Related Experiment Video
Updated: Jan 3, 2026
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
Published on: March 21, 2025
Multiparametric MRI and auto-fixed volume of interest-based radiomics signature for clinically significant peripheral
Jeroen Bleker1, Thomas C Kwee2, Rudi A J O Dierckx2
1Medical Imaging Center, Departments of Radiology, Nuclear Medicine and Molecular Imaging, University Medical Center Groningen, University of Groningen, Hanzeplein 1, 9700 RB, Groningen, The Netherlands. j.bleker@umcg.nl.
Objectives:
To create a radiomics approach based on multiparametric magnetic resonance imaging (mpMRI) features extracted from an auto-fixed volume of interest (VOI) that quantifies the phenotype of clinically significant (CS) peripheral zone (PZ) prostate cancer (PCa).
Methods:
This study included 206 patients with 262 prospectively called mpMRI prostate imaging reporting and data system 3-5 PZ lesions. Gleason scores > 6 were defined as CS PCa. Features were extracted with an auto-fixed 12-mm spherical VOI placed around a pin point in each lesion. The value of dynamic contrast-enhanced imaging(DCE), multivariate feature selection and extreme gradient boosting (XGB) vs. univariate feature selection and random forest (RF), expert-based feature pre-selection, and the addition of image filters was investigated using the training (171 lesions) and test (91 lesions) datasets.
Results:
The best model with features from T2-weighted (T2-w) + diffusion-weighted imaging (DWI) + DCE had an area under the curve (AUC) of 0.870 (95% CI 0.980-0.754). Removal of DCE features decreased AUC to 0.816 (95% CI 0.920-0.710), although not significantly (p = 0.119). Multivariate and XGB outperformed univariate and RF (p = 0.028). Expert-based feature pre-selection and image filters had no significant contribution.
Conclusions:
The phenotype of CS PZ PCa lesions can be quantified using a radiomics approach based on features extracted from T2-w + DWI using an auto-fixed VOI. Although DCE features improve diagnostic performance, this is not statistically significant. Multivariate feature selection and XGB should be preferred over univariate feature selection and RF. The developed model may be a valuable addition to traditional visual assessment in diagnosing CS PZ PCa.
Key Points:
• T2-weighted and diffusion-weighted imaging features are essential components of a radiomics model for clinically significant prostate cancer; addition of dynamic contrast-enhanced imaging does not significantly improve diagnostic performance. • Multivariate feature selection and extreme gradient outperform univariate feature selection and random forest. • The developed radiomics model that extracts multiparametric MRI features with an auto-fixed volume of interest may be a valuable addition to visual assessment in diagnosing clinically significant prostate cancer.
Insights
This study developed a radiomics approach using multiparametric MRI to quantify clinically significant prostate cancer. T2-weighted and diffusion-weighted imaging features are key, with dynamic contrast-enhanced imaging offering no significant diagnostic improvement.
Area of Science:
- Radiology
- Oncology
- Medical Imaging Analysis
Background:
- Prostate cancer diagnosis relies on accurate tumor characterization.
- Multiparametric magnetic resonance imaging (mpMRI) offers detailed insights into prostate tissue.
- Quantifying the phenotype of clinically significant (CS) peripheral zone (PZ) prostate cancer (PCa) remains a challenge.
Purpose of the Study:
- To develop a radiomics approach using mpMRI features from an auto-fixed volume of interest (VOI).
- To quantify the phenotype of CS PZ PCa.
- To evaluate the contribution of different imaging sequences and feature selection methods.
Main Methods:
- mpMRI data from 206 patients with 262 PZ lesions (PI-RADS 3-5) were analyzed.
- Features were extracted from a 12-mm spherical VOI placed in each lesion.
- The study compared dynamic contrast-enhanced (DCE) imaging, multivariate (XGBoost) vs. univariate (Random Forest) feature selection, and image filters.
Main Results:
- The best model combining T2-weighted (T2-w) + diffusion-weighted imaging (DWI) + DCE achieved an AUC of 0.870.
- Excluding DCE features reduced AUC to 0.816 (p=0.119), indicating no significant impact.
- Multivariate feature selection with XGBoost outperformed univariate selection with Random Forest (p=0.028).
Conclusions:
- A radiomics approach using T2-w + DWI features from an auto-fixed VOI can quantify CS PZ PCa phenotype.
- DCE imaging does not significantly improve diagnostic performance.
- Multivariate feature selection and XGBoost are preferred methods for developing such radiomics models.
