Related Experiment Video
Updated: Nov 11, 2025
05:19
Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors
Published on: March 29, 2019
10.6K
Radiomics-based model for predicting pathological complete response to neoadjuvant chemotherapy in muscle-invasive
1Department of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
Clinical Radiology
|March 25, 2021
Summary
A new radiomics model using baseline CT scans can predict treatment response in muscle-invasive bladder cancer (MIBC) patients undergoing neoadjuvant chemotherapy (NAC). This imaging-based model shows promise for personalized treatment strategies.
Area of Science:
- Radiology
- Oncology
- Medical Imaging
Background:
- Muscle-invasive bladder cancer (MIBC) requires effective treatment strategies.
- Predicting response to neoadjuvant chemotherapy (NAC) is crucial for patient outcomes.
- Baseline computed tomography (CT) imaging offers potential for non-invasive response prediction.
Purpose of the Study:
- To develop and validate a radiomics-based model for predicting pathological complete response (pCR) to NAC in MIBC patients.
- To assess the performance and clinical utility of the developed imaging-based model.
Main Methods:
- A radiomics signature was developed using features selected by random forest classification on baseline CT images.
- An imaging-based model was constructed incorporating radiomics signature, tumor shape, size, and clinical stage.
- The model was trained on 87 patients and validated on an independent set of 48 patients from outside institutions.
Main Results:
- The radiomics signature comprised six stable radiomics features.
- The imaging-based model demonstrated good performance in predicting pCR, with AUCs of 0.85 (training) and 0.75 (validation).
- The model showed a higher positive likelihood ratio for pCR compared to traditional imaging and histological predictors.
Conclusions:
- A radiomics-based model utilizing baseline CT images shows potential for predicting NAC response in MIBC patients.
- This model may aid in personalizing treatment decisions for bladder cancer.
- Further validation is warranted to integrate this tool into clinical practice.
