Artificial intelligence and radiologists in prostate cancer detection on MRI (PI-CAI): an international, paired, non-inferiority, confirmatory study.

BACKGROUND: Artificial intelligence (AI) systems can potentially aid the diagnostic pathway of prostate cancer by alleviating the increasing workload, preventing overdiagnosis, and reducing the dependence on experienced radiologists. We aimed to investigate the performance of AI systems at detecting clinically significant prostate cancer on MRI in comparison with radiologists using the Prostate Imaging-Reporting and Data System version 2.1 (PI-RADS 2.1) and the standard of care in multidisciplinary routine practice at scale. METHODS: In this international, paired, non-inferiority, confirmatory study, we trained and externally validated an AI system (developed within an international consortium) for detecting Gleason grade group 2 or greater cancers using a retrospective cohort of 10 207 MRI examinations from 9129 patients. Of these examinations, 9207 cases from three centres (11 sites) based in the Netherlands were used for training and tuning, and 1000 cases from four centres (12 sites) based in the Netherlands and Norway were used for testing. In parallel, we facilitated a multireader, multicase observer study with 62 radiologists (45 centres in 20 countries; median 7 [IQR 5-10] years of experience in reading prostate MRI) using PI-RADS (2.1) on 400 paired MRI examinations from the testing cohort. Primary endpoints were the sensitivity, specificity, and the area under the receiver operating characteristic curve (AUROC) of the AI system in comparison with that of all readers using PI-RADS (2.1) and in comparison with that of the historical radiology readings made during multidisciplinary routine practice (ie, the standard of care with the aid of patient history and peer consultation). Histopathology and at least 3 years (median 5 [IQR 4-6] years) of follow-up were used to establish the reference standard. The statistical analysis plan was prespecified with a primary hypothesis of non-inferiority (considering a margin of 0·05) and a secondary hypothesis of superiority towards the AI system, if non-inferiority was confirmed. This study was registered at ClinicalTrials.gov, NCT05489341. FINDINGS: Of the 10 207 examinations included from Jan 1, 2012, through Dec 31, 2021, 2440 cases had histologically confirmed Gleason grade group 2 or greater prostate cancer. In the subset of 400 testing cases in which the AI system was compared with the radiologists participating in the reader study, the AI system showed a statistically superior and non-inferior AUROC of 0·91 (95% CI 0·87-0·94; p<0·0001), in comparison to the pool of 62 radiologists with an AUROC of 0·86 (0·83-0·89), with a lower boundary of the two-sided 95% Wald CI for the difference in AUROC of 0·02. At the mean PI-RADS 3 or greater operating point of all readers, the AI system detected 6·8% more cases with Gleason grade group 2 or greater cancers at the same specificity (57·7%, 95% CI 51·6-63·3), or 50·4% fewer false-positive results and 20·0% fewer cases with Gleason grade group 1 cancers at the same sensitivity (89·4%, 95% CI 85·3-92·9). In all 1000 testing cases where the AI system was compared with the radiology readings made during multidisciplinary practice, non-inferiority was not confirmed, as the AI system showed lower specificity (68·9% [95% CI 65·3-72·4] vs 69·0% [65·5-72·5]) at the same sensitivity (96·1%, 94·0-98·2) as the PI-RADS 3 or greater operating point. The lower boundary of the two-sided 95% Wald CI for the difference in specificity (-0·04) was greater than the non-inferiority margin (-0·05) and a p value below the significance threshold was reached (p<0·001). INTERPRETATION: An AI system was superior to radiologists using PI-RADS (2.1), on average, at detecting clinically significant prostate cancer and comparable to the standard of care. Such a system shows the potential to be a supportive tool within a primary diagnostic setting, with several associated benefits for patients and radiologists. Prospective validation is needed to test clinical applicability of this system. FUNDING: Health~Holland and EU Horizon 2020.

Robot-assisted vs open retropubic radical prostatectomy: a propensity score-matched comparative analysis based on 15 years and 18,805 patients.

PURPOSE: To compare oncological, functional, and surgical outcomes of a large cohort of patients who underwent open retropubic radical prostatectomy (ORP) or robot-assisted radical prostatectomy (RARP). MATERIALS AND METHODS: Data from 18,805 RPs performed with either the open or the robot-assisted approaches at a single tertiary referral center between 2008 and 2022 were analyzed. The impact of surgical approach on biochemical recurrence-free survival, salvage radiotherapy-free survival, and metastasis-free survival was analyzed by log-rank test and Kaplan-Meier analysis in a propensity score (PS)-based matched cohort. Intraoperative and postoperative surgical outcomes were assessed. One-week, 3-month, and 12-month continence rates and 12-month erectile function (EF) were analyzed. RESULTS: No statistically significant differences in oncological outcomes were found between ORP and RARP. A slight statistically significant difference in favor of RARP was noted in urinary continence at 3 months (RARP vs. ORP: 81% vs. 77%, p = 0.007) and 12 months (91% vs. 89.3%, p = 0.008), respectively. The rate of EF was statistically significantly higher (60%) after RARP than after ORP (45%, p < 0.001). CONCLUSION: Both RARP and ORP yielded similar oncological outcomes. RARP offered a slight advantage in terms of continence recovery, but its clinical significance may be less meaningful. RARP resulted in significantly improved postoperative EF, suggesting a potential influence of both surgical experience and minimally invasive approach.

PI-QUAL version 2: an update of a standardised scoring system for the assessment of image quality of prostate MRI.

Multiparametric MRI is the optimal primary investigation when prostate cancer is suspected, and its ability to rule in and rule out clinically significant disease relies on high-quality anatomical and functional images. Avenues for achieving consistent high-quality acquisitions include meticulous patient preparation, scanner setup, optimised pulse sequences, personnel training, and artificial intelligence systems. The impact of these interventions on the final images needs to be quantified. The prostate imaging quality (PI-QUAL) scoring system was the first standardised quantification method that demonstrated the potential for clinical benefit by relating image quality to cancer detection ability by MRI. We present the updated version of PI-QUAL (PI-QUAL v2) which applies to prostate MRI performed with or without intravenous contrast medium using a simplified 3-point scale focused on critical technical and qualitative image parameters. CLINICAL RELEVANCE STATEMENT: High image quality is crucial for prostate MRI, and the updated version of the PI-QUAL score (PI-QUAL v2) aims to address the limitations of version 1. It is now applicable to both multiparametric MRI and MRI without intravenous contrast medium. KEY POINTS: High-quality images are essential for prostate cancer diagnosis and management using MRI. PI-QUAL v2 simplifies image assessment and expands its applicability to prostate MRI without contrast medium. PI-QUAL v2 focuses on critical technical and qualitative image parameters and emphasises T2-WI and DWI.

A systematic review of cytoreductive prostatectomy outcomes and complications in oligometastatic disease.

Objective: To analyze outcomes and complications of cytoreductive prostatectomy (CRP) for oligometastatic prostate cancer (PCa) in order to elucidate its role in this space. Methods: We performed a systematic literature search using three databases (Medline, Scopus, and Web of Science). The primary endpoints were oncologic outcomes. The secondary endpoints were complication rates and functional results. Results: In all studies, overall survival was better or at least comparable variable in the groups with CRP compared to no local treatment. The greatest benefit from CRP in 5-year overall survival in one study was 67.4% for CRP versus 22.5% for no local treatment. Cancer-specific survival (CSS) showed the same trend. Several authors found significant benefits from CSS in the CRP group: from 79% vs. 46% to 100% vs. 61%. CRP was a predictor of better CSS (hazard ratio 0.264, p=0.004). Positive surgical margin rates differed widely from 28.6% to 100.0%. Urinary continence in CRP versus RP for localized PCa was significantly lower (57.4% vs. 90.8%, p<0.0001). Severe incontinence occurred seldom (2.5%-18.6%). Total complication rates after CRP differed widely, from 7.0% to 43.6%. Rates of grades 1 and 2 events prevailed. Patients on ADT alone also showed a considerable number of complications varying from 5.9% to 57.7%. Conclusion: CRP improves medium-term cancer control in patients with oligometastatic PCa. The morbidity and complication rates of this surgery are comparable with other approaches, but postoperative incontinence rate is higher compared with RP for localized disease.

Nerve-sparing radical prostatectomy using the neurovascular structure-adjacent frozen-section examination (NeuroSAFE): results after 20 years of experience.

OBJECTIVES: To evaluate the long-term oncological outcomes and functional results of the neurovascular structure-adjacent frozen-section examination (NeuroSAFE) during nerve-sparing (NS) radical prostatectomy (RP). MATERIALS AND METHODS: A 10-yr survival analysis on 11069 RPs performed with or without the NeuroSAFE, between January 2002 to June 2011 was carried out. In the NeuroSAFE cohort, the neurovascular structure-adjacent prostatic margins are removed and stained for cryo-sectioning during RP. In case of a PSM, partial or full removal of the neurovascular bundle was performed. The impact of NeuroSAFE on biochemical recurrence-free survival (BFS), salvage radiation therapy-free survival, metastasis-free survival, and prostate cancer-specific survival at 10 years was analyzed. 1-year (1-yr) erectile function (EF), 1-yr, and 2-yr continence rates were assessed in propensity score-based matched cohorts. RESULTS: Median follow-up was 121 (IQR: 73, 156) months. No differences in BFS between NeuroSAFE and non-NeuroSAFE were recorded (10-yr BFS: NeuroSAFE vs non-Neurosafe, pT2: 81% vs 84%, p = 0.06; pT3a: 58% vs. 63%, p = 0.6; ≥pT3b: 22% vs. 27%, p = 0.99). No differences were found between the two groups in terms of sRFS (pT2: p = 0.1; pT3a: p = 0.4; ≥pT3b: p = 0.4) (Fig. 1B, Table 2), and MTS (pT2: p = 0.3; pT3a: p = 0.6; ≥pT3b: p = 0.9). The NeuroSAFE-navigated patients reported a better 1-yr EF than non-NeuroSAFE (68% vs. 58%, p = 0.02) and no differences in 1-yr and 2-yr continence rates (92.4% vs. 91.8%, and 93.4% vs. 93%, respectively). The main limitation is the retrospective study design. CONCLUSIONS: While the NeuroSAFE approach did not show significant improvements in long-term oncologic or continence outcomes, it did provide an opportunity for a higher proportion of patients to improve postoperative functional results, possibly through increased nerve-sparing procedures.

Future of focal therapy for the treatment of prostate cancereuropean section of urotechnology (esut) position / Futuro de la terapia focal para el tratamieto del cáncer de próstata- posición de la sección de urotecnología (ESUT)

Introduction: Focal therapy (FT) is a treatment option for prostate cancer (PCa), which offers the possibility of an effective therapy in selected patients who have the localized disease, with a significant reduction in treatment related morbidity. Based on the current status of FT, our objective was to determine the most appropriate strategy to improve patient management Materials and methods: A literature review was done performed through the PubMed database and focused on the following topics: localised prostate cancer, MRI, prostate biopsies, ablative therapy and focal therapy. Results: Indications for FT were mainly patients with a localised PCa, a single lesion at Gleason score 7 (3+4) (Grade group 2) favourable in size. Precise identification of the tumour, currently based on multiparametric MRI data and targeted biopsy, was the cornerstone of FT success. New imaging modalities such as PET/MRI and multiparametric ultrasound have proven to be effective in detecting and targeting the tumour. Several energy sources were reported for an effective tissue ablation. Non-thermal option should be investigated to further limit the risk of side effects with the same cancer control. Conclusion: Focal therapy is a new option in the armamentarium of PCa. Technological improvements and the development of novel energy sources should make it possible to treat lesions with even greater precision, while limiting the risk of side effects. In the future, we should probably be able to effectively expand the indications of this technique to include more aggressive tumours

Introducción: La terapia focal (TF) es una opción terapéutica del cáncer de próstata (CaP), que ofrece la posibilidad de un tratamiento efectivo en pacientes seleccionados que tienen enfermedad localizada, con una reducción significativa de la morbilidad relacionada con el tratamiento. Nuestro objetivo es determinar la estrategia más apropiada para mejorar el manejo del paciente en base al estado actual de la terapia focal. Material y métodos: Realizamos una revisión de la literatura por medio de la base de datos PubMed centrada en los siguientes temas: cáncer de próstata localizado, RMN, biopsias de próstata, tratamiento ablativo y terapia focal. Resultados: Las indicaciones de TF eran principalmente pacientes con CaP localizado, lesión única Gleason 7 (3+4) (Grado Grupo 2) con tamaño favorable. La identificación precisa del tumor, actualmente basada en datos de RMN multiparamétrica y biopsia dirigida, es la piedra angular del éxito de la TF. Las nuevas modalidades de técnicas de imagen tales como PET/RMN y ecografía con contraste han demostrado ser eficaces en la detección y abordaje del tumor. Se han comunicado varias fuentes de energía para una ablación eficaz del tumor. La opción no térmica debería investigarse para limitar más aún el riesgo de efectos colaterales con el mismo control del cáncer. Conclusiones: La terapia focal es una nueva opción en el armamentario para el CaP. Las mejoras tecnológicas y el desarrollo de nuevas fuentes de energía deberían hacer posible el tratamiento de las lesiones con mayor precisión incluso, limitando a la vez el riesgo de efectos colaterales. En el futuro, deberíamos ser capaces probablemente de expandir efectivamente las indicaciones de esta técnica para incluir tumores más agresivos