Music cognition transforms auditory signals into perceptual experiences through complex brain processing, yet neuroimaging studies have underrepresented mid-level features like timbre and tonality. This work introduces a parametric General Linear Model (GLM) framework integrating Mel- Frequency Cepstral Coefficients (MFCCs) and Chroma features—established Music Information Retrieval (MIR) tools for spectral envelope and tonal content— directly into fMRI analysis. Analyzing datasets evaluating perception vs. imagery in trained musicians, we reveal: (1) a motor-executive network dominant in imagery, with Chroma driving subcortical sequencing hubs; (2) functional dissociation in auditory cortex, with primary regions exclusive to perception and higher- order areas persistent in imagery; and (3) feature- specific codes during perception, linking MFCC to spectral analysis and Chroma to tonal prediction, with overlapping auditory hubs but distinct spatial extents. This MIR-neuroimaging fusion demonstrates state- dependent neural dynamics, enabling precise decomposition of auditory processing hierarchies and advancing models for music-based neurotherapeutics and brain-computer interfaces.

INTRODUCTION:The US supply disruption of surgical irrigation fluids in September 2024 prompted the need for fluid conservation and potential deferral of urology procedures. We characterized fluid use in common endoscopic procedures to articulate recommendations for irrigation fluid stewardship and case prioritization during fluid shortages. METHODS:We reviewed case volumes and irrigation fluid use for endoscopic urological procedures at our institution during January-September 2024. We convened a panel of high-volume urologists and used a 3-step modified Delphi method to determine consensus recommendations for fluid stewardship and case prioritization. RESULTS:Among 6155 cases, the procedures consuming the highest mean per-case fluid volumes were prostate enucleation (26.6 L), transurethral resection of the prostate (16.7 L), percutaneous nephrolithotomy (12.4 L), and robotic water-jet prostate ablation (10.9 L). These 4 procedures comprised 17% of all cases but consumed 42% of total fluid volume. To prioritize procedures for potential deferral, procedures were stratified into 3 fluid tiers based on fluid consumption and 3 urgency tiers based on clinical indication. Combining both fluid and urgency tiers, we identified 5 procedural priority levels in which lower priority cases that consume more fluid and treat less urgent indications are deferred first. Finally, we defined 4 fluid stewardship principles addressing patient and trainee needs. CONCLUSIONS:Among endoscopic urology cases, the 4 most fluid-intensive procedures consume 42% of surgical irrigation fluid. A case prioritization framework that accounts for fluid consumption and clinical urgency can help urology practices navigate potential case deferrals. Fluid stewardship principles may optimize fluid conservation to minimize adverse impact on patients and trainees.

In this third installment of our GenAI workshop series at DIS, we focus on 'stopsigns'-the blockages that impede progress in design research with GenAI. These stopsigns manifest as both semantic barriers (political, social, or mental frameworks) and pragmatic hurdles (technical limitations or implementation challenges) that persist despite the rapid advancements since the GenAI boom. Such stopsigns present a productive tension-they often contain partial truths worthy of consideration while simultaneously being shortsighted in ways that prevent progression. From blanket rejection to uncritical acceptance, these barriers affect how meaningfully we engage with GenAI's potential. Our workshop welcomes both returning and first-time participants to share their experiences with these persistent challenges and work together to develop practical solutions. Through analysis of real cases and hands-on activities,

This essay examines how Generative AI (GenAI) is rapidly transforming design practices and how discourse often falls into over-simplified narratives that impede meaningful research and practical progress. We identify and deconstruct five prevalent "semantic stopsigns" – reductive framings about GenAI in design that halt deeper inquiry and limit productive engagement. Reflecting upon two expert workshops at ACM conferences and semi-structured interviews with design practitioners, we analyze how these stopsigns manifest in research and practice. Our analysis develops mid-level knowledge that bridges theoretical discourse and practical implementation, helping designers and researchers interrogate common assumptions about GenAI in their own contexts. By recasting these stopsigns into more nuanced frameworks, we provide the design research community with practical approaches for thinking about and working with these emerging technologies.

Introduction: Ureteral stents are widely used in the specialty of urology to preserve renal function and provide ureteral patency in cases of urolithiasis, strictures, malignancy, and trauma. This paper presents a novel application of prophylactic ureteral stents deployed under MRI-guidance for ureteral protection in the setting of in-bore salvage cryoablation therapy for recurrent and metastatic prostate cancer. This is the first known case series of ureteral stent placement using near real-time MRI. Materials and Methods: A retrospective chart review was performed for all patients who underwent MRI-guided ureteral stent placement prior to in-bore cryoablation therapy from 2021 to 2022. Each case was managed by an interdisciplinary team of urologists and interventional radiologists. Preoperative and postoperative data were collected for descriptive analysis. Physics safety testing was conducted on the cystoscope and viewing apparatus prior to its implementation for stent deployment. Results: A total of seven males, mean age 73.4 years (range 65–81), underwent successful prophylactic, cystoscopic MRI-guided ureteral stent placement prior to cryoablation therapy of their prostate cancer. No intraoperative complications occurred. A Grade 2 postoperative complication of pyelonephritis and gross hematuria following stent removal occurred in one case. The majority of patients were discharged the same day as their procedure. Conclusions: This case series demonstrates the feasibility of in-bore cystoscopic aided MRI guidance for ureteral stent placement. Ureteral stents can be used to increase the safety margin of complex cryoablation treatments close to the ureter. Furthermore, by following the meticulous MRI safety protocols established by MRI facility safety design guidelines, MRI conditional tools can aid therapy in the burgeoning interventional MRI space.

OBJECTIVES:The aims of the study are to develop a prostate cancer risk prediction model that combines clinical and magnetic resonance imaging (MRI)-related findings and to assess the impact of adding Prostate Imaging-Reporting and Data System (PI-RADS) ≥3 lesions-level findings on its diagnostic performance. METHODS:This 3-center retrospective study included prostate MRI examinations performed with clinical suspicion of clinically significant prostate cancer (csPCa) between 2018 and 2022. Pathological diagnosis within 1 year after the MRI was used to diagnose csPCa. Seven clinical, 3 patient-level MRI-related, and 4 lesion-level MRI-related findings were extracted. After feature selection, 2 logistic regression models with and without lesions-level findings were created using data from facility I and II (development cohort). The area under the receiver operating characteristic curve (AUC) between the 2 models was compared in the PI-RADS ≥3 population in the development cohort and Facility III (validation cohort) using the Delong test. Interfacility differences of the selected predictive variables were evaluated using the Kruskal-Wallis test or chi-squared test. RESULTS:Selected lesion-level features included the peripheral zone involvement and apparent diffusion coefficient (ADC) values. The model with lesions-level findings had significantly higher AUC than the model without in 655 examinations in the development cohort (0.81 vs 0.79, respectively, P  = 0.005), but not in 553 examinations in the validation cohort (0.77 vs 0.76, respectively). Large interfacility differences were seen in the ADC distribution ( P  < 0.001) and csPCa proportion in PI-RADS 3-5 ( P  < 0.001). CONCLUSIONS:Adding lesions-level findings improved the csPCa discrimination in the development but not the validation cohort. Interfacility differences impeded model generalization, including the distribution of reported ADC values and PI-RADS score-level csPCa proportion.

Abstract Purpose To assess the diagnostic performance of prostate MRI by estimating the proportion of clinically significant prostate cancer (csPCa) in patients without prostate pathology. Materials and methods This three-center retrospective study included prostate MRI examinations performed for clinical suspicion of csPCa (Grade group ≥ 2) between 2018 and 2022. Examinations were divided into two groups: pathological diagnosis within 1 year after the MRI (post-MRI pathology) is present and absent. Risk prediction models were developed using the extracted eleven common predictive variables from the patients with post-MRI pathology. Then, the csPCa proportion in the patients without post-MRI pathology was estimated by applying the model. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive and negative predictive values (PPV/NPV) of prostate MRI in diagnosing csPCa were subsequently calculated for patients with and without post-MRI prostate pathology (estimated statistics) with a positive threshold of PI-RADS ≥ 3. Results Of 12,191 examinations enrolled (mean age, 65.7 years ± 8.4 [standard deviation]), PI-RADS 1–2 was most frequently assigned (55.4%) with the lowest pathological confirmation rate of 14.0–18.2%. Post-MRI prostate pathology was found in 5670 (46.5%) examinations. The estimated csPCa proportions across facilities were 12.6–15.3%, 18.4–31.4%, 45.7–69.9%, and 75.4–88.3% in PI-RADS scores of 1–2, 3, 4, and 5, respectively. The estimated (observed) performance statistics were as follows: AUC, 0.78–0.81 (0.76–0.79); sensitivity, 76.6–77.3%; specificity, 67.5–78.6%; PPV, 49.8–66.6% (52.0–67.7%); and NPV, 84.4–87.2% (82.4–86.6%). Conclusion We proposed a method to estimate the probabilities harboring csPCa for patients who underwent prostate MRI examinations, which allows us to understand the PI-RADS diagnostic performance with several metrics. Clinical relevance statement The reported estimated performance metrics are expected to aid in understanding the true diagnostic value of PI-RADS in the entire prostate MRI population performed with clinical suspicion of prostate cancer. Key Points Calculating performance metrics only from patients who underwent prostate biopsy may be biased due to biopsy selection criteria, especially in PI-RADS 1–2. The estimated area under the receiver operating characteristic curve of PI-RADS in the entire prostate MRI population ranged from 0.78 to 0.81 at three facilities. The estimated statistics are expected to help us understand the true PI-RADS performance and serve as a reference for future studies. Graphical Abstract

You have accessJournal of UrologySurgical Technology & Simulation: Artificial Intelligence I (MP07)1 May 2024MP07-04 INITIAL EXPERIENCE WITH A FULLY INTEGRATED ARTIFICIAL INTELLIGENCE PLATFORM DURING MINIMALLY INVASIVE SURGERY Abhinav Khanna, Stephen A. Boorjian, Igor Frank, Paras Shah, Vidit Sharma, R. Houston Thompson, Aaron Potretzke, George Chow, Adam Miller, Ross Avant, Daniel Elliott, Derek Lomas, J. Nicholas Warner, Kevin Koo, Meghan Cooper, Tobias Kohler, Lance Mynderse, and Matthew Tollefson Abhinav KhannaAbhinav Khanna , Stephen A. BoorjianStephen A. Boorjian , Igor FrankIgor Frank , Paras ShahParas Shah , Vidit SharmaVidit Sharma , R. Houston ThompsonR. Houston Thompson , Aaron PotretzkeAaron Potretzke , George ChowGeorge Chow , Adam MillerAdam Miller , Ross AvantRoss Avant , Daniel ElliottDaniel Elliott , Derek LomasDerek Lomas , J. Nicholas WarnerJ. Nicholas Warner , Kevin KooKevin Koo , Meghan CooperMeghan Cooper , Tobias KohlerTobias Kohler , Lance MynderseLance Mynderse , and Matthew TollefsonMatthew Tollefson View All Author Informationhttps://doi.org/10.1097/01.JU.0001008728.41882.d7.04AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: Recent advances in computer vision have enabled artificial intelligence (AI) evaluation of surgical video at a scale not previously feasible. Applying AI video analysis to real-world practice has potential to unearth new insights into surgery. We report our experience with an AI platform that is fully integrated into our urology practice. METHODS: Video from endoscopic, laparoscopic, and robotic surgeries performed at our tertiary academic center were uploaded into a secure location on the Mayo Clinic cloud server. Videos were analyzed in real-time using a novel AI computer vision platform (Theator, Inc.). Each surgical step was automatically detected by individualized AI algorithms tailored to each surgery type. Key safety events, such as "critical views of safety", preservation of key anatomic structures, and safety maneuvers were automatically annotated. Adverse events, including hemorrhage, tumor disruption, and vascular injury were identified. All AI-generated insights were annotated directly onto surgical video timelines, and results of AI analysis were available on mobile and desktop apps in real-time. RESULTS: From December 2021-September 2023, a total of 1388 surgeries were performed by 18 individual surgeons with real-time AI analysis. This included 766 radical prostatectomy (median video duration 156 [IQR 112-197] minutes), 395 endoscopic BPH procedures (49 [25-80] minutes), 132 partial nephrectomy (122 [92-184] minutes), and 29 transurethral bladder tumor resection (31 [23-77] minutes). Insights offered by AI video analysis include breakdown of full-length surgeries into distinct labeled steps, benchmarking efficiency of individual surgical steps across surgeons, and cataloging trends in surgical step duration and safety milestones over time (Figure 1). CONCLUSIONS: To our knowledge, this represents the first report of comprehensive integration of a novel AI computer vision platform into real-world surgical practice in the United States. Future investigations should explore the relationship between AI-detected intra-operative events with clinical outcomes. AI video analysis has potential applications in surgical education, quality benchmarking, performance review, automated documentation, and surgeon decision-support, all of which warrant further study. Download PPT Source of Funding: None © 2024 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 211Issue 5SMay 2024Page: e105 Advertisement Copyright & Permissions© 2024 by American Urological Association Education and Research, Inc.Metrics Author Information Abhinav Khanna More articles by this author Stephen A. Boorjian More articles by this author Igor Frank More articles by this author Paras Shah More articles by this author Vidit Sharma More articles by this author R. Houston Thompson More articles by this author Aaron Potretzke More articles by this author George Chow More articles by this author Adam Miller More articles by this author Ross Avant More articles by this author Daniel Elliott More articles by this author Derek Lomas More articles by this author J. Nicholas Warner More articles by this author Kevin Koo More articles by this author Meghan Cooper More articles by this author Tobias Kohler More articles by this author Lance Mynderse More articles by this author Matthew Tollefson More articles by this author Expand All Advertisement PDF downloadLoading ...

Generative AI systems are increasingly capable of expressing emotions via text and imagery. Effective emotional expression will likely play a major role in the efficacy of AI systems -- particularly those designed to support human mental health and wellbeing. This motivates our present research to better understand the alignment of AI expressed emotions with the human perception of emotions. When AI tries to express a particular emotion, how might we assess whether they are successful? To answer this question, we designed a survey to measure the alignment between emotions expressed by generative AI and human perceptions. Three generative image models (DALL-E 2, DALL-E 3 and Stable Diffusion v1) were used to generate 240 examples of images, each of which was based on a prompt designed to express five positive and five negative emotions across both humans and robots. 24 participants recruited from the Prolific website rated the alignment of AI-generated emotional expressions with a text prompt used to generate the emotion (i.e., "A robot expressing the emotion amusement"). The results of our evaluation suggest that generative AI models are indeed capable of producing emotional expressions that are well-aligned with a range of human emotions; however, we show that the alignment significantly depends upon the AI model used and the emotion itself. We analyze variations in the performance of these systems to identify gaps for future improvement. We conclude with a discussion of the implications for future AI systems designed to support mental health and wellbeing.

This workshop explores the transformative potential of generative artificial intelligence (GenAI) in design research. GenAI, capable of creating new content such as images, text, music, video, and code, raises important questions about authorship, agency, and design practice. Inspired by Roland Barthes’ "The Death of the Author," this workshop examines how GenAI reshapes design research roles and methods. Key topics include best practices, ethical considerations, knowledge generation, and collaboration patterns between human and AI creatives. Building on themes identified in the successful DIS 2023 workshop, this 2-day event invites designers and researchers to present completed projects, works-in-progress, and theoretical provocations. The structure allows time for both presentations and in-depth discussions, aiming to develop an online resource library and a collaborative publication. The workshop seeks to advance the discourse on GenAI, addressing its challenges and opportunities in design research.

The PRESERVE study (NCT04972097) aims to evaluate the safety and effectiveness of the NanoKnife System to ablate prostate tissue in patients with intermediate-risk prostate cancer (PCa). The NanoKnife uses irreversible electroporation (IRE) to deliver high-voltage electrical pulses to change the permeability of cell membranes, leading to cell death. A total of 121 subjects with organ-confined PCa ≤ T2c, prostate-specific antigens (PSAs) ≤ 15 ng/mL, and a Gleason score of 3 + 4 or 4 + 3 underwent focal ablation of the index lesion. The primary endpoints included negative in-field biopsy and adverse event incidence, type, and severity through 12 months. At the time of analysis, the trial had completed accrual with preliminary follow-up available. Demographics, disease characteristics, procedural details, PSA responses, and adverse events (AEs) are presented. The median (IQR) age at screening was 67.0 (61.0–72.0) years and Gleason distribution 3 + 4 (80.2%) and 4 + 3 (19.8%). At 6 months, all patients with available data (n = 74) experienced a median (IQR) percent reduction in PSA of 67.6% (52.3–82.2%). Only ten subjects (8.3%) experienced a Grade 3 adverse event; five were procedure-related. No Grade ≥ 4 AEs were reported. This study supports prior findings that IRE prostate ablation with the NanoKnife System can be performed safely. Final results are required to fully assess oncological, functional, and safety outcomes.

As artificial intelligence (AI) continues advancing, ensuring positive societal impacts becomes critical, especially as AI systems become increasingly ubiquitous in various aspects of life. However, developing "AI for good" poses substantial challenges around aligning systems with complex human values. Presently, we lack mature methods for addressing these challenges. This article presents and evaluates the Positive AI design method aimed at addressing this gap. The method provides a human-centered process to translate wellbeing aspirations into concrete practices. First, we explain the method's four key steps: contextualizing, operationalizing, optimizing, and implementing wellbeing supported by continuous measurement for feedback cycles. We then present a multiple case study where novice designers applied the method, revealing strengths and weaknesses related to efficacy and usability. Next, an expert evaluation study assessed the quality of the resulting concepts, rating them moderately high for feasibility, desirability, and plausibility of achieving intended wellbeing benefits. Together, these studies provide preliminary validation of the method's ability to improve AI design, while surfacing areas needing refinement like developing support for complex steps. Proposed adaptations such as examples and evaluation heuristics could address weaknesses. Further research should examine sustained application over multiple projects. This human-centered approach shows promise for realizing the vision of 'AI for Wellbeing' that does not just avoid harm, but actively benefits humanity.

INTRODUCTION:With Alzheimer's disease and related dementias (ADRD) representing an enormous public health challenge, there is a need to support individuals in learning about and addressing their modifiable risk factors (e.g., diet, sleep, and physical activity) to prevent or delay dementia onset. However, there is limited availability for evidence-informed tools that deliver both quality education and support for positive behavior change such as by increasing self-efficacy and personalizing goal setting. Tools that address the needs of Latino/a, at higher risk for ADRD, are even more scarce. METHODS:We established a multidisciplinary team to develop the Healthy Actions and Lifestyles to Avoid Dementia or Hispanos y el ALTo a la Demencia (HALT-AD) program, a bilingual online personalized platform to educate and motivate participants to modify their risk factors for dementia. Grounded in social cognitive theory and following a cultural adaptation framework with guidance from a community advisory board, we developed HALT-AD iteratively through several cycles of rapid prototype development, user-centered evaluation through pilot testing and community feedback, and refinement. RESULTS:Using this iterative approach allowed for more than 100 improvements in the content, features, and design of HALT-AD to improve the program's usability and alignment with the interests and educational/behavior change support needs of its target audience. Illustrative examples of how pilot data and community feedback informed improvements are provided. DISCUSSION:Developing HALT-AD iteratively required learning through trial and error and flexibility in workflows, contrary to traditional program development methods that rely on rigid, pre-set requirements. In addition to efficacy trials, studies are needed to identify mechanisms for effective behavior change, which might be culturally specific. Flexible and personalized educational offerings are likely to be important in modifying risk trajectories in ADRD.

To develop an automated pipeline for extracting prostate cancer-related information from clinical notes. This retrospective study included 23,225 patients who underwent prostate MRI between 2017 and 2022. Cancer risk factors (family history of cancer and digital rectal exam findings), pre-MRI prostate pathology, and treatment history of prostate cancer were extracted from free-text clinical notes in English as binary or multi-class classification tasks. Any sentence containing pre-defined keywords was extracted from clinical notes within one year before the MRI. After manually creating sentence-level datasets with ground truth, Bidirectional Encoder Representations from Transformers (BERT)-based sentence-level models were fine-tuned using the extracted sentence as input and the category as output. The patient-level output was determined by compilation of multiple sentence-level outputs using tree-based models. Sentence-level classification performance was evaluated using the area under the receiver operating characteristic curve (AUC) on 15

ObjectiveAutomated surgical step recognition (SSR) using AI has been a catalyst in the “digitization” of surgery. However, progress has been limited to laparoscopy, with relatively few SSR tools in endoscopic surgery. This study aimed to create a SSR model for transurethral resection of bladder tumors (TURBT), leveraging a novel application of transfer learning to reduce video dataset requirements.Materials and methodsRetrospective surgical videos of TURBT were manually annotated with the following steps of surgery: primary endoscopic evaluation, resection of bladder tumor, and surface coagulation. Manually annotated videos were then utilized to train a novel AI computer vision algorithm to perform automated video annotation of TURBT surgical video, utilizing a transfer-learning technique to pre-train on laparoscopic procedures. Accuracy of AI SSR was determined by comparison to human annotations as the reference standard.ResultsA total of 300 full-length TURBT videos (median 23.96 min; IQR 14.13–41.31 min) were manually annotated with sequential steps of surgery. One hundred and seventy-nine videos served as a training dataset for algorithm development, 44 for internal validation, and 77 as a separate test cohort for evaluating algorithm accuracy. Overall accuracy of AI video analysis was 89.6%. Model accuracy was highest for the primary endoscopic evaluation step (98.2%) and lowest for the surface coagulation step (82.7%).ConclusionWe developed a fully automated computer vision algorithm for high-accuracy annotation of TURBT surgical videos. This represents the first application of transfer-learning from laparoscopy-based computer vision models into surgical endoscopy, demonstrating the promise of this approach in adapting to new procedure types.

Purpose: To evaluate the safety and effectiveness of magnetic resonance (MR) imaging-guided cryoablation of prostate cancer metastatic lymph nodes (LNs). Materials and methods: Fifty-two patients with prostate cancer who underwent MR imaging-guided LN ablation from September 2013 to June 2022 were retrospectively reviewed. Of these, 6 patients were excluded because adequate ablation margins (3-5 mm) could not be achieved secondary to adjacent structures. The remaining 46 patients (mean age, 70 years [SD +/- 7]) underwent 55 MR imaging-guided cryoablation procedures of metastatic LNs (25 in the pelvic sidewall, 20 within the pelvic region, and 10 in the abdomen) with procedural intent of complete ablation. Locoregional tumor control (ie, technical success in the target LN) was evaluated on initial follow-up positron emission tomography (PET) scans at a mean of 4 months (SD +/- 2). Preablation and postablation prostate-specific antigen (PSA) levels were recorded. Imaging follow-up continued until a median of 27.5 months (range: 3-108 months). Results: Ninety-five percent (52/55) of treated LNs demonstrated no considerable activity on PET scans at initial follow-up at 4 months (SD +/- 2). PSA decreased to an undetectable level of <0.1 ng/mL after cryoablation in 14 of 46 (30.4%) patients with corresponding lack of activity in 13 of 46 (28.2%) patients on continued PET imaging follow-up. Only 6 of 55 (10.9%) patients had transient adverse events, which all resolved with no long-term sequelae. Conclusions: MR imaging-guided percutaneous cryoablation of metastatic LNs is a safe and technically effective technique for treating metastatic prostate cancer in LNs.

OBJECTIVE:To define the natural history, patterns of recurrence and treatment modalities for local prostate cancer (PCa) recurrence following radical prostatectomy (RP) and radiation therapy (RT), and to investigate factors that could predict metastasis-free survival (MFS) in this unique patient population. METHODS:We queried a prospectively maintained PCa registry to identify men developing in-field recurrence (IFR) following RP and RT from 2008 to 2021 at a single institution. IFR was defined as biopsy-proven recurrent PCa or the presence of persistent positron emission tomography-avid lesions in the prior radiation field without evidence of metastasis. Cox regression was conducted to determine predictors of MFS. Kaplan-Meier methods were used to calculate MFS, cancer-specific survival (CSS) and overall survival (OS) for patients in three primary therapy categories: cryoablation, androgen deprivation therapy (ADT) alone, and surveillance. RESULTS:Of 4575 patients from our registry, 108 (2.3%) with IFR were identified. The median (interquartile range [IQR]) time to IFR from salvage treatment was 78 (50-126) months. A total of 29 patients (26%) were managed with cryoablation, 23 (21%) with ADT, and 28 (25%) with surveillance. The median (IQR) follow-up was 76 (48-100) months. There were no statistically significant differences in MFS (P = 0.67) or OS (P = 0.07) among the three primary treatment cohorts. Patients treated with ADT or cryoablation had longer CSS compared to patients managed with surveillance (P = 0.047). CONCLUSIONS:We found that IFR may present years after completion of primary treatment for PCa. While curative management strategies may be attempted, local and distant metastatic recurrence is common and often requires systemic therapy.