develop a CT-based delta-radiomics model for predicting postoperative prognosis in bladder cancer.
- To identify genes associated with tumor recurrence.
- To create a combined clinical-radiomic model for enhanced predictive performance.
Main Methods:
- Retrospective analysis of 316 bladder cancer patients undergoing preoperative CT scans.
- Extraction of radiomic features from unenhanced and arterial-phase CT images.
- Calculation of delta-radiomic features and application of machine learning for model development.
- Validation using ROC analysis, calibration, and decision curve analysis.
Main Results:
- A delta-radiomics model using nine features achieved AUCs of 0.837 (training) and 0.822 (validation).
- A combined model integrating delta-radiomics score and muscle invasion yielded superior AUCs of 0.860 (training) and 0.861 (validation).
- Higher radiomics scores correlated with shorter recurrence-free survival; transcriptomic analysis revealed immune pathway enrichment in low-risk subgroups.
Conclusions:
- Multiphasic CT delta-radiomics offers a non-invasive method for predicting bladder cancer recurrence and prognosis.
- The combined clinico-radiomic model demonstrates superior predictive capability for individualized postoperative risk assessment.