RESUMO
Background: The Prostate Imaging for Recurrence Reporting (PI-RR) system was recently proposed to assess the local recurrence of prostate cancer (PCa), but its exact performance for the prostate after radiotherapy or radical prostatectomy is difficult to determine. We aimed to evaluate the diagnostic performance and interreader agreement of this system using whole-mount histology of the prostate after androgen deprivation therapy (ADT) as the standard of reference. Methods: In total, 119 patients with PCa post-ADT underwent multiparametric magnetic resonance imaging (mp-MRI) before prostatectomy. Three radiologists analyzed the MRI images independently, scoring imaging findings according to PI-RR. Spearman correlation was performed to assess the relationship between the percentage of sectors with residual cancer and PI-RR score. The diagnostic performance for detection of residual cancer was assessed on a per-sector basis. The chi-squared test was used to compare the cancer detection rate (CDR) among readers. Overall and pairwise interreader agreement in assigning PI-RR categories and residual cancer sectors with a score ≥3 or ≥4 were evaluated with the Cohen kappa coefficient. Results: Histology revealed 209 sectors with residual cancer. The percentage of pathologically positive sectors increased with the increase in PI-RR score for all readers. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) at a cutoff of score 3 ranged from 74.2% to 83.7%, 86.4% to 92.7%, 51.3% to 64.3%, and 95.4% to 96.9%, respectively, and at a cutoff of score 4, they ranged from 47.4% to 56.5%, 97.9% to 98.6%, 82.5% to 85.3%, and 91.6% to 92.9%, respectively. There was no significant difference among the CDR of readers. In PI-RR categories and detection of residual cancer sectors, overall interreader agreement was moderate for all readers, but agreement was higher between the more experienced readers (moderate to substantial) than between the more and less experienced readers (fair to moderate). Conclusions: MRI scoring with the PI-RR assessment provided accurate evaluation of PCa after ADT, but readers' experience influenced interreader agreement and cancer diagnosis.
RESUMO
BACKGROUND: TP53 mutations are associated with prostate cancer (PCa) prognosis and therapy. PURPOSE: To develop TP53 mutation classification models for PCa using MRI radiomics and clinicopathological features. STUDY TYPE: Retrospective. POPULATION: 388 patients with PCa from two centers (Center 1: 281 patients; Center 2: 107 patients). Cases from Center 1 were randomly divided into training and internal validation sets (7:3). Cases from Center 2 were used for external validation. FIELD STRENGTH/SEQUENCE: 3.0T/T2-weighted imaging, dynamic contrast-enhanced imaging, diffusion-weighted imaging. ASSESSMENT: Each patient's index tumor lesion was manually delineated on the above MRI images. Five clinicopathological and 428 radiomics features were obtained from each lesion. Radiomics features were selected by least absolute shrinkage and selection operator and binary logistic regression (LR) analysis, while clinicopathological features were selected using Mann-Whitney U test. Radiomics models were constructed using LR, support vector machine (SVM), and random forest (RF) classifiers. Clinicopathological-radiomics combined models were constructed using the selected radiomics and clinicopathological features with the aforementioned classifiers. STATISTICAL TESTS: Mann-Whitney U test. Receiver operating characteristic (ROC) curve analysis and area under the curve (AUC). P value <0.05 indicates statistically significant. RESULTS: In the internal validation set, the radiomics model had an AUC of 0.74 with the RF classifier, which was significantly higher than LR (AUC = 0.61), but similar to SVM (AUC = 0.69; P = 0.422). For the combined model, the AUC of RF model was 0.84, which was significantly higher than LR (0.64), but similar to SVM (0.80; P = 0.548). Both the combined RF and combined SVM models showed significantly higher AUCs than the radiomics models. In the external validation set, the combined RF and combined SVM models showed AUCs of 0.83 and 0.82. DATA CONCLUSION: Pathological-radiomics combined models with RF, SVM show the association of TP53 mutations and pathological-radiomics features of PCa. EVIDENCE LEVEL: 3 TECHNICAL EFFICACY: Stage 2.