The development and assessment of a predicting nomogram for the recovery of immediate urinary continence following laparoscopic radical prostatectomy

Preoperative Prostate Magnetic Resonance Imaging-based Anatomical Predictors of Early Urinary Continence Following Single-port Transvesical Robot-assisted Radical Prostatectomy

BACKGROUND AND OBJECTIVE

The introduction of the single-port (SP) robotic system has led to new approaches in robot-assisted radical prostatectomy (RARP), such as the transvesical (TV) approach, offering high rates of early urinary continence. While previous studies of SP TV RARP have identified perioperative factors influencing continence outcomes, the impact of anatomical factors remains unexplored. This study aims to assess magnetic resonance imaging (MRI)-based anatomical predictors of urinary continence after SP TV RARP.

METHODS

A retrospective analysis of consecutive SP TV RARP cases (November 2020 to June 2023) with preoperative prostate MRI was performed. Two urogenital radiologists independently evaluated ten anatomical parameters to distinguish patients achieving urinary continence within 1 wk and 3 mo. Nonparametric methods estimated receiver operating characteristic curves (area under the curve [AUC]) and inter-reader agreement.

KEY FINDINGS AND LIMITATIONS

In 120 cases, 40% achieved continence within 1 wk, rising to 71.7% by 3 mo. Membranous urethra length (MUL) alone was significantly associated with continence at 3 mo (AUC: 0.67, p = 0.003). At 1 wk, several parameters, including anteroposterior diameter of the prostate, coronal membranous urethra length, prostate volume, and transverse diameter of the prostate, showed promise in predicting continence.

CONCLUSIONS AND CLINICAL IMPLICATIONS

A longer preoperative MUL was significantly associated with better odds of an early return to urinary continence after SP TV RARP. Each 1-mm increase in coronal MUL was associated with a 27% increase in the odds of continence at 3 mo. This information can aid in patient counseling and expectations preoperatively.

PATIENT SUMMARY

Urinary incontinence is a common outcome after prostate cancer surgery, particularly in the early months. Recently, the single-port (SP) robotic system has emerged, localizing surgery to the diseased area. With the SP robot, accessing the prostate via the bladder leads to high rates of early continence. Our study reveals that the longer the urethral portion beneath the prostate, the higher the likelihood of regaining continence within 3 mo after surgery.

Membranous urethral length is the single independent predictor of urinary continence recovery at 12 months following Retzius-sparing robot-assisted radical prostatectomy

The influence of anatomical parameters on urinary continence (UC) after Retzius-sparing robot-assisted radical prostatectomy (RS-RARP) remains uncharted. Our objective was to evaluate their association with UC at 3, 6 and 12 months post-operatively. Data from patients who underwent RS-RARP were prospectively collected. Continence was defined as no pad use. Anatomic variables were measured on preoperative magnetic resonance imaging (MRI). Regression analyses were performed to identify predictors of UC at each time point. We included 158 patients with a median age of 60 years, most of whom had a localized tumor (≤ cT2). On multivariate analyses, at 3 months post-surgery, urinary incontinence (UI) rises with age, odds ratio (OR) 1.07 [95% confidence interval (CI) 1.004-1.142] and with prostate volume (PV), OR 1.029 (95% CI 1.006-1.052); it reduces with longer membranous urethral length (MUL), OR 0.875 (95% CI 0.780-0.983) and with higher membranous urethral volume (MUV), OR 0.299 (95% CI 0.121-0.737). At 6 months, UI rises with PV, OR 1.033 (95% CI 1.011-1.056) and decreases with MUV, OR 0.1504 (95% CI 0.050-0.444). Significantly, at 12 months post-surgery, the only predictor of UI is MUL, OR 0.830 (95% CI 0.706-0.975), establishing a threshold associated with a risk of UI of 5% (MUL > 15 mm) in opposition to a risk of 25% (MUL < 10 mm). This single institutional study requires external validation. To our knowledge, this is the first prospective cohort study supporting MUL as the single independent predictor of UC at 12 months post-surgery. By establishing MUL thresholds, we enable precise patient counseling.

Development of Machine Learning Algorithm to Predict the Risk of Incontinence After Robot-Assisted Radical Prostatectomy

Introduction: Predicting postoperative incontinence beforehand is crucial for intensified and personalized rehabilitation after robot-assisted radical prostatectomy. Although nomograms exist, their retrospective limitations highlight artificial intelligence (AI)'s potential. This study seeks to develop a machine learning algorithm using robot-assisted radical prostatectomy (RARP) data to predict postoperative incontinence, advancing personalized care. Materials and Methods: In this propsective observational study, patients with localized prostate cancer undergoing RARP between April 2022 and January 2023 were assessed. Preoperative variables included age, body mass index, prostate-specific antigen (PSA) levels, digital rectal examination (DRE) results, Gleason score, International Society of Urological Pathology grade, and continence and potency questionnaires responses. Intraoperative factors, postoperative outcomes, and pathological variables were recorded. Urinary continence was evaluated using the Expanded Prostate cancer Index Composite questionnaire, and machine learning models (XGBoost, Random Forest, Logistic Regression) were explored to predict incontinence risk. The chosen model's SHAP values elucidated variables impacting predictions. Results: A dataset of 227 patients undergoing RARP was considered for the study. Post-RARP complications were predominantly low grade, and urinary continence rates were 74.2%, 80.7%, and 91.4% at 7, 13, and 90 days after catheter removal, respectively. Employing machine learning, XGBoost proved the most effective in predicting postoperative incontinence risk. Significant variables identified by the algorithm included nerve-sparing approach, age, DRE, and total PSA. The model's threshold of 0.67 categorized patients into high or low risk, offering personalized predictions about the risk of incontinence after surgery. Conclusions: Predicting postoperative incontinence is crucial for tailoring rehabilitation after RARP. Machine learning algorithm, particularly XGBoost, can effectively identify those variables more heavily, impacting the outcome of postoperative continence, allowing to build an AI-driven model addressing the current challenges in post-RARP rehabilitation.

Automated pelvic MRI measurements associated with urinary incontinence for prostate cancer patients undergoing radical prostatectomy

BACKGROUND

Pelvic morphological parameters on magnetic resonance imaging (MRI), such as the membranous urethral length (MUL), can predict urinary incontinence after radical prostatectomy but are prone to interobserver disagreement. Our objective was to improve interobserver agreement among radiologists in measuring pelvic parameters using deep learning (DL)-based segmentation of pelvic structures on MRI scans.

METHODS

Preoperative MRI was collected from 167 prostate cancer patients undergoing radical prostatectomy within our regional multicentric cohort. Two DL networks (nnU-Net) were trained on coronal and sagittal scans and evaluated on a test cohort using an 80/20% train-test split. Pelvic parameters were manually measured by three abdominal radiologists on raw MRI images and with the use of DL-generated segmentations. Automated measurements were also performed for the pelvic parameters. Interobserver agreement was evaluated using the intraclass correlation coefficient (ICC) and the Bland-Altman plot.

RESULTS

The DL models achieved median Dice similarity coefficient (DSC) values of 0.85-0.97 for coronal structures and 0.87-0.98 for sagittal structures. When radiologists used DL-generated segmentations of pelvic structures, the interobserver agreement for sagittal MUL improved from 0.64 (95% confidence interval 0.28-0.83) to 0.91 (95% CI 0.84-0.95). Furthermore, there was an increase in ICC values for the obturator internus muscle from 0.74 (95% CI 0.42-0.87) to 0.86 (95% CI 0.75-0.92) and for the levator ani muscle from 0.40 (95% CI 0.05-0.66) to 0.61 (95% CI 0.31-0.78).

CONCLUSIONS

DL-based automated segmentation of pelvic structures improved interobserver agreement in measuring pelvic parameters on preoperative MRI scans.

RELEVANCE STATEMENT

The implementation of deep learning segmentations allows for more consistent measurements of pelvic parameters by radiologists. Standardized measurements are crucial for incorporating these parameters into urinary continence prediction models.

KEY POINTS

• DL-generated segmentations improve interobserver agreement for pelvic measurements among radiologists. • Membranous urethral length measurement improved from substantial to almost perfect agreement. • Artificial intelligence enhances objective pelvic parameter assessment for continence prediction models.