Prediction Of Extracapsular Extension Research Articles

Optimization and validation of 18F-DCFPyL PET radiomics-based machine learning models in intermediate- to high-risk primary prostate cancer.

Radiomics extracted from prostate-specific membrane antigen (PSMA)-PET modeled with machine learning (ML) may be used for prediction of disease risk. However, validation of previously proposed approaches is lacking. We aimed to optimize and validate ML models based on 18F-DCFPyL-PET radiomics for the prediction of lymph-node involvement (LNI), extracapsular extension (ECE), and postoperative Gleason score (GS) in primary prostate cancer (PCa) patients. Patients with intermediate- to high-risk PCa who underwent 18F-DCFPyL-PET/CT before radical prostatectomy with pelvic lymph-node dissection were evaluated. The training dataset included 72 patients, the internal validation dataset 24 patients, and the external validation dataset 27 patients. PSMA-avid intra-prostatic lesions were delineated semi-automatically on PET and 480 radiomics features were extracted. Conventional PET-metrics were derived for comparative analysis. Segmentation, preprocessing, and ML methods were optimized in repeated 5-fold cross-validation (CV) on the training dataset. The trained models were tested on the combined validation dataset. Combat harmonization was applied to external radiomics data. Model performance was assessed using the receiver-operating-characteristics curve (AUC). The CV-AUCs in the training dataset were 0.88, 0.79 and 0.84 for LNI, ECE, and GS, respectively. In the combined validation dataset, the ML models could significantly predict GS with an AUC of 0.78 (p<0.05). However, validation AUCs for LNI and ECE prediction were not significant (0.57 and 0.63, respectively). Conventional PET metrics-based models had comparable AUCs for LNI (0.59, p>0.05) and ECE (0.66, p>0.05), but a lower AUC for GS (0.73, p<0.05). In general, Combat harmonization improved external validation AUCs (-0.03 to +0.18). In internal and external validation, 18F-DCFPyL-PET radiomics-based ML models predicted high postoperative GS but not LNI or ECE in intermediate- to high-risk PCa. Therefore, the clinical benefit seems to be limited. These results underline the need for external and/or multicenter validation of PET radiomics-based ML model analyses to assess their generalizability.

The feasibility of distance to the tumor of biopsy cores to estimate the extracapsular extension

BackgroundTo investigate the predictive capability of a new parameter, the distance between the fibromuscular capsule and the tumor as measured using a prostate biopsy core (referred to as “distance to the tumor” [DTT]), for the presence of extracapsular extension (ECE). Materials and methodsWe analyzed specimens obtained from 246 patients diagnosed with prostate cancer. All patients underwent prebiopsy, prostate magnetic resonance imaging (MRI), and subsequent prostatectomy. DTT measurements were obtained for each prostate biopsy core, and the minimum (min) DTT was extracted. We assessed the relationship between min DTT, MRI-estimated ECE, and pathological ECE, considering factors such as the PI-RADS score and tumor location. ResultsIn this study of 246 patients, the mean age was 65.8 years, and the mean prostate-specific antigen (PSA) level was 18.9 ng/ml. Patients with suspicious lesions in the peripheral zone and pathological ECE displayed higher rates of positive digital rectal examination (DRE), elevated PSA levels, and shorter DTT values in the biopsy cores. DTT demonstrated an accurate estimation of the presence of ECE, similar to MRI findings. Min DTT exhibited higher accuracy for peripheral zone masses, with a cutoff value of 1.0 mm for min DTT predicting ECE (AUC: 0.84, sensitivity: 72.23%, specificity: 77.78%, P < 0.01). Of the 246 patients, 66 had no ECE on MRI; however, 18 of these patients displayed pathological ECE, with 14 having DTT values <1.0 mm. ConclusionsMin DTT, positive DRE results, and a higher Gleason grade were significantly associated with ECE. DTT measurements of <1 mm can provide a more accurate prediction of ECE in the peripheral zone of the prostate than MRI-based assessments.

Prediction of extracapsular extension in prostate cancer using the Likert scale combined with clinical and pathological parameters.

This study aimed to investigate the independent clinical, pathological, and radiological factors associated with extracapsular extension in radical prostatectomy specimens and to improve the accuracy of predicting extracapsular extension of prostate cancer before surgery. From August 2018 to June 2023, the clinical and pathological data of 229 patients with confirmed prostate cancer underwent radical prostatectomy from The Second Hospital of Yinzhou. The patients' multiparametric magnetic resonance imaging data were graded using the Likert scale. The chi-square or independent-sample T-test was used to analyze the related factors for an extracapsular extension. Multivariate analysis was used to identify independent factors associated with extracapsular extension in prostate cancer. Additionally, receiver operating characteristic curve analysis was used to calculate the area under the curve and assess the diagnostic performance of our model. The clinical decision curve was used to analyze the clinical net income of Likert scale, biopsy positive rate, biopsy GG, and combined mode. Of the 229 patients, 52 had an extracapsular extension, and 177 did not. Multivariate analysis showed that the Likert scale score, biopsy grade group and biopsy positive rate were independent risk factors for extracapsular extension in prostate cancer. The area under the curves for the Likert scale score, biopsy grade group, and biopsy positive rate were 0.802, 0.762, and 0.796, respectively. Furthermore, there was no significant difference in the diagnostic efficiency for extracapsular extension (P>0.05). However, when these three factors were combined, the diagnostic efficiency was significantly improved, and the area under the curve increased to 0.905 (P<0.05). In the analysis of the decision curve, The clinical net income of the combined model is obviously higher than that of Likert scale, biopsy positive rate, and biopsy GG. The Likert scale, biopsy grade group and biopsy positive rate are independent risk factors for extracapsular extension in prostate cancer, and their combination can significantly improve the diagnostic efficiency for an extracapsular extension.

PD10-10 IMPROVING PREDICTION OF LOCAL STAGE BY PSMA-PET. DEVELOPMENT OF A NOVEL INTEGRATED TOOL FOR EXTRACAPSULAR EXTENSION AND SEMINAL VESICLE INVASION COMBINING CLINICAL AND IMAGING FEATURES IN LOCALIZED PROSTATE CANCER

PD10-10 IMPROVING PREDICTION OF LOCAL STAGE BY PSMA-PET. DEVELOPMENT OF A NOVEL INTEGRATED TOOL FOR EXTRACAPSULAR EXTENSION AND SEMINAL VESICLE INVASION COMBINING CLINICAL AND IMAGING FEATURES IN LOCALIZED PROSTATE CANCER

Added value of shear-wave elastography in the prediction of extracapsular extension and seminal vesicle invasion before radical prostatectomy.

The purpose of this study was to analyze the value of transrectal shear-wave elastography (SWE) in combination with multivariable tools for predicting adverse pathological features before radical prostatectomy (RP). Preoperative clinicopathological variables, multiparametric magnetic resonance imaging (mp-MRI) manifestations, and the maximum elastic value of the prostate (Emax) on SWE were retrospectively collected. The accuracy of SWE for predicting adverse pathological features was evaluated based on postoperative pathology, and parameters with statistical significance were selected. The diagnostic performance of various models, including preoperative clinicopathological variables (model 1), preoperative clinicopathological variables + mp-MRI (model 2), and preoperative clinicopathological variables + mp-MRI + SWE (model 3), was evaluated with area under the receiver operator characteristic curve (AUC) analysis. Emax was significantly higher in prostate cancer with extracapsular extension (ECE) or seminal vesicle invasion (SVI) with both P < 0.001. The optimal cutoff Emax values for ECE and SVI were 60.45 kPa and 81.55 kPa, respectively. Inclusion of mp-MRI and SWE improved discrimination by clinical models for ECE (model 2 vs model 1, P = 0.031; model 3 vs model 1, P = 0.002; model 3 vs model 2, P = 0.018) and SVI (model 2 vs model 1, P = 0.147; model 3 vs model 1, P = 0.037; model 3 vs model 2, P = 0.134). SWE is valuable for identifying patients at high risk of adverse pathology.

External Validation of Models for Prediction of Side-specific Extracapsular Extension in Prostate Cancer Patients Undergoing Radical Prostatectomy

BackgroundPredicting the risk of side-specific extracapsular extension (ECE) is essential for planning nerve-sparing radical prostatectomy (RP) in patients with prostate cancer (PCa). ObjectiveTo externally validate available models for prediction of ECE. Design, setting, and participantsSixteen models were assessed in a cohort of 737 consecutive PCa patients diagnosed via multiparametric magnetic resonance imaging (MRI)-targeted and systematic biopsies and treated with RP between January 2016 and November 2021 at eight referral centers. Outcome measurements and statistical analysisModel performance was evaluated in terms of discrimination using area under the receiver operating characteristic curve (AUC), calibration plots, and decision curve analysis (DCA). Results and limitationsOverall, ECE was identified in 308/1474 (21%) prostatic lobes. Prostatic lobes with ECE had higher side-specific clinical stage on digital rectal examination and MRI, number of positive biopsy cores, and International Society of Urological Pathology grade group in comparison to those without ECE (all p < 0.0001). Less optimistic performance was observed in comparison to previous published studies, although the models described by Pak, Patel, Martini, and Soeterik achieved the highest accuracy (AUC ranging from 0.73 to 0.77), adequate calibration for a probability threshold <40%, and the highest net benefit for a probability threshold >8% on DCA. Inclusion of MRI-targeted biopsy data and MRI information in models improved patient selection and clinical usefulness. Using model-derived cutoffs suggested by their authors, approximately 15% of positive surgical margins could have been avoided. Some available models were not included because of missing data, which constitutes a limitation of the study. ConclusionsWe report an external validation of models predicting ECE and identified the four with the best performance. These models should be applied for preoperative planning and patient counseling. Patient summaryWe validated several tools for predicting extension of prostate cancer outside the prostate gland. These tools can improve patient selection for surgery that spares nerves affecting recovery of sexual potency after removal of the prostate. They could potentially reduce the risk of finding cancer cells at the edge of specimens taken for pathology, a finding that suggests that not all of the cancer has been removed.

Integration of Prostate Biopsy Results with Pre-Biopsy Multiparametric Magnetic Resonance Imaging Findings Improves Local Staging of Prostate Cancer.

To assess the added value of histological information for local staging of prostate cancer (PCa) by comparing the accuracy of multiparametric MRI alone (mpMRI) and mpMRI with biopsy Gleason grade (mpMRI+Bx). 133 consecutive patients who underwent preoperative 3T-MRI and subsequent radical prostatectomy for PCa were included in this single-centre retrospective study. mpMRI imaging was reviewed independently by two uroradiologists for the presence of extracapsular extension (ECE) and seminal vesicle invasion (SVI) on a 5-point Likert scale. For second reads, the radiologists received results of targeted fused MR/US biopsy (mpMRI+Bx) prior to re-staging. The median patient age was 63years (interquartile range (IQR) 58-67years) and median PSA was 6.5ng/mL (IQR 5.0-10.0ng/mL). Extracapsular extension was present in 85/133 (63.9%) patients and SVI was present in 22/133 (16.5%) patients. For ECE prediction, mpMRI showed sensitivity and specificity of 63.5% and 81.3%, respectively, compared to 77.7% and 81.3% achieved by mpMRI+Bx. At an optimal cut-off value of Likert score ≥ 3, areas under the curves (AUCs) was .85 for mpMRI+Bx and .78 for mpMRI, P < .01. For SVI prediction, AUC was .95 for mpMRI+Bx compared to .92 for mpMRI; P = .20. Inter-reader agreement for ECE and SVI prediction was substantial for mpMRI (k range, .78-.79) and mpMRI+Bx (k range, .74-.79). MpMRI+Bx showed superior diagnostic performance with an increased sensitivity for ECE prediction but no significant difference for SVI prediction. Inter-reader agreement was substantial for both protocols. Integration of biopsy information adds value when staging prostate mpMRI.

Integrating Quantitative Radiomics in De-intensification Treatment for Oropharyngeal Carcinoma

Deintensification for early-stage oropharyngeal carcinoma includes surgery +/- adjuvant radiation therapy without the use of concurrent chemotherapy. Pathologic findings of nodal extracapsular extension (ECE), however, obligate the use of postoperative concurrent chemotherapy in these patients. The purpose of this study was to develop a robust predictive model for ECE using quantitative radiomics.Between 2016 and 2020, 81 patients with newly diagnosed resectable oropharyngeal carcinoma underwent upfront transoral robotic surgery and neck dissection at our institutions. In all these patients, high-resolution CT scans were done preoperatively and were concluded to have no evidence of ECE by experienced head and neck radiologists. Eight five percent of tumors were HPV-positive. Median age was 63 years. Radiomics features (107 features) from the primary and extended nodal regions (1-3 mm extension) were extracted to generate predictive models. Two feature selection approaches were evaluated: Minimum Redundancy Maximum Relevance (MRMR) and Linear Discriminant Analysis (LDA). Logistic regression, decision tree, and random forests classifier were chosen for our analysis.Thirty eight percent of patients were found to have ECE in at least one of the nodes, and therefore received concurrent chemoradiation postoperatively. There was a total of 119 pathological positive nodes. Of these positive nodes, 31 nodes were found to have ECE with a ECE of less than 1 to 10mm. Five-fold stratified cross-validation was used for evaluation. A 96% accuracy (0.95 AUC, 0.96 recall) was achieved from the primary node without extension, using LDA feature selection. An improved result of 97% accuracy (0.96 AUC, 0.97 recall) was obtained with the 3mm extension. MRMR attained the maximum accuracy of 77% (0.64 AUC, 0.36 recall) with the 3mm extension.Quantitative radiomics allows a robust prediction of ECE, thereby optimizing de-intensification therapy for oropharyngeal carcinoma.

Predictors of Extracapsular Extension in Patients With Squamous Cell Carcinoma of the Head and Neck and Outcome Analysis.

IntroductionExtracapsular extension (ECE) in the lymph nodes for patients with head and neck cancer has been found to be a poor prognostic factor in multiple studies. The purpose of the study is to evaluate the predictive factors for ECE on computer tomography (CT) imaging for patients undergoing surgery and to analyze outcomes.MethodsWe conducted an Institutional Review Board-approved, Health Insurance Portability and Accountability Act (HIPAA)-compliant retrospective review of 82 patients with biopsy-proven squamous cell carcinomas of the head and neck who underwent definitive surgery without neoadjuvant chemotherapy or radiation therapy. CT scans were evaluated for the level of involvement, size, and presence or absence of central necrosis. Extracapsular extension in lymph nodes on the postoperative pathology was correlated with the central necrosis in the lymph nodes appreciated on the CT neck with contrast. Survival estimates were evaluated using the Kaplan-Meier test.ResultsECE on postoperative pathology was seen in 74.07% of patients who had evidence of central necrosis in lymph nodes on preoperative CT neck compared to 46.43% without CT necrosis (p=0.013). The incidence of ECE is higher in poorly differentiated tumors and also nodal stages >N2c at presentation. Patents with ECE had inferior disease-free and overall survival (OS).ConclusionsOur results reveal that patients with necrosis on CT and with moderately to poorly differentiated tumors have a high incidence of extracapsular extension. There was no difference in local control (LC) between the groups of patients, but the OS was inferior in patients with ECE. Predicting extracapsular extension upfront helps to formulate the appropriate treatment. We propose to study additional chemotherapy to improve outcomes in patients with positive extracapsular extension.

Comparison of biparametric versus multiparametric prostate MRI for the detection of extracapsular extension and seminal vesicle invasion in biopsy naïve patients

PurposeTo compare biparametric MRI (bpMRI) with multiparametric MRI (mpMRI) staging accuracy in assessing extracapsular extension (ECE) and seminal vesicle invasion (SVI). MethodBiopsy-naïve patients undergoing 3 T-MRI before radical prostatectomy for clinically significant prostate cancer were included in this single-centre retrospective study. Two uroradiologists separately evaluated bpMRI and mpMRI for presence of ECE and SVI using a 5-point Likert scale (1: ECE/SVI highly unlikely, 5: ECE/SVI highly likely). Results110 men of median age 63 years and PSA 8.5 ng/mL were included. ECE and SVI was confirmed histologically in 71/110 (64.5 %) and 18/110 (16.4 %) patients, respectively. Sensitivity and specificity of bpMRI versus mpMRI for predicting ECE was 59.1 % and 87.2 % versus 66.2 % and 84.6 %, respectively. For SVI detection, the sensitivity and specificity for bpMRI versus mpMRI was 66.7 % and 92.4 % versus 83.3 % and 97.8 %, respectively. At an optimal cut-off Likert score ≥3 for ECE prediction, mpMRI area under the receiver operating curve (AUC) was 0.80 (95 % confidence interval (CI) 0.72–0.87) versus 0.78 (95 % CI 0.69–0.86) for bpMRI (p = 0.52) and for SVI, mpMRI AUC was 0.91 (95 % CI 0.84–0.96) versus 0.86 (95 % CI 0.78–0.92) for bpMRI (p = 0.02), respectively. Inter-reader agreement for both ECE and SVI prediction was substantial, with a marginally higher k-value for mpMRI (k range, 0.67–0.75) than bpMRI (k range, 0.65–0.69). ConclusionsDiagnostic performance of bpMRI and mpMRI was comparable for detection of ECE, however, mpMRI with contrast was superior for SVI detection and improved the inter-reader agreement.

Can we use neutrophil to lymphocyte ratio in the diagnosis and prediction of extracapsular extension in localized prostate cancer?

We investigated role of neutrophil-to-lymphocyte ratio (NLR) in the diagnosis and prediction of extracapsular extension (ECE) in clinically localized prostate cancer (PCa). A total of 396 patients with clinically localized PCa who underwent open radical retropubic prostatectomy (RRP), and 260 patients with benign prostatic hyperplasia (BPH) who underwent suprapubic prostatectomy were included in the study. Preoperative NLR, prostate specific antigen (PSA), prostate specific antigen density (PSAD), free PSA, prostate volume (PV), free/total PSA (f/t PSA) in both groups, and relation of NLR with PSA, Gleason Score (GS), and pathologic stage in PCa group were investigated. Records of patients were analyzed retrospectively. NLR, free PSA, f/t PSA, and PV were statistically higher in BHP, and PSAD was higher in PCa group. In PCa group, NLR was found to be higher in patients with PSA >10 ng/ml compared to those with less than ⩽10 ng/ml. NLR increases as the preoperative GS increases, and it was higher in pT3 patients than pT2 patients. NLR was statistically higher in those patients with positive lymph nodes than those without after RRP (p = 0.029). NLR is not a sufficient biomarker in differentiating clinically localized PCa from BPH. NLR increases as preoperative GS and pathologic stage increases. Lymph node involved patients after RRP have statistically higher NLR. NLR can be an indicator of ECE and lymph-node involvement in clinically localized PCa.

Abstract PO-039: Artificial intelligence-based extracapsular extension prediction in head and neck cancer analysis

Abstract Extracapsular extension (ECE) is a decisive indication for treatment planning of patients with head and neck squamous cell carcinoma (HNSCC). ECE occurs when metastatic tumor cells within the lymph node break through the nodal capsule into surrounding tissues. It is crucial to identify whether ECE occurs in HNSCC patient treatment. Current ECE detection practice mainly relies on the visual identification of doctors and professionals, which can be extremely labor intensive and time-consuming. Therefore, we aim to automatically perform ECE detection using a machine learning technique to classify whether ECE appears or not. In this research, we propose a systematic machine learning approach to detect ECE from 3D computed tomography (CT) scans. The process includes four steps: 1) apply sliding-cube to extract small 3D samples from patient data; 2) various 3D features are extracted for each sample; and 3) three machine learning models, gradient boosting (GB), random forest (RF), and support vector machine (SVM), with feature extraction and selection approaches, are employed for sample classification task; 4) classify the patient based on sample classification result. Different training scenarios are designed for the experimental test. Based on five-fold cross-validation, the experimental results have demonstrated that our model is able to classify ECE and non-ECE patients. To check the explainability of the models, feature analysis is also conducted. The outcome of this research is expected to promote the implementation of artificial intelligence for ECE classification and detection as well as head and neck cancer diagnosis in the radiology computer vision field. Citation Format: Yibin Wang, William N. Duggar, Toms V. Thomas, Paul Roberts, Linkan Bian, Haifeng Wang. Artificial intelligence-based extracapsular extension prediction in head and neck cancer analysis [abstract]. In: Proceedings of the AACR Virtual Special Conference on Artificial Intelligence, Diagnosis, and Imaging; 2021 Jan 13-14. Philadelphia (PA): AACR; Clin Cancer Res 2021;27(5_Suppl):Abstract nr PO-039.

Radiomics and Prostate MRI: Current Role and Future Applications.

Multiparametric prostate magnetic resonance imaging (mpMRI) is widely used as a triage test for men at a risk of prostate cancer. However, the traditional role of mpMRI was confined to prostate cancer staging. Radiomics is the quantitative extraction and analysis of minable data from medical images; it is emerging as a promising tool to detect and categorize prostate lesions. In this paper we review the role of radiomics applied to prostate mpMRI in detection and localization of prostate cancer, prediction of Gleason score and PI-RADS classification, prediction of extracapsular extension and of biochemical recurrence. We also provide a future perspective of artificial intelligence (machine learning and deep learning) applied to the field of prostate cancer.

External Validation of a Multiparametric Magnetic Resonance Imaging–based Nomogram for the Prediction of Extracapsular Extension and Seminal Vesicle Invasion in Prostate Cancer Patients Undergoing Radical Prostatectomy

The nomogram reported by Gandaglia et al (The key combined value of multiparametric magnetic resonance imaging, and magnetic resonance imaging-targeted and concomitant systematic biopsies for the prediction of adverse pathological features in prostate cancer patients undergoing radical prostatectomy. Eur Urol 2020;77:733–41) predicting extracapsular extension (ECE) or seminal vesicle invasion (SVI) has been developed using multiparametric magnetic resonance imaging (MRI) parameters and MRI-targeted biopsy. We aimed to validate this nomogram externally by analyzing 566 patients harboring prostate cancer diagnosed on MRI-targeted biopsy followed by radical prostatectomy. At final pathology, 37% and 12% patients had ECE and SVI, respectively. Performance of the nomogram, in comparison with the Memorial Sloan Kettering Cancer Center (MSKCC) model and Partin tables, was evaluated using discrimination, calibration, and decision curve analysis. Regarding ECE prediction, the nomogram showed higher discrimination (71.8% vs 69.8%, p = 0.3 and 71.8% vs 61.3%, p < 0.001), and similar miscalibration and net benefit for probability threshold above 30% when compared with MSKCC model and Partin tables, respectively. Performance of the nomogram with regard to SVI was comparable in terms of discrimination (68.5% vs 70.4% vs 67.8%, p ≥ 0.6), presenting a slight overestimation on calibration plots and a net benefit for probability threshold above 7.5%. This is the first multicentric study that externally validates a nomogram predicting ECE and SVI in patients diagnosed with MRI-targeted biopsy. Its performance was less optimistic than expected, and implementation of MRI in this setting was not associated with a clear improvement in patient selection and clinical usefulness when compared with available models. We proposed an updated version of the nomogram predicting ECE using the recalibration method, which leads to an improvement in its performance and needs to be validated in another external set. Patient summaryWe validate a prediction tool based on multiparametric magnetic resonance imaging (MRI) parameters and MRI-targeted biopsy predicting extracapsular extension and seminal vesicle invasion at radical prostatectomy. An improvement of patient selection was not clearly demonstrated when compared with available models based on clinical parameters, and implementation of MRI in this setting still needs to be clarified.

Added Value of Biparametric MRI and TRUS-Guided Systematic Biopsies to Clinical Parameters in Predicting Adverse Pathology in Prostate Cancer.

ObjectiveTo develop novel models for predicting extracapsular extension (EPE), seminal vesicle invasion (SVI), or upgrading in prostate cancer (PCa) patients using clinical parameters, biparametric magnetic resonance imaging (bp-MRI), and transrectal ultrasonography (TRUS)-guided systematic biopsies.Patients and MethodsWe retrospectively collected data from PCa patients who underwent standard (12-core) systematic biopsy and radical prostatectomy. To develop predictive models, the following variables were included in multivariable logistic regression analyses: total prostate-specific antigen (TPSA), central transition zone volume (CTZV), prostate-specific antigen (PSAD), maximum diameter of the index lesion at bp-MRI, EPE at bp-MRI, SVI at bp-MRI, biopsy Gleason grade group, and number of positive biopsy cores. Three risk calculators were built based on the coefficients of the logit function. The area under the curve (AUC) was applied to determine the models with the highest discrimination. Decision curve analyses (DCAs) were performed to evaluate the net benefit of each risk calculator.ResultsA total of 222 patients were included in this study. Overall, 83 (37.4%), 75 (33.8%), and 107 (48.2%) patients had EPE, SVI, and upgrading at final pathology, respectively. The addition of bp-MRI data improved the discrimination of models for predicting SVI (0.807 vs 0.816) and upgrading (0.548 vs 0.625) but not EPE (0.766 vs 0.763). Similarly, models including clinical parameters, bp-MRI data, and information on systematic biopsies achieved the highest AUC in the prediction of EPE (0.842), SVI (0.913), and upgrading (0.794), and the three corresponding risk calculators yielded the highest net benefit.ConclusionWe developed three easy-to-use risk calculators for the prediction of adverse pathological features based on patient clinical parameters, bp-MRI data, and information on systematic biopsies. This may be greatly beneficial to urologists in the decision-making process for PCa patients.

MP62-10 UTILITY OF A MULTIVARIATE LOGISTIC REGRESSION MODEL FOR THE PREDICTION OF PROSTATE CANCER EXTRACAPSULAR EXTENSION BASED ON 3TMPMRI, CLINICAL, AND BIOPSY

You have accessJournal of UrologyProstate Cancer: Staging I (MP62)1 Apr 2020MP62-10 UTILITY OF A MULTIVARIATE LOGISTIC REGRESSION MODEL FOR THE PREDICTION OF PROSTATE CANCER EXTRACAPSULAR EXTENSION BASED ON 3TMPMRI, CLINICAL, AND BIOPSY Sohrab Afshari Mirak*, Robert Reiter, and Steven Raman Sohrab Afshari Mirak*Sohrab Afshari Mirak* More articles by this author , Robert ReiterRobert Reiter More articles by this author , and Steven RamanSteven Raman More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000000937.010AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Extracapsular extension (ECE) of prostate cancer (PCa) is a poor prognostic factor associated with progression, recurrence after treatment, and increased prostate cancer- related mortality. Accurate staging prior to radical prostatectomy is crucial in avoidance of positive margins and when planning nerve-sparing procedures. In this study, we investigated the predictive value of the clinical, biopsy & 3T multiparametric MRI (3TmpMRI) parameters using a multivariate logistic model for per-lesion detection of PCa extracapsular extension (ECE) with wholemount histopathology (WMHP) as reference. METHODS: This IRB approved, HIPAA compliant study included 575 patients with 774 true positive PCa lesions, who underwent radical prostatectomy between 7/2010-2/2019. The relationship between pathologic ECE & parameters including clinical; age, prostate specific antigen (PSA) & PSA density (PSAD), biopsy; percentage of positive systematic cores & Gleason score (GS) & 3TmpMRI; prostate volume, number of lesions per patient, size, location, level, PIRADSv2 score, laterality, apparent diffusion coefficient (ADC) value & risk of ECE on MRI was evaluated using bivariate and multivariate analysis. The accuracy of the final model was evaluated using ROC analysis. RESULTS: 27.8% (215/774), 42.9% (332/774) & 29.3% (227/774) of the lesions were PIRADSv2 score 3, 4 & 5 & 59.9% (464/774), 24.7% (191/774) & 17.7% (137/774) were low, intermediate & high risk for ECE, respectively. 23.6% (183/774) of the lesions had ECE on WMHP. On bivariate analysis higher PSA, PSAD, percentage of positive biopsy cores, biopsy GS, size, PIRADSv2 score, ADC value, risk of ECE on MRI, location (posterior), level (midgland & base), bilaterality & lower number of lesions per patient were significant for ECE prediction. The multivariate logistic model included age, PSAD, number of lesions per patient, size, location, level, PIRADSv2 score & risk of ECE on MRI. The AUC for the prediction of ECE for this model was 0.85. CONCLUSIONS: This multivariate regression model based on clinical, biopsy & 3TmpMRI parameters have a high predictive value for pathology ECE detection. Source of Funding: none © 2020 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 203Issue Supplement 4April 2020Page: e949-e949 Advertisement Copyright & Permissions© 2020 by American Urological Association Education and Research, Inc.MetricsAuthor Information Sohrab Afshari Mirak* More articles by this author Robert Reiter More articles by this author Steven Raman More articles by this author Expand All Advertisement PDF downloadLoading ...

PD57-03 NOMOGRAM INCLUDING MAXIMUM CORE LENGTH AT BIOPSY AND INDEX LESION SIZE AT MPMRI BEST PREDICTS THE EXTRACAPSULAR EXTENSION OF PROSTATE CANCER AT WHOLE-MOUNT SECTIONS OF RADICAL PROSTATECTOMIES

You have accessJournal of UrologyProstate Cancer: Staging II (PD57)1 Apr 2020PD57-03 NOMOGRAM INCLUDING MAXIMUM CORE LENGTH AT BIOPSY AND INDEX LESION SIZE AT MPMRI BEST PREDICTS THE EXTRACAPSULAR EXTENSION OF PROSTATE CANCER AT WHOLE-MOUNT SECTIONS OF RADICAL PROSTATECTOMIES Francesco Sanguedolce*, Jose Daniel Subiela Henriquez, Luisa Granados Palacio, Jhonatan Hernandez Mancera, Maria Jose Martinez Barcina, Jose Calderon Cortez, Territo Angelo, Palou Redorta Joan, and Breda Alberto Francesco Sanguedolce*Francesco Sanguedolce* More articles by this author , Jose Daniel Subiela HenriquezJose Daniel Subiela Henriquez More articles by this author , Luisa Granados PalacioLuisa Granados Palacio More articles by this author , Jhonatan Hernandez ManceraJhonatan Hernandez Mancera More articles by this author , Maria Jose Martinez BarcinaMaria Jose Martinez Barcina More articles by this author , Jose Calderon CortezJose Calderon Cortez More articles by this author , Territo AngeloTerrito Angelo More articles by this author , Palou Redorta JoanPalou Redorta Joan More articles by this author , and Breda AlbertoBreda Alberto More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000000967.03AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: The accuracy of mpMRI in predicting extracapsular extension (ECE) of prostate cancer (PCa) is limited. The PIRADS scoring system includes the 15 mm index lesion (IL) size as a cut-off to distinguish between scores 4 and 5, and it was introduced for its relationship to a higher risk of extracapsular extension (ECE). We have analysed clinical and radiological parameters to select and integrate the most relevant features in a new nomogram for the prediction of ECE. METHODS: From 01/2013 to 12/2017, 128 patients had an mpMRI (T2W, DWI and DCE) before undertaking a radical prostatectomy (RP) at our institution. Clinical parameters included PSA, PSA density (PSAd), clinical stage (cT), ISUP grade group (Gg) and maximum length of cancer (MLC) at TRUS biopsy; variables collected at mpMRI involved index lesion size (IL), length of capsular contact (LCC),PIRADS v2 score, overall prostate LIKERT score, ESUR ECE score and LIKERT ECE score. Reference standard was the histology features at whole-mount specimen sections. Two experienced radiologists retrospectively reviewed the imaging studies blinded to the final histology. Variables resulting associated to ECE at univariate analysis were dichotomised as appropriate by identifying cut-off values at ROC curve (continuous variables) and Kundel test (categorical/nominal variables). Multivariate logistic regression was performed with the step-wise method; the statistically significant variables associated to ECE were included in a nomogram calibrated with the Hosmer-Lomeshow and R2 test. Inter-observer variabilities between the mpMRI readings of the two radiologists were assessed with the Intraclass Correlation Coefficient (ICC). RESULTS: Variables introduced in the multivariate model resulted to be the cT (<T2≥), Gg (<7≥), MLC (<5.5≥ mm), IL (<11≥ mm), PSAd (<0.26≥), PIRADS (≤4>), ESUR (≤2>), LIKERT (≤4>). The variables which finally were entered in the nomogram included the cT, MLC and IL. The probability for ECE with the combination of the three variables was 81.8%, the AUC of the model in a ROC analysis was 0.84 [95%CI(0.75-0.91)], p<0.001, and the calibration analysis resulted in a Hosmer-Lemeshow test p=0.985 and a R2=56.52%. ICC were good for PIRADS, ESUR and overall/ECE LIKERT (0.752, 0.810, 0.834, 0.857, respectively), and substantial for IL size (0.916). CONCLUSIONS: The combination of clinical and mpMRI features best predicts ECE at radical prostatectomy. The 15 mm cut-off distinguishing PIRADS score 4 to 5 should be lowered Source of Funding: none © 2020 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 203Issue Supplement 4April 2020Page: e1194-e1194 Advertisement Copyright & Permissions© 2020 by American Urological Association Education and Research, Inc.MetricsAuthor Information Francesco Sanguedolce* More articles by this author Jose Daniel Subiela Henriquez More articles by this author Luisa Granados Palacio More articles by this author Jhonatan Hernandez Mancera More articles by this author Maria Jose Martinez Barcina More articles by this author Jose Calderon Cortez More articles by this author Territo Angelo More articles by this author Palou Redorta Joan More articles by this author Breda Alberto More articles by this author Expand All Advertisement PDF downloadLoading ...

A multivariate logistic regression model based on 3T mpMRI, clinical, and biopsy parameters for the prediction of prostate cancer extracapsular extension.

27 Background: Extracapsular extension (ECE) of prostate cancer (PCa) is a poor prognostic factor associated with progression, recurrence after treatment and increased PCa- related mortality. Accurate staging prior to radical prostatectomy is crucial in avoidance of positive margins and when planning nerve-sparing procedures. This study investigated the predictive value of clinical, biopsy &amp; 3TmpMRI parameters using a multivariate logistic model for per-lesion detection of PCa ECE with wholemount histopathology (WMHP) as reference. Methods: This IRB approved, HIPAA compliant study included 575 patients with 774 true positive PCa lesions, who underwent radical prostatectomy between 7/2010-2/2019. The relationship between pathologic ECE &amp; parameters including clinical; age, prostate specific antigen (PSA) &amp; PSA density (PSAD), biopsy; percentage of positive systematic cores &amp; Gleason score (GS) &amp; 3TmpMRI; prostate volume, number of lesions per patient, size, location, level, PIRADSv2 score, laterality, apparent diffusion coefficient (ADC) value &amp; risk of ECE on MRI was evaluated using bivariate and multivariate analysis. The accuracy of the final model was evaluated using ROC analysis. Results: 27.8% (215/774), 42.9% (332/774) &amp; 29.3% (227/774) of the lesions were PIRADSv2 score 3, 4 &amp; 5 &amp; 59.9% (464/774), 24.7% (191/774) &amp; 17.7% (137/774) were low, intermediate &amp; high risk for ECE, respectively. 23.6% (183/774) of the lesions had ECE on WMHP. On bivariate analysis higher PSA, PSAD, percentage of positive biopsy cores, biopsy GS, size, PIRADSv2 score, ADC value, risk of ECE on MRI, location (posterior), level(midgland &amp; base), bilaterality &amp; lower number of lesions per patient were significant for ECE prediction. The multivariate logistic model included age, PSAD, number of lesions per patient, size, location, level, PIRADSv2 score &amp; risk of ECE on MRI. The AUC for the prediction of ECE for this model was 0.85. Conclusions: This multivariate regression model based on clinical, biopsy &amp; 3TmpMRI parameters have a high predictive value for pathology ECE detection.

Value of adding the apparent diffusion coefficient to capsular contact for the prediction of extracapsular extension in prostate cancer.

ObjectiveTo determine whether evaluating the mean apparent diffusion coefficient (ADC) together with capsular contact (CC) adds value in the prediction of microscopic extracapsular extension (ECE) of prostate cancer.Materials and MethodsBetween January 2012 and December 2016, 383 patients underwent multiparametric magnetic resonance imaging (mpMRI) of the prostate. A total of 67 patients were selected for inclusion. Two radiologists (observers 1 and 2), working independently, performed qualitative and quantitative analyses of ECE, macroscopic ECE, and microscopic ECE. A third radiologist assessed the correlation with the clinical data, and two experienced pathologists reviewed all histopathological findings.ResultsAmong the 67 patients, mpMRI showed lesions that were confined to the capsule in 44 (66.7%), had microscopic ECE in 12 (17.9%), and had macroscopic ECE in 11 (16.4%). There were no significant differences, in terms of the diagnostic accuracy, as measured by determining the area under the curve (AUC), of CC on T2-weighted images (CCT2), CC on diffusion-weighted imaging (CCDWI), and the mean ADC for the prediction of microscopic ECE, between observer 1 (AUC of 0.728, 0.691, and 0.675, respectively) and observer 2 (AUC of 0.782, 0.821, and 0.799, respectively). Combining the mean ADC with the CCT2 or CCDWI did not improve the diagnostic accuracy for either observer. There was substantial interobserver agreement for the qualitative evaluation of ECE, as demonstrated by the kappa statistic, which was 0.77 (0.66-0.87). The diagnostic accuracy (AUC) of the qualitative assessment for predicting microscopic ECE was 0.745 for observer 1 and 0.804 for observer 2, and the difference was less than significant. In a multivariate analysis, none of clinical or imaging parameters were found to be associated with ECE.ConclusionFor the detection of microscopic ECE on mpMRI, CC appears to have good diagnostic accuracy, especially if the observer has considerable experience. Adding the mean ADC to the CCT2 or CCDWI does not seem to provide any significant improvement in that diagnostic accuracy.

Predicting side-specific prostate cancer extracapsular extension: a simple decision rule of PSA, biopsy, and MRI parameters

ObjectiveTo develop an easy-to-use side-specific tool for the prediction of prostate cancer extracapsular extension (ECE) using clinical, biopsy, and MRI parameters.Materials and methodsRetrospective analysis of patients who underwent radical prostatectomy preceded by staging multiparametric MRI of the prostate was performed. Multivariate logistic regression analysis was used to choose independent predictors of ECE. Continuous variables were transformed to categorical ones by choosing threshold values using spline knots or testing thresholds used in previously described models. Internal validation of the rule was carried out as well as validation of other algorithms on our group was performed.ResultsIn the analyzed period of time, 88 out of 164 patients who underwent radical prostatectomy met inclusion criteria. ECE was evidenced at radical prostatectomy in 41 patients (46.6%) and in 53 lobes (30.1%). In the multivariate analysis PSA, total percentage of cancerous tissue in cores (%PCa) and maximum tumour diameter (MTD) of Likert 3–5 lesions on MRI were independent predictors of ECE. The following rule for predicting side-specific ECE was proposed: %PCa ≥ 15% OR MTD ≥ 15 mm OR PSA ≥ 20 ng/mL. Internal validation of the algorithm revealed safe lower confidence limits for sensitivity and NPV, proving that model offers accurate risk grouping that can be safely used in decision-making.ConclusionThe rule developed in this study makes ECE prediction fast, intuitive, and side-specific. However, until validated externally it should be used with caution.