Related Experiment Video
Updated: Aug 16, 2025
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
Published on: March 21, 2025
Early biomarkers of extracapsular extension of prostate cancer using MRI-derived semantic features
Adalgisa Guerra1, Filipe Caseiro Alves2, Kris Maes3
1Radiology Department, Hospital da Luz Lisboa, Avenida Lusíada, n° 100, 1500-650, Lisbon, Portugal. gisaguerra@gmail.com.
Background:
To construct a model based on magnetic resonance imaging (MRI) features and histological and clinical variables for the prediction of pathology-detected extracapsular extension (pECE) in patients with prostate cancer (PCa).
Methods:
We performed a prospective 3 T MRI study comparing the clinical and MRI data on pECE obtained from patients treated using robotic-assisted radical prostatectomy (RARP) at our institution. The covariates under consideration were prostate-specific antigen (PSA) levels, the patient's age, prostate volume, and MRI interpretative features for predicting pECE based on the Prostate Imaging-Reporting and Data System (PI-RADS) version 2.0 (v2), as well as tumor capsular contact length (TCCL), length of the index lesion, and prostate biopsy Gleason score (GS). Univariable and multivariable logistic regression models were applied to explore the statistical associations and construct the model. We also recruited an additional set of participants-which included 59 patients from external institutions-to validate the model.
Results:
The study participants included 184 patients who had undergone RARP at our institution, 26% of whom were pECE+ (i.e., pECE positive). Significant predictors of pECE+ were TCCL, capsular disruption, measurable ECE on MRI, and a GS of ≥7(4 + 3) on a prostate biopsy. The strongest predictor of pECE+ is measurable ECE on MRI, and in its absence, a combination of TCCL and prostate biopsy GS was significantly effective for detecting the patient's risk of being pECE+. Our predictive model showed a satisfactory performance at distinguishing between patients with pECE+ and patients with pECE-, with an area under the ROC curve (AUC) of 0.90 (86.0-95.8%), high sensitivity (86%), and moderate specificity (70%).
Conclusions:
Our predictive model, based on consistent MRI features (i.e., measurable ECE and TCCL) and a prostate biopsy GS, has satisfactory performance and sufficiently high sensitivity for predicting pECE+. Hence, the model could be a valuable tool for surgeons planning preoperative nerve sparing, as it would reduce positive surgical margins.
Insights
A new model using MRI and biopsy data accurately predicts extracapsular extension in prostate cancer patients. This tool aids surgeons in planning nerve-sparing procedures and reducing positive surgical margins.
Area of Science:
- Oncology
- Radiology
- Urology
Background:
- Prostate cancer (PCa) diagnosis and treatment planning.
- Accurate prediction of extracapsular extension (ECE) is crucial for surgical outcomes.
- Pathology-detected ECE (pECE) impacts surgical margin status and nerve sparing.
Purpose of the Study:
- To develop and validate a predictive model for pECE in PCa patients.
- Integrate magnetic resonance imaging (MRI) features with clinical and histological data.
- Improve preoperative assessment of ECE for robotic-assisted radical prostatectomy (RARP).
Main Methods:
- Prospective 3T MRI study including 184 RARP patients.
- Analysis of covariates: PSA, age, prostate volume, PI-RADS v2, tumor capsular contact length (TCCL), index lesion length, Gleason score (GS).
- Univariable/multivariable logistic regression and external validation with 59 additional patients.
Main Results:
- 26% of patients had pECE.
- Significant predictors: TCCL, capsular disruption, measurable ECE on MRI, GS ≥7(4+3).
- Model achieved AUC of 0.90, sensitivity 86%, specificity 70% for pECE prediction.
Conclusions:
- A predictive model combining MRI features (measurable ECE, TCCL) and biopsy GS effectively predicts pECE.
- The model demonstrates satisfactory performance and high sensitivity.
- This tool can aid surgeons in preoperative planning, potentially reducing positive surgical margins.
