ABSTRACT
Objective: Multiparametric magnetic resonance imaging (MRI) has become the standard of care for the diagnosis of prostate cancer patients. This study aimed to evaluate the influence of preoperative MRI on the positive surgical margin (PSM) rates. Methods: We retrospectively reviewed 1070 prostate cancer patients treated with radical prostatectomy (RP) at Siriraj Hospital between January 2013 and September 2019. PSM rates were compared between those with and without preoperative MRI. PSM locations were analyzed. Results: In total, 322 (30.1%) patients underwent MRI before RP. PSM most frequently occurred at the apex (33.2%), followed by posterior (13.5%), bladder neck (12.7%), anterior (10.7%), posterolateral (9.9%), and lateral (2.3%) positions. In preoperative MRI, PSM was significantly lowered at the posterior surface (9.0% vs. 15.4%, p=0.01) and in the subgroup of urologists with less than 100 RP experiences (32% vs. 51%, odds ratio=0.51, p<0.05). Blood loss was also significantly decreased when a preoperative image was obtained (200 mL vs. 250 mL, p=0.02). Multivariate analysis revealed that only preoperative MRI status was associated with overall PSM and PSM at the prostatic apex. Neither the surgical approach, the neurovascular bundle sparing technique, nor the perioperative blood loss was associated with PSM. Conclusion: MRI is associated with less overall PSM, PSM at apex, and blood loss during RP. Additionally, preoperative MRI has shown promise in lowering the PSM rate among urologists who are in the early stages of performing RP.
ABSTRACT
BACKGROUND: Due to the low cancer-detection rate in patients with PIRADS category 3 lesions, we created machine learning (ML) models to facilitate decision-making about whether to perform prostate biopsies or monitor clinical information without biopsy results. METHODS: In our retrospective, single-center study, 101 eligible patients with at least one PIRADS category 3 lesion but no higher PIRADS lesions underwent MRI/US fusion biopsies between September 2017 and June 2020. Thirty additional patients were included as the validation cohort from the next chronological period from June 2020 to October 2020. Our ML research was a supervised classification problem, with a binary output based on pathological reports of cancerous or benign tissue. The clinical inputs were age, prostate-specific antigen (PSA), prostate volume, prostate-specific antigen density (PSAD), and the number of previous biopsies. The radiology-report inputs were the number of lesions, maximum lesion diameter, lesion location, and lesion zone. We subsequently removed the inputs with low importance. Logistic Regression, Support Vector Machine, Naive Bayes, Decision Tree, Random Forest, and eXtreme Gradient Boosting Tree (XGBoost) were employed. From receiver operating characteristic (ROC) curves, we determined Area Under the ROC Curve (AUC), the cut-off point, and sensitivity score (recall score) to evaluate the ML-model performance. RESULTS: Twenty-four adenocarcinoma patients had a mean age of 70 ± 5.79 years, a mean PSA of 12.42 ± 6.67 ng/ml, a mean prostate volume of 46.49 ± 23.13 ml, and a mean PSAD of 0.31 ± 0.22 ng/ml2 . Seventy-seven patients with benign tissue reports had a mean age of 66.39 ± 6.66 years, a mean PSA of 11.31 ± 7.50 ng/ml, a mean prostate volume of 65.25 ± 35.88 ml, and a mean PSAD of 0.19 ± 0.13 ng/ml2 . On the validation cohort, XGBoost had the best AUC of 0.76, which considered 80% sensitivity and 72% specificity at a probability cutoff of 57%. The remaining possible ML models performed worse with lesser AUC. The worst was Naïve Bayes, with AUC of 0.50. CONCLUSIONS: ML models facilitate PIRADS 3 patient selection for MRI/US fusion biopsies. ML could optimize how we use previously known clinical risk factors to their full potential.
