Related Experiment Videos
Radiomics-based interpretable machine learning model from multiphasic CT imaging for predicting pathological grade in
Zhanpeng Yuan1, Yuhua Mei1, Xiang Peng1
1Department of Urology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China.
Frontiers in Oncology
|July 8, 2026
Summary
This study developed a machine learning model using radiomic features from CT urography to predict upper tract urothelial carcinoma (UTUC) grade non-invasively. The model aids in preoperative diagnosis and personalized treatment planning.
Area of Science:
- Radiology
- Oncology
- Artificial Intelligence
Background:
- Upper tract urothelial carcinoma (UTUC) diagnosis and grading are crucial for treatment planning.
- Current diagnostic methods may be invasive or lack precision.
- Radiomics offers a non-invasive approach to extract quantitative features from medical images.
Purpose of the Study:
- To develop and validate a non-invasive machine learning (ML) model for predicting the pathological grade of UTUC.
- To utilize radiomic features from computed tomography urography (CTU) for preoperative diagnosis.
- To enhance diagnostic accuracy and support personalized treatment strategies for UTUC patients.
Main Methods:
- A retrospective multicenter study included 338 patients who underwent radical nephroureterectomy (RNU) with preoperative CTU.
- Radiomic features were extracted from CTU images (non-contrast, arterial, venous phases) using PyRadiomics.
- Feature selection was performed, and six ML models (XGBoost, ExtraTrees, RandomForest, SVM, MLP, LGBM) were trained and evaluated using ROC curves, AUC, sensitivity, and specificity. SHAP analysis was used for interpretability.
Main Results:
- The Light Gradient Boosting Machine (LGBM) model achieved the highest performance in the training set (AUC: 0.945, sensitivity: 84.5%, specificity: 91.2%).
- In the test set, LGBM demonstrated robust generalizability (AUC: 0.829, sensitivity: 71.8%, specificity: 77.4%), outperforming other models.
- SHAP analysis identified features from arterial and venous CTU phases as most influential, enhancing model interpretability.
Conclusions:
- The developed radiomics-based ML model shows significant potential for non-invasive preoperative grading of UTUC.
- This tool can improve diagnostic accuracy and assist in personalized treatment planning for UTUC.
- The model offers a clinically interpretable and non-invasive method for UTUC management.
Related Concept Videos
01:27Imaging Studies IV: Magnetic Resonance Imaging
Introduction:Magnetic Resonance Imaging, or MRI, can include a specialized imaging technique of the urinary system known as Magnetic Resonance Urography (MRU). This radiation-free technique uses strong magnetic fields and radio waves to produce detailed images with the help of a computer. MRU is particularly effective for visualizing fluid-filled structures like the kidneys, ureters, and bladder.Applications of MRI in the Genitourinary SystemKidneys and Ureters: MRI detects tumors, cysts,...
01:27Imaging Studies III: Computed Tomography
DefinitionComputed Tomography (CT) of the genitourinary (GU) tract is a non-invasive imaging modality that utilizes X-rays and computer processing to generate detailed cross-sectional images of the urinary system, encompassing the kidneys, ureters, bladder, and adjacent structures such as the adrenal glands.PurposeCT scans of the GU tract serve several diagnostic and therapeutic purposes, including:Diagnosis of Urinary Tract Diseases: Detects kidney stones, tumors, cysts, and congenital...
01:28Imaging Studies I: Kidney, Ureter, and Bladder Studies
Kidney, Ureter, and Bladder (KUB) StudiesKidney, Ureter, and Bladder (KUB) studies are standard diagnostic imaging procedures used to assess the anatomy of the urinary system. They are commonly utilized for patients experiencing abdominal pain or urinary symptoms. By using a simple X-ray of the abdomen, KUB studies can reveal structural and pathological abnormalities within the kidneys, ureters, and bladder. These studies are particularly valuable in diagnosing kidney stones, urinary...