Extracapsular extension risk assessment using an artificial intelligence prostate cancer mapping algorithm

We compared the results of transrectal sonography and endorectal MR imaging in the local staging of prostatic carcinoma. 56 patients (mean age, 61.1 +/- 7.3 years) with the diagnosis of prostate cancer who by transrectal sonography had no evidence of gross extracapsular extension underwent endorectal coil MR imaging prior to radical prostatectomy. Imaging findings prospectively evaluated in each patient were cancer laterality, extracapsular extension, and seminal vesicle invasion. Twenty-one of 56 (38%) patients had extracapsular extension on final pathology. A total of 100 sides and five seminal vesicles were involved with cancer, and 27 sides (21 patients, six with bilateral extracapsular extension) demonstrated extracapsular extension. Imaging results were correlated with step-sectioned, radical prostatectomy pathologic data, and statistical analysis was expressed at a p = .05 level of significance. Retrospective readings of the images were used to construct receiver operating characteristic curves for the detection of extracapsular extension. For tumor laterality, transrectal sonography was compared with endorectal coil MR imaging for sensitivity (70% versus 97%; p < .001), specificity (58% versus 58%), positive predictive value (93% versus 95%) and negative predictive value (18% versus 70%). For extracapsular extension, transrectal sonography was compared with endorectal coil MR imaging for the entire prostate and individually for each side of the prostate. The respective results for sensitivity (48% versus 91%, p < .01 and 37% versus 78%, p < .005), specificity (71% versus 49% and 87% versus 73%), positive predictive value (50% versus 51% and 48% versus 48%), and negative predictive value (69% versus 90% and 81% versus 91%). The receiver operating characteristic analysis of retrospective data demonstrated endorectal coil MR imaging to be superior to transrectal sonography in the detection of extracapsular extension. The small number of seminal vesicles involved by cancer (n = 5) precluded meaningful comparisons between the imaging techniques. Endorectal coil MR imaging is more sensitive but less specific than transrectal sonography for detecting extracapsular extension of carcinoma of the prostate. Both procedures have low positive predictive values yet similarly high negative predictive values when each side of the prostate is assessed independently for extracapsular extension.

PurposeTo retrospectively determine the prevalence and diagnostic performance of the capsular enhancement sign (CES) on multiparametric (mp) MRI for the detection of prostate cancer (PCa) extracapsular extension (ECE). MethodsThis retrospective study included patients who underwent mpMRI prior to radical prostatectomy. CES was defined as an area of asymmetrical early hyperenhancement on DCE-MRI adjacent to a peripheral zone tumour, matched or exceeded the tumour circumferential diameter, and with persistent enhancement. Two uro-radiologists evaluated the presence of CES on mpMRI, independently and in consensus, with interobserver agreement calculated using bias and prevalence-adjusted kappa (PABAK). CES performance for predicting ECE was assessed using sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). ResultsThe study included 146 patients, with 91/146 (62%) having ECE on surgical pathology. Following initial review, Reader 1 identified 12/146 (8%) CES-positive cases, while Reader 2 reported 14/146 (10%) CES-positive cases, with 15/146 (10%) lesions determined as demonstrating the CES sign on consensus reading. PABAK for CES between the two readers was high at 0.90. All consensus determined CES-positive lesions represented pathological stage ≥ T3a disease, with the overall prevalence of CES among tumours with confirmed ECE being 15/91 (17%). The sign showed high specificity (100%) and PPV (100%) for ECE detection, but with low sensitivity, NPV, and accuracy at 16.5%, 41.3%, and 47.4%, respectively. ConclusionsCES was demonstrated to be a rare but highly specific ECE predictor on mpMRI that may improve local staging in the patients in whom it is demonstrated.

Study question Do artificial intelligence (AI) models used to assess embryo viability (based on pregnancy outcomes) also correlate with known embryo quality measures such as Gardner score? Summary answer An AI for embryo viability assessment also correlated with Gardner score, further substantiating the use of AI for assessment and selection of good quality embryos. What is known already The Gardner score consists of three separate components of embryo morphology that are graded individually, then combined to give a final score describing Day 5 embryo (blastocyst) quality. Evidence suggests the Gardner score has some correlation with clinical pregnancy. We hypothesized that an AI model trained to evaluate likelihood of clinical pregnancy based on fetal heartbeat (in clinical use globally) would also correlate with components of the Gardner score itself. We also compared the ability of the AI and Gardner score to predict pregnancy outcomes. Study design, size, duration This study involved analysis of a prospectively collected dataset of single static Day 5 embryo images with associated Gardner scores and AI viability scores. The dataset comprised time-lapse images of 1,485 embryos (EmbryoScope) from 638 patients treated at a single in vitro fertilization (IVF) clinic between November 2019 and December 2020. The AI model was not trained on data from this clinic. Participants/materials, setting, methods Average patient age was 35.4 years. Embryologists manually graded each embryo using the Gardner method, then subsequently used the AI to obtain a score between 0 (predicted non-viable, unlikely to lead to a pregnancy) and 10 (predicted viable, likely to lead to a pregnancy). Correlation between the AI viability score and Gardner score was then assessed. Main results and the role of chance The average AI score was significantly correlated with the three components of the Gardner score: expansion grade, inner cell mass (ICM) grade, and trophectoderm grade. Average AI score generally increased with advancing blastocyst developmental stage. Blastocysts with expansion grades of ≥ 3 are generally considered suitable for transfer. This study showed that embryos with expansion grade 3 had lower AI scores than those with grades 4-6, consistent with a reduced pregnancy rate. AI correlation with trophectoderm grade was more significant than with ICM grade, consistent with studies demonstrating that trophectoderm grade is more important than ICM in determining clinical pregnancy likelihood. The AI predicted Gardner scores of ≥ 2BB with an accuracy of 71.7% (sensitivity 75.1%, specificity 45.9%), and an AUC of 0.68. However, when used to predict pregnancy outcome, the AI performed 27.9% better than the Gardner score (accuracies of 49.8% and 39.0% respectively). Even though the AI was highly correlated with the Gardner score, the improved efficacy for predicting pregnancy suggests that a) the AI provides an advantage in standardization of scoring over the manual and subjective Gardner method, and b) the AI is likely identifying and evaluating morphological features of embryo quality that are not captured by the Gardner method. Limitations, reasons for caution The Gardner score is not a linear score, creating challenges with setting a suitable threshold relating to the prediction of pregnancy. The 2BB treshold was chosen based on literature (Munné et al 2019) and verified by experienced embryologists. This correlative study may also require additional confirmatory studies on independent datasets. Wider implications of the findings The correlation between AI scores and known features of embryo quality (Gardner score) substantiates the use of the AI for embryo assessment. The AI score provides further insight into components of the Gardner score, and may detect morphological features related to clinical pregnancy beyond those evaluated by the Gardner method. Trial registration number Not applicable

This study aimed to examine whether preoperative Prostate Imaging Reporting and Data System v2 (PI-RADS v2) can predict pathological extracapsular extension (EPE) after radical prostatectomy. We also studied the preoperative factors which can predict EPE. In our institute, 294 patients underwent robot assisted radical prostatectomy (RARP) between December 2012 and August 2016. In this era, we performed MRI after biopsy to determine clinical stage before surgery. PI-RADS v2 scores were retrospectively reviewed using biparametric MRI and EPE in pathological mapping of resected specimens for each lobe. In the excised specimen, EPE was observed in 73 lobes (12%). The percentage of EPE by PI-RADS v2 score was score '1': 6% (17/297 lobes), '2': 3% (1/33 lobes), '3': 12% (8/67 lobes), '4': 19% (27/139 lobes), and '5': 38% (20/52 lobes). The higher the PI-RADS score, the higher the percentage of EPE (P <0.01). When classified as PI-RADS score ≥4 and <4, the positive predictive value (PPV) was 24.6% (47/191 lobes, 95%CI: 0.187 - 0.313) and negative predictive value (NPV) was 93.5% (371/397 lobes, 95%CI: 0.906 - 0.957). By multivariate analysis, positive biopsy core percentage ≥60%, and PI-RADS score ≥4 were independent factors for predicting EPE. The positive rate of EPE in lobes with zero, one and two factors (PI-RADS ≥4 and positive biopsy core percentage ≥60%) was 4%, 19%, and 38%, respectively. PPV and NPV of PI-RADS ≥4 for predicting pathologic EPE were 24.6% and 93.5%, respectively. PI-RADS ≥4 and positive biopsy core percentage ≥60% were independent risk factors for predicting EPE. The positive rate of EPE in lobes with zero, one and two factors (PI-RADS ≥4 and positive biopsy core percentage ≥60%) was 4%, 19%, and 38%, respectively.

Study question Can EMA Genetics, an AI-based genetic screening tool, confidently deselect embryos at risk of aneuploidy across diverse, unbalanced data using a validated AI score threshold? Summary answer The model identified high-risk aneuploid embryos (AI score ≤ 28) with 85.2% NPV, increasing to 88% for ages &amp;gt;40, consistent across real-world and validation datasets. What is known already Embryo selection is critical for optimizing IVF outcomes. Preimplantation genetic testing for aneuploidy (PGT-A) identifies euploid embryos but is invasive, costly, and incompatible with fresh transfer protocols. EMA Genetics offers a non-invasive screening method using time-lapse imaging (TLI) and AI to estimate aneuploidy risk prior to confirmatory testing and/or transfer. Previous validation on balanced datasets demonstrated its ability to deselect embryos at risk of aneuploidy with a score threshold ≤ 28, achieving high negative predictive value (NPV). However, real-world data often involve unbalanced patient cohorts, necessitating further validation to confirm the model’s robustness across diverse clinical settings and patient populations. Study design, size, duration The study utilized an independently collected multicenter dataset of 1,920 biopsied blastocysts from four clinics across four countries. Data included oocyte age, PGT-A-confirmed aneuploidy status, and TLI videos. An AI score (1–99) was assigned to each embryo. The score increases linearly with likelihood of euploidy. The deselection threshold (AI score ≤ 28) was evaluated for reliability by comparing its negative predictive value (NPV) with results from the balanced validation dataset (N = 700 embryos). Participants/materials, setting, methods The final dataset included 1,049 aneuploid (56.4%) and 808 euploid (43.6%) embryos, with maternal age and aneuploidy rates matching reported clinical distributions. AI scores were compared to known PGT-A labels (aneuploid/euploid). Classification performance metrics were assessed in both unbalanced real-world and balanced validation datasets, and the NPV at the validated deselection score threshold was compared across datasets. Main results and the role of chance The AI model identified embryos with AI scores ≤ 28 as high-risk aneuploid with a 85.2% negative predictive value (NPV), confirmed by PGT-A in the independently collected dataset. Performance improved with maternal age, with NPV reaching 88% for patients aged 40–42. The deselection threshold of ≤ 28 remained consistent with the threshold identified in the balanced validation dataset (84.8%), demonstrating consistency across diverse patient cohorts.Logistic regression (OR) analysis for evaluating the association between AI scores and euploidy likelihood in the unbalanced real-world and balanced validation datasets: 2.19 [95% CI: 1.749– 2.733] and 2.79 [95% CI = 2.05-3.82], respectively. Limitations, reasons for caution Prospective validation in larger, more diverse cohorts is needed. Additionally, potential variability in clinical protocols among participating centers may influence results. Caution is warranted when extrapolating these findings to clinical populations outside the studied demographic. Wider implications of the findings This AI-driven tool has the potential to complement existing diagnostic methods, improve embryo selection strategies, and optimize IVF resource allocation, particularly for patients with advanced maternal age or limited embryos available for transfer. Trial registration number No

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.

The Role of Magnetic Resonance Image Guided Prostate Biopsy in Stratifying Men for Risk of Extracapsular Extension at Radical Prostatectomy

The role of magnetic resonance image guided prostate biopsy in stratifying men for risk of extracapsular extension at radical prostatectomy. Raskolnikov D, George AK, Rais-Bahrami S, Turkbey B, Siddiqui MM, Shakir NA, Okoro C, Rothwax JT, Walton-Diaz A, Sankineni S, Su D, Stamatakis L, Merino MJ, Choyke PL, Wood BJ, Pinto PA. Urologic Oncology Branch, National Cancer Institute, National Institutes

To determine retrospectively the role of endorectal magnetic resonance in the staging of prostate cancer. The aim of the study was to assess whether it is possible to identify a group of patients with prostate cancer, chosen for certain prognostic factors, eligible for radiotherapy that could take advantage of endorectal magnetic resonance in staging and therapy management. Between January 2002 and December 2005, 143 patients with biopsy proven prostate cancer underwent endorectal magnetic resonance. All patients were initially evaluated considering the following prognostic factors: serum prostate-specific antigen at diagnosis, Gleason score, histological grade, involvement of the seminal vesicle and extracapsular extension using the Roach III and ECE equations. The findings were then compared to the results of endorectal magnetic resonance. The relationship between the variable post-endorectal magnetic resonance stage modification and Gleason score was statistically significant (P = 0.02847). In addition, our study showed a statistically significant correlation between the risk of seminal vesicle involvement according to the Roach III formula and post-endorectal magnetic resonance stage modification (P = 0.01305). Conversely, statistical analysis showed no significant correlation between post-endorectal magnetic resonance stage modification and prostate-specific antigen values (P = 0.83440) or between post-endorectal magnetic resonance stage modification and the risk of extracapsular extension according to the extracapsular extension formula (P = 0.42748). Our data suggest that endorectal magnetic resonance could be used for staging of the subgroup of patients at high risk of seminal vesicle involvement (> 15%). Although we found a statistical correlation between Gleason score and post-endorectal magnetic resonance stage modification, statistical analysis showed no correlation between any of the subgroups. Therefore, it is not possible at the moment to identify a subgroup of patients by Gleason score that may benefit from endorectal magnetic resonance. In our opinion, extracapsular extension values were not useful to select patients for endorectal magnetic resonance.

To determine retrospectively the role of endorectal magnetic resonance in the staging of prostate cancer. The aim of the study was to assess whether it is possible to identify a group of patients with prostate cancer, chosen for certain prognostic factors, eligible for radiotherapy that could take advantage of endorectal magnetic resonance in staging and therapy management. Between January 2002 and December 2005, 143 patients with biopsy proven prostate cancer underwent endorectal magnetic resonance. All patients were initially evaluated considering the following prognostic factors: serum prostate-specific antigen at diagnosis, Gleason score, histological grade, involvement of the seminal vesicle and extracapsular extension using the Roach III and ECE equations. The findings were then compared to the results of endorectal magnetic resonance. The relationship between the variable post-endorectal magnetic resonance stage modification and Gleason score was statistically significant (P = 0.02847). In addition, our study showed a statistically significant correlation between the risk of seminal vesicle involvement according to the Roach III formula and post-endorectal magnetic resonance stage modification (P = 0.01305). Conversely, statistical analysis showed no significant correlation between post-endorectal magnetic resonance stage modification and prostate-specific antigen values (P = 0.83440) or between post-endorectal magnetic resonance stage modification and the risk of extracapsular extension according to the extracapsular extension formula (P = 0.42748). Our data suggest that endorectal magnetic resonance could be used for staging of the subgroup of patients at high risk of seminal vesicle involvement (> 15%). Although we found a statistical correlation between Gleason score and post-endorectal magnetic resonance stage modification, statistical analysis showed no correlation between any of the subgroups. Therefore, it is not possible at the moment to identify a subgroup of patients by Gleason score that may benefit from endorectal magnetic resonance. In our opinion, extracapsular extension values were not useful to select patients for endorectal magnetic resonance.

ObjectivesTo evaluate the diagnostic reliability of a web-based Artificial Intelligence program on the detection and classification of dental structures and treatments present on panoramic radiographs. MethodsA total of 300 orthopantomographies (OPG) were randomly selected for this study. First, the images were visually evaluated by two calibrated operators with radiodiagnosis experience that, after consensus, established the “ground truth”. Operators’ findings on the radiographs were collected and classified as follows: metal restorations (MR), resin-based restorations (RR), endodontic treatment (ET), Crowns (C) and Implants (I). The orthopantomographies were then anonymously uploaded and automatically analyzed by the web-based software (Denti.Ai). Results were then stored, and a statistical analysis was performed by comparing them with the ground truth in terms of Sensitivity (S), Specificity (E), Positive Predictive Value (PPV) Negative Predictive Value (NPV) and its later representation in the area under (AUC) the Receiver Operating Characteristic (ROC) Curve. ResultsDiagnostic metrics obtained for each study variable were as follows: (MR) S=85.48%, E=87.50%, PPV=82.8%, NPV=42.51%, AUC=0.869; (PR) S=41.11%, E=93.30%, PPV=90.24%, NPV=87.50%, AUC=0.672; (ET) S=91.9%, E=100%, PPV=100%, NPV=94.62%, AUC=0.960; (C) S=89.53%, E=95.79%, PPV=89.53%, NPV=95.79%, AUC=0.927; (I) S, E, PPV, NPV=100%, AUC=1.000. ConclusionsFindings suggest that the web-based Artificial intelligence software provides a good performance on the detection of implants, crowns, metal fillings and endodontic treatments, not being so accurate on the classification of dental structures or resin-based restorations. Clinical SignificanceGeneral diagnostic and treatment decisions using orthopantomographies can be improved by using web-based artificial intelligence tools, avoiding subjectivity and lapses from the clinician.

Validation of artificial intelligence contrast mammography in diagnosis of breast cancer: Relationship to histopathological results

The objective of this study was to perform an independent external validation of the Giganti-Coppola nomogram (GCN), which uses clinical and radiological parameters to predict prostate extracapsular extension (ECE) on the final pathology of patients undergoing radical prostatectomy (RP). Seventy-two patients diagnosed with prostate cancer (PCa), who were RP candidates from two institutions, were prospectively included. All patients underwent preoperative multi-parametric magnetic resonance imaging (mpMRI) at 1.5T, without the use of an endorectal coil, with multiplanar images in T1WI, T2WI, DWI, and DCE. The AUC and a calibration graph were used to validate the nomogram, using the regression coefficients of the Giganti-Coppola study. The original nomogram had an AUC of 0.90 (p = 0.001), with a sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of 100%, 5.1%, 47.1%, 100%, and 48%, respectively. The calibration graph showed an overestimation of the nomogram for ECE. The GCN has an adequate ability in predicting ECE; however, in our sample, it showed limited accuracy and overestimated likelihood of ECE in the final pathology of patients with PCa submitted to RP. • Knowledge of preoperative local staging of prostate cancer is essential for surgical treatment. Extracapsular extension increases the chance of positive surgical margins. • Imaging modalities such as mpMRI alone does not have suitable accuracy in local staging. • Giganti-Coppola's nomogram achieved an adequate ability in predicting ECE.

68Ga-PSMA PET/CT Imaging Predicting Intraprostatic Tumor Extent, Extracapsular Extension and Seminal Vesicle Invasion Prior to Radical Prostatectomy in Patients with Prostate Cancer.

Predicting Likelihood of Having Four or More Positive Nodes in Patient With Sentinel Lymph Node-Positive Breast Cancer: A Nomogram Validation Study