Visual extended reality tools in image-guided surgery in urology: a systematic review.

PURPOSE: The aim of this systematic review is to assess the clinical implications of employing various Extended Reality (XR) tools for image guidance in urological surgery. METHODS: In June 2023, a systematic electronic literature search was conducted using the Medline database (via PubMed), Embase (via Ovid), Scopus, and Web of Science. The search strategy was designed based on the PICO (Patients, Intervention, Comparison, Outcome) criteria. Study protocol was registered on PROSPERO (registry number CRD42023449025). We incorporated retrospective and prospective comparative studies, along with single-arm studies, which provided information on the use of XR, Mixed Reality (MR), Augmented Reality (AR), and Virtual Reality (VR) in urological surgical procedures. Studies that were not written in English, non-original investigations, and those involving experimental research on animals or cadavers were excluded from our analysis. The quality assessment of comparative and cohort studies was conducted utilizing the Newcastle-Ottawa scale, whilst for randomized controlled trials (RCTs), the Jadad scale was adopted. The level of evidence for each study was determined based on the guidelines provided by the Oxford Centre for Evidence-Based Medicine. RESULTS: The initial electronic search yielded 1,803 papers after removing duplicates. Among these, 58 publications underwent a comprehensive review, leading to the inclusion of 40 studies that met the specified criteria for analysis. 11, 20 and 9 studies tested XR on prostate cancer, kidney cancer and miscellaneous, including bladder cancer and lithiasis surgeries, respectively. Focusing on the different technologies 20, 15 and 5 explored the potential of VR, AR and MR. The majority of the included studies (i.e., 22) were prospective non-randomized, whilst 7 and 11 were RCT and retrospective studies respectively. The included studies that revealed how these new tools can be useful both in preoperative and intraoperative setting for a tailored surgical approach. CONCLUSIONS: AR, VR and MR techniques have emerged as highly effective new tools for image-guided surgery, especially for urologic oncology. Nevertheless, the complete clinical advantages of these innovations are still in the process of evaluation.

Prognostic significance of residual tumor at restaging transurethral bladder resection in high-risk non-muscle-invasive bladder cancer.

PURPOSE: To assess prognostic significance of residual tumor at repeat transurethral resection (reTUR) in contemporary non-muscle-invasive bladder cancer (NMIBC) patients. METHODS: Patients were identified retrospectively from eight referral centers in France, Italy and Spain. The cohort included consecutive patients with high or very-high risk NMIBC who underwent reTUR and subsequent adjuvant BCG therapy. RESULTS: A total of 440 high-risk NMIBC patients were screened, 29 (6%) were upstaged ≥ T2 at reTUR and 411 were analyzed (T1 stage: n = 275, 67%). Residual tumor was found in 191 cases (46%). In patients with T1 tumor on initial TURBT, persistent T1 tumor was found in 18% of reTUR (n = 49/275). In patients with high-grade Ta tumor on initial TURBT, T1 tumor was found in 6% of reTUR (n = 9/136). In multivariable logistic regression analysis, we found no statistical association between the use of photodynamic diagnosis (PDD, p = 0.4) or type of resection (conventional vs. en bloc, p = 0.6) and the risk of residual tumor. The estimated 5-yr recurrence and progression-free survival were 56% and 94%, respectively. Residual tumor was significantly associated with a higher risk of recurrence (p < 0.001) but not progression (p = 0.11). Only residual T1 tumor was associated with a higher risk of progression (p < 0.001) with an estimated 5-yr progression-free survival rate of 76%. CONCLUSIONS: ReTUR should remain a standard for T1 tumors, irrespective of the use of en bloc resection or PDD and could be safely omitted in high-grade Ta tumors. Persistent T1 tumor at reTUR should not exclude these patients from conservative management, and further studies are needed to explore the benefit of a third resection in this subgroup.

Three-dimensional virtual models assistance predicts higher rates of "successful" minimally invasive partial nephrectomy: an Institutional analysis across the available trifecta definitions.

PURPOSE: 3D virtual models (3DVMs) are nowadays under scrutiny to improve partial nephrectomy (PN) outcomes. Five different Trifecta definitions have been proposed to optimize the framing of "success" in the PN field. Our aim is to analyze if the use of 3DVMs could impact the success rate of minimally invasive PN (mi-PN), according to the currently available definitions of Trifecta. MATERIALS AND METHODS: At our Institution 250 cT1-2N0M0 renal masses patients treated with mi-PN were prospectively enrolled. Inclusion criteria were the availability of contrast-enhanced CT, baseline and postoperative serum creatinine, and eGFR. These patients were then compared with a control group of 710 patients who underwent mi-PN with the same renal function assessments, but without 3DVMs. Multivariable logistic regression (MLR) models were used to predict the trifecta achievement according to the different trifecta definitions. RESULTS: Among the definitions, Trifecta rates ranged between 70.8% to 97.4% in the 3DVM group vs. 56.8% to 92.8% in the control group (all p values < 0.05). 3DVMs showed better postoperative outcomes in terms of ΔeGFR, ( - 16.6% vs. - 2.7%, p = 0.03), postoperative complications (15%, vs 22.9%, p = 0.002) and major complications (Clavien Dindo > 3, 2.8% vs 5.6%, p = 0.03). At MLR 3DVMs assistance independently predicted higher rates of successful PN across all the available definitions of Trifecta (OR: 2.7 p < 0.001, OR:2.0 p = 0.0008, OR:2.8 p = 0.02, OR 2.0 p = 0.003). CONCLUSIONS: The 3DVMs availability was found to be the constant predictive factor of successful PN, with a twofold higher probability of achieving Trifecta regardless of the different definitions available in Literature.

Adrenocortical carcinoma with venous tumor invasion: is there a role for mini-invasive surgery?

OBJECTIVE: This study aims to investigate early oncologic outcomes in patients with adrenocortical carcinoma (ACC) with venous invasion (VI) treated using both open and mini-invasive approaches. PATIENTS AND MATERIALS: We conducted a retrospective analysis of 4 international referral center databases, including all the patients undergoing adrenalectomy for ACC with VI from January 2007 to March 2020. According to CT scan or MRI, the tumor thrombus was classified into four levels: (1) adrenal vein invasion; (2) renal vein invasion; (3) infra-hepatic Inferior vena cava (IVC); and (4) retro-hepatic IVC. In addition, we divided our patients into patients who had undergone open surgery and mini-invasive surgery. RESULTS: We identified 20 patients with a median follow-up of 12 months. The median tumor size was 110mm. ENSAT stage was II in 4 patients, III in 13 patients, and IV in 3 patients. Tumor thrombus extended in the adrenal vein (n=5), renal vein (n=1), infra-hepatic IVC (n=9), or into the retro-hepatic IVC (n=5). Ten patients were treated with a mini-invasive approach. The patient treated with an open approach reported a more aggressive disease. The two groups did not differ in surgical margins, surgical time, blood losses, complications, and length of stay. The prognosis resulted worse in the patient undergoing open. Kaplan-Meier analysis indicated a difference in OS for the patients stratified by ENSAT stage (Log-rank p=0.011); we also reported a difference in DFS for patients stratified for thrombus extension (p=0.004) and ENSAT stage (p<0.001). CONCLUSION: The DFS of patients with VI from ACC is influenced by the staging and the extension of the venous invasion; the staging influences the OS. The mini-invasive approach seems feasible in selected patients; however, further studies investigating the oncological outcomes are needed. A mini-invasive approach for adrenal tumors with venous invasion is an explorable option in very selected patients.

Treatment of Ureteral Stent-Related Symptoms.

BACKGROUND: The aim of the study was to assess the effectiveness of the main classes of drugs used at reducing morbidity related to ureteric stents. SUMMARY: After establishing a priori protocol, a systematic electronic literature search was conducted in July 2019. The randomized clinical trials (RCTs) selection proceeded in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines and was registered (PROSPERO ID 178130). The risk of bias and the quality assessment of the included RCTs were performed. Ureteral Stent Symptom Questionnaire (USSQ), International Prostate Symptom Score (IPSS), and quality of life (QoL) were pooled for meta-analysis. Mean difference and risk difference were calculated as appropriate for each outcome to determine the cumulative effect size. Fourteen RCTs were included in the analysis accounting for 2,842 patients. Alpha antagonist, antimuscarinic, and phosphodiesterase (PDE) inhibitors significatively reduced all indexes of the USSQ, the IPSS and QoL scores relative to placebo. Conversely, combination therapy (alpha antagonist plus antimuscarinic) showed in all indexes of the USSQ, IPSS, and QoL over alpha antagonist or antimuscarinic alone. On comparison with alpha blockers, PDE inhibitors were found to be equally effective for urinary symptoms, general health, and body pain parameters, but sexual health parameters improved significantly with PDE inhibitors. Finally, antimuscarinic resulted in higher decrease in all indexes of the USSQ, the IPSS, and QoL relative to alpha antagonist. KEY MESSAGE: Relative to placebo, alpha antagonist alone, antimuscarinics alone, and PDE inhibitors alone have beneficial effect in reducing stent-related symptoms. Furthermore, there are significant advantages of combination therapy compared with monotherapy. Finally, PDE inhibitors are comparable to alpha antagonist, and antimuscarinic seems to be more effective than alpha antagonist alone.

The impact of 3D models on positive surgical margins after robot-assisted radical prostatectomy.

PURPOSE: To evaluate the role of 3D models on positive surgical margin rate (PSM) rate in patients who underwent robot-assisted radical prostatectomy (RARP) compared to a no-3D control group. Secondarily, we evaluated the postoperative functional and oncological outcomes. METHODS: Prospective study enrolling patients with localized prostate cancer (PCa) undergoing RARP with mp-MRI-based 3D model reconstruction, displayed in a cognitive or augmented-reality fashion, at our Centre from 01/2016 to 01/2020. A control no-3D group was extracted from the last two years of our Institutional RARP database. PSMr between the two groups was evaluated and multivariable linear regression (MLR) models were applied. Finally, Kaplan-Meier estimator was used to calculate biochemical recurrence at 12 months after the intervention. RESULTS: 160 patients were enrolled in the 3D Group, while 640 were selected for the Control Group. A more conservative NS approach was registered in the 3D Group (full NS 20.6% vs 12.7%; intermediate NS 38.1% vs 38.0%; standard NS 41.2% vs 49.2%; p = 0.02). 3D Group patients had lower PSM rates (25 vs. 35.1%, p = 0.01). At MLR models, the availability of 3D technology (p = 0.005) and the absence of extracapsular extension (ECE, p = 0.004) at mp-MRI were independent predictors of lower PSMr. Moreover, 3D model represented a significant protective factor for PSM in patients with ECE or pT3 disease. CONCLUSION: The availability of 3D models during the intervention allows to modulate the NS approach, limiting the occurrence of PSM, especially in patients with ECE at mp-MRI or pT3 PCa.

Anastomosis quality score during robot-assisted radical prostatectomy: a new simple tool to maximize postoperative management.

PURPOSE: The urethro-vesical anastomosis represents one of the most challenging steps of robotic prostatectomy (RARP). To maximize postoperative management, we specifically designed our anastomosis quality score (AQS), based on the intraoperative characteristics of the urethra and bladder neck. METHODS: This is a prospective study, conducted from April 2019 to March 2020. All the patients were classified into three different AQS categories (low, intermediate, high) based on the quality of the anastomosis. The postoperative management was modulated accordingly. RESULTS: We enrolled 333 patients. According to AQS, no differences were recorded in intraoperative complications (p = 0.9). Median hospital stay and catheterization time were longer in AQS 1 group (p < 0.001). Additionally, the occurrence of postoperative complication was higher in AQS 1 category (p = 0.002) but, when focusing on the complications related to the quality of the anastomosis, no differences were found neither for acute urinary retention (p = 0.12) nor urine leakage (p = 0.11). Finally, concerning the continence recovery, no significant differences were found among the three groups for each time point. The highest potency recovery rate at one month of follow-up was recorded in AQS 3 category (p = 0. 03). CONCLUSION: The AQS proposed revealed to be a valid too to intraoperatively categorize patients who underwent RARP on the basis of the urethral and bladder neck features. The modulated postoperative management for each specific score category allowed to limit the occurrence of complications and to maximize the functional outcomes.

Implementing telemedicine for the management of benign urologic conditions: a single centre experience in Italy.

PURPOSE: To assess the use of telemedicine with phone-call visits as a practical tool to follow-up with patients affected by urological benign diseases, whose clinic visits had been cancelled during the acute phase of the COVID-19 pandemic. METHODS: Patients were contacted via phone-call and a specific questionnaire was administered to evaluate the health status of these patients and to identify those who needed an "in-person" ambulatory visit due to the worsening of their condition. Secondarily, the patients' perception of a potential shift towards a "telemedicine" approach to the management of their condition and to indirectly evaluate their desire to return to "in-person" clinic visits. RESULTS: 607 were contacted by phone-call. 87.5% (531/607) of the cases showed stability of the symptoms so no clinic in-person or emergency visits were needed. 81.5% (495/607) of patients were more concerned about the risk of contagion than their urological condition. The median score for phone visit comprehensibility and ease of communication of exams was 5/5; whilst patients' perception of phone visits' usefulness was scored 4/5. 53% (322/607) of the interviewees didn't own the basic supports required to be able to perform a real telemedicine consult according to the required standards. CONCLUSION: Telemedicine approach limits the number of unnecessary accesses to medical facilities and represents an important tool for the limitation of the risk of transmission of infectious diseases, such as COVID-19. However, infrastructures, health workers and patients should reach out to a computerization process to allow a wider diffusion of more advanced forms of telemedicine, such as televisit.

3D virtual models and augmented reality for radical prostatectomy: a narrative review.

BACKGROUND AND OBJECTIVE: The increasing popularity of three-dimensional (3D) virtual reconstructions of two-dimensional (2D) imaging in urology has led to significant technological advancements, resulting in the creation of highly accurate 3D virtual models (3DVMs) that faithfully replicate individual anatomical details. This technology enhances surgical reality, providing surgeons with hyper-accurate insights into instantaneous subjective surgical anatomy and improving preoperative surgical planning. In the uro-oncologic field, the utility of 3D virtual reconstruction has been demonstrated in nephron-sparing surgery, impacting surgical strategy and postoperative outcomes in prostate cancer (PCa). The aim of this study is to offer a thorough narrative review of the current state and application of 3D reconstructions and augmented reality (AR) in radical prostatectomy (RP). METHODS: A non-systematic literature review was conducted using Medline, PubMed, the Cochrane Database, and Embase to gather information on clinical trials, randomized controlled trials, review articles, and prospective and retrospective studies related to 3DVMs and AR in RP. The search strategy followed the PICOS (Patients, Intervention, Comparison, Outcome, Study design) criteria and was performed in January 2024. KEY CONTENT AND FINDINGS: The adoption of 3D visualization has become widespread, with applications ranging from preoperative planning to intraoperative consultations. The urological community's interest in intraoperative surgical navigation using cognitive, virtual, mixed, and AR during RP is evident in a substantial body of literature, including 16 noteworthy investigations. These studies highlight the varied experiences and benefits of incorporating 3D reconstructions and AR into RP, showcasing improvements in preoperative planning, intraoperative navigation, and real-time decision-making. CONCLUSIONS: The integration of 3DVMs and AR technologies in urological oncology, particularly in the context of RP, has shown promising advancements. These technologies provide crucial support in preoperative planning, intraoperative navigation, and real-time decision-making, significantly improving the visualization of complex anatomical structures helping in the nerve sparing (NS) approach modulation and reducing positive surgical margin (PSM) rate. Despite positive outcomes, challenges such as small patient cohorts, lack of standardized methodologies, and concerns about costs and technology adoption persist.

Urinary PSA-ZINC biomarker outperforms standard of care in early detection of prostate cancer.

BACKGROUND: Urine is a promising biological fluid for prostate cancer (PCa) diagnostics due to its non-invasive collection and wide range of biomarkers. The aim of this study was to assess the role of urinary PSA (uPSA) and urinary Zinc (uZinc) as biomarkers for the diagnosis of PCa in combination with routine parameters of standard of care (SOC - blood PSA, abnormal DRE, age) and MRI in patients candidates for prostate biopsy. METHODS: Urine samples after prostatic massages were collected from men with suspected PCa scheduled for prostate biopsy. Quantification of uPSA was performed by ECLIA platform and confirmed by ELISA assay, while uZinc measurement was evaluated by ICP-MS and confirmed by colorimetric in vitro assay. Six multivariate logistic regression analysis were performed to assess diagnostic performance of uPSA and uZinc (urine), SOC and MRI alone, and combination of MRI+SOC, MRI+urine and SOC+MRI+urine. The discriminative power of the logistic models was assessed by calculating the area under the receiver operating characteristic (ROC) curves (AUC). RESULTS: Two hundred thirty-eight patients were included in the analysis; 145 of them were diagnosed with PCa. Urine test showed a better discrimination of HS from CP, in respect of uPSA and uZinc alone, both for PCa of any grade and Gleason Score ≥7 (4+3) (AUC 0.804 and 0.823 respectively). ROC curve combining SOC+MRI+urine showed an AUC=0.882, that is statistically different from SOC or MRI alone, or MRI+SOC (P=0.0001, P=0.0001, and P=0.008 respectively). PCa risk algorithm designed considering SOC+MRI+urine results in potential reduction of 57% of unnecessary biopsies compared to the current standard parameters. CONCLUSIONS: The loss of uPSA and Zinc production and secretion during neoplastic transformation of the prostate could potentially represent a hallmark of PCa. Its combination with age, PSA and DRE, as well as with mpMRI could represent an interesting approach to improve the diagnostic accuracy of PCa.

Development of Machine Learning Algorithm to Predict the Risk of Incontinence After Robot-Assisted Radical Prostatectomy.

Introduction: Predicting postoperative incontinence beforehand is crucial for intensified and personalized rehabilitation after robot-assisted radical prostatectomy. Although nomograms exist, their retrospective limitations highlight artificial intelligence (AI)'s potential. This study seeks to develop a machine learning algorithm using robot-assisted radical prostatectomy (RARP) data to predict postoperative incontinence, advancing personalized care. Materials and Methods: In this propsective observational study, patients with localized prostate cancer undergoing RARP between April 2022 and January 2023 were assessed. Preoperative variables included age, body mass index, prostate-specific antigen (PSA) levels, digital rectal examination (DRE) results, Gleason score, International Society of Urological Pathology grade, and continence and potency questionnaires responses. Intraoperative factors, postoperative outcomes, and pathological variables were recorded. Urinary continence was evaluated using the Expanded Prostate cancer Index Composite questionnaire, and machine learning models (XGBoost, Random Forest, Logistic Regression) were explored to predict incontinence risk. The chosen model's SHAP values elucidated variables impacting predictions. Results: A dataset of 227 patients undergoing RARP was considered for the study. Post-RARP complications were predominantly low grade, and urinary continence rates were 74.2%, 80.7%, and 91.4% at 7, 13, and 90 days after catheter removal, respectively. Employing machine learning, XGBoost proved the most effective in predicting postoperative incontinence risk. Significant variables identified by the algorithm included nerve-sparing approach, age, DRE, and total PSA. The model's threshold of 0.67 categorized patients into high or low risk, offering personalized predictions about the risk of incontinence after surgery. Conclusions: Predicting postoperative incontinence is crucial for tailoring rehabilitation after RARP. Machine learning algorithm, particularly XGBoost, can effectively identify those variables more heavily, impacting the outcome of postoperative continence, allowing to build an AI-driven model addressing the current challenges in post-RARP rehabilitation.

Computer Vision and Machine-Learning Techniques for Automatic 3D Virtual Images Overlapping During Augmented Reality Guided Robotic Partial Nephrectomy.

OBJECTIVES: The research's purpose is to develop a software that automatically integrates and overlay 3D virtual models of kidneys harboring renal masses into the Da Vinci robotic console, assisting surgeon during the intervention. INTRODUCTION: Precision medicine, especially in the field of minimally-invasive partial nephrectomy, aims to use 3D virtual models as a guidance for augmented reality robotic procedures. However, the co-registration process of the virtual images over the real operative field is performed manually. METHODS: In this prospective study, two strategies for the automatic overlapping of the model over the real kidney were explored: the computer vision technology, leveraging the super-enhancement of the kidney allowed by the intraoperative injection of Indocyanine green for superimposition and the convolutional neural network technology, based on the processing of live images from the endoscope, after a training of the software on frames from prerecorded videos of the same surgery. The work-team, comprising a bioengineer, a software-developer and a surgeon, collaborated to create hyper-accuracy 3D models for automatic 3D-AR-guided RAPN. For each patient, demographic and clinical data were collected. RESULTS: Two groups (group A for the first technology with 12 patients and group B for the second technology with 8 patients) were defined. They showed comparable preoperative and post-operative characteristics. Concerning the first technology the average co-registration time was 7 (3-11) seconds while in the case of the second technology 11 (6-13) seconds. No major intraoperative or postoperative complications were recorded. There were no differences in terms of functional outcomes between the groups at every time-point considered. CONCLUSION: The first technology allowed a successful anchoring of the 3D model to the kidney, despite minimal manual refinements. The second technology improved kidney automatic detection without relying on indocyanine injection, resulting in better organ boundaries identification during tests. Further studies are needed to confirm this preliminary evidence.

Automatic 3D Augmented-Reality Robot-Assisted Partial Nephrectomy Using Machine Learning: Our Pioneer Experience.

The aim of "Precision Surgery" is to reduce the impact of surgeries on patients' global health. In this context, over the last years, the use of three-dimensional virtual models (3DVMs) of organs has allowed for intraoperative guidance, showing hidden anatomical targets, thus limiting healthy-tissue dissections and subsequent damage during an operation. In order to provide an automatic 3DVM overlapping in the surgical field, we developed and tested a new software, called "ikidney", based on convolutional neural networks (CNNs). From January 2022 to April 2023, patients affected by organ-confined renal masses amenable to RAPN were enrolled. A bioengineer, a software developer, and a surgeon collaborated to create hyper-accurate 3D models for automatic 3D AR-guided RAPN, using CNNs. For each patient, demographic and clinical data were collected. A total of 13 patients were included in the present study. The average anchoring time was 11 (6-13) s. Unintended 3D-model automatic co-registration temporary failures happened in a static setting in one patient, while this happened in one patient in a dynamic setting. There was one failure; in this single case, an ultrasound drop-in probe was used to detect the neoplasm, and the surgery was performed under ultrasound guidance instead of AR guidance. No major intraoperative nor postoperative complications (i.e., Clavien Dindo > 2) were recorded. The employment of AI has unveiled several new scenarios in clinical practice, thanks to its ability to perform specific tasks autonomously. We employed CNNs for an automatic 3DVM overlapping during RAPN, thus improving the accuracy of the superimposition process.

Robotic Vena Cava Thrombectomy with Three-dimensional Augmented Reality Guidance.

Robotic surgery has recently been used for treatment of renal cell carcinoma (RCC) and neoplastic thrombus located in the renal vein or inferior vena cava (IVC). Accurate identification of the thrombus location is crucial, and three-dimensional augmented reality (3D AR) may be valuable in achieving this. We enrolled patients with nonmetastatic RCC and level 0-I venous thrombus (Mayo Clinic classification) for robot-assisted radical nephrectomy and thrombectomy with 3D AR guidance. Five patients were prospectively enrolled; three had a level 0 thrombus and two had a level I thrombus. The mean operative time was 123 ± 15 min, mean IVC clamping time was 9.4 ± 6.8 min, and mean estimated blood loss was 750 ± 150 ml. The AR system allowed precise estimation of the thrombus location in all cases. No intraoperative complications or postoperative Clavien-Dindo grade >2 complications occurred. Use of 3D AR guidance allowed correct estimation of the limits of the thrombus and guided the surgeon in selecting an appropriate surgical strategy.

Metaverse Surgical Planning with Three-dimensional Virtual Models for Minimally Invasive Partial Nephrectomy.

The recent integration of new virtual visualization modalities with artificial intelligence and high-speed internet connection has opened the door to the advent of the metaverse in medicine. In this totally virtual environment, three-dimensional virtual models (3DVMs) of the patient's anatomy can be visualized and discussed via digital avatars. Here we present for the first time a metaverse preoperative clinical case discussion before minimally invasive partial nephrectomy. The surgeons' digital avatars met in a virtual room and participated in a virtual consultation on the surgical strategy and clamping approach before the procedure. Robotic or laparoscopic procedures are then carried out according to the simulated surgical strategy. We demonstrate how this immersive virtual reality experience overcomes the barriers of distance and how the quality of surgical planning is enriched by a great sense of "being there", even if virtually. Further investigation will improve the quality of interaction with the models and among the avatars.

3D Model Artificial Intelligence-Guided Automatic Augmented Reality Images during Robotic Partial Nephrectomy.

More than ever, precision surgery is making its way into modern surgery for functional organ preservation. This is possible mainly due to the increasing number of technologies available, including 3D models, virtual reality, augmented reality, and artificial intelligence. Intraoperative surgical navigation represents an interesting application of these technologies, allowing to understand in detail the surgical anatomy, planning a patient-tailored approach. Automatic superimposition comes into this context to optimally perform surgery as accurately as possible. Through a dedicated software (the first version) called iKidney, it is possible to superimpose the images using 3D models and live endoscopic images during partial nephrectomy, targeting the renal mass only. The patient is 31 years old with a 28 mm totally endophytic right-sided renal mass, with a PADUA score of 9. Thanks to the automatic superimposition and selective clamping, an enucleoresection of the renal mass alone was performed with no major postoperative complication (i.e., Clavien-Dindo < 2). iKidney-guided partial nephrectomy is safe, feasible, and yields excellent results in terms of organ preservation and functional outcomes. Further validation studies are needed to improve the prototype software, particularly to improve the rotational axes and avoid human help. Furthermore, it is important to reduce the costs associated with these technologies to increase its use in smaller hospitals.

MRI/real-time ultrasound image fusion guided high-intensity focused ultrasound: a prospective comparative and functional analysis of different ablative techniques.

BACKGROUND: The aim of this paper was to compare safety and functional outcomes of total, hemi and focal ablation by the latest focal high-intensity focused ultrasound (HIFU) device. METHODS: This is a prospective study including patients with low to intermediate-risk PCa treated with HIFU by Focal One® device from 11/2018 to 3/2020. Before the treatment all patients underwent mp-magnetic resonance imaging (MRI) and subsequent MRI/transrectal ultrasound (TRUS) fusion and standard biopsy. Patients were stratified according to the type of ablation: total, hemi- or focal ablation. Functional data (IPSS, Quality of Life [QoL], IIEF-5, maximum flow [Qmax] and post void residual [PVR] at flowmetry) were assessed preoperatively and at 1, 3, 6 and 12 months after treatment. Moreover, the urinary symptoms reported by patients at IPSS questionnaire were divided in "irritative" and "obstructive" and compared. RESULTS: One hundred patients were enrolled. Median prostate volume and lesion diameter were 46 (IQR 25-75) mL and 10 (IQR 6-13) mm. 15, 50 and 35 patients underwent total, hemi- and focal ablation, respectively. No differences were found between them except for operative time (lower in the focal group, P<0.01). Significant lower incidence of irritative symptoms was identified in the focal group compared to the others (P<0.05 at 1 and 3 months of follow-up). No differences were found among the baseline status and the postoperative assessment in terms of obstructive IPSS items, IIEF-5, QoL, Qmax and PVR (all P value>0.05). CONCLUSIONS: Our study suggests that patients' specific HIFU tailoring with the MRI/real-time TRUS Guidance by Focal One® device is able to minimize the side effects of treatment.

Development of a novel nomogram to identify the candidate to extended pelvic lymph node dissection in patients who underwent mpMRI and target biopsy only.

BACKGROUND: Nowadays a tool able to predict the risk of lymph-node invasion (LNI) in patients underwent target biopsy (TB) only before radical prostatectomy (RP) is still lacking. Our aim is to develop a model based on mp-MRI and target biopsy (TB) alone able to predict the risk of LNI. METHODS: We retrospectively extracted data of patients with preoperative positive mp-MRI and TB only who underwent RARP with ePLND from April 2014 to March 2020. A logistic regression model was performed to evaluate the impact of pre- and intra-operative factors on the risk of LNI. Model discrimination was assessed using an area under (AUC) the ROC curve. A nomogram, and its calibration plot, to predict the risk of LNI were generated based on the logistic model. A validation of the model was done using a similar cohort. RESULTS: 461 patients were included, of which 52 (11.27) had LNI. After logistic regression analysis and multivariable model DRE, PI-RADS, seminal vesicle invasion, PSA and worst GS at I and II target lesions were significant predictors of LNI. The AUC was 0.74 [0.67-0.81] 95% CI. The calibration plot shows that our model is very close to the ideal one which is in the 95% CI. After the creation of a visual nomogram, the cut-off to discriminate between the risk or not of LNI was set with Youden index at 60 points that correspond to a risk of LNI of 7%. The model applied on a similar cohort shown a LH+ of 2.58 [2.17-2.98] 95% CI. CONCLUSIONS: Our nomogram for patients undergoing MRI-TB only takes into account clinical stage, SVI at MRI, biopsy Gleason pattern and PSA and it is able to identify patients with risk of LNI when a score higher than 7% is achieved.

Artificial Intelligence-Based Hyper Accuracy Three-Dimensional (HA3D®) Models in Surgical Planning of Challenging Robotic Nephron-Sparing Surgery: A Case Report and Snapshot of the State-of-the-Art with Possible Future Implications.

Recently, 3D models (3DM) gained popularity in urology, especially in nephron-sparing interventions (NSI). Up to now, the application of artificial intelligence (AI) techniques alone does not allow us to obtain a 3DM adequate to plan a robot-assisted partial nephrectomy (RAPN). Integration of AI with computer vision algorithms seems promising as it allows to speed up the process. Herein, we present a 3DM realized with the integration of AI and a computer vision approach (CVA), displaying the utility of AI-based Hyper Accuracy Three-dimensional (HA3D®) models in preoperative planning and intraoperative decision-making process of challenging robotic NSI. A 54-year-old Caucasian female with no past medical history was referred to the urologist for incidental detection of the right renal mass. Preoperative contrast-enhanced abdominal CT confirmed a 35 × 25 mm lesion on the anterior surface of the upper pole (PADUA 7), with no signs of distant metastasis. CT images in DICOM format were processed to obtain a HA3D® model. RAPN was performed using Da Vinci Xi surgical system in a three-arm configuration. The enucleation strategy was achieved after selective clamping of the tumor-feeding artery. Overall operative time was 85 min (14 min of warm ischemia time). No intra-, peri- and post-operative complications were recorded. Histopathological examination revealed a ccRCC (stage pT1aNxMx). AI is breaking new ground in medical image analysis panorama, with enormous potential in organ/tissue classification and segmentation, thus obtaining 3DM automatically and repetitively. Realized with the integration of AI and CVA, the results of our 3DM were accurate as demonstrated during NSI, proving the potentialities of this approach for HA3D® models' reconstruction.

Development of Bleeding Artificial Intelligence Detector (BLAIR) System for Robotic Radical Prostatectomy.

BACKGROUND: Addressing intraoperative bleeding remains a significant challenge in the field of robotic surgery. This research endeavors to pioneer a groundbreaking solution utilizing convolutional neural networks (CNNs). The objective is to establish a system capable of forecasting instances of intraoperative bleeding during robot-assisted radical prostatectomy (RARP) and promptly notify the surgeon about bleeding risks. METHODS: To achieve this, a multi-task learning (MTL) CNN was introduced, leveraging a modified version of the U-Net architecture. The aim was to categorize video input as either "absence of blood accumulation" (0) or "presence of blood accumulation" (1). To facilitate seamless interaction with the neural networks, the Bleeding Artificial Intelligence-based Detector (BLAIR) software was created using the Python Keras API and built upon the PyQT framework. A subsequent clinical assessment of BLAIR's efficacy was performed, comparing its bleeding identification performance against that of a urologist. Various perioperative variables were also gathered. For optimal MTL-CNN training parameterization, a multi-task loss function was adopted to enhance the accuracy of event detection by taking advantage of surgical tools' semantic segmentation. Additionally, the Multiple Correspondence Analysis (MCA) approach was employed to assess software performance. RESULTS: The MTL-CNN demonstrated a remarkable event recognition accuracy of 90.63%. When evaluating BLAIR's predictive ability and its capacity to pre-warn surgeons of potential bleeding incidents, the density plot highlighted a striking similarity between BLAIR and human assessments. In fact, BLAIR exhibited a faster response. Notably, the MCA analysis revealed no discernible distinction between the software and human performance in accurately identifying instances of bleeding. CONCLUSION: The BLAIR software proved its competence by achieving over 90% accuracy in predicting bleeding events during RARP. This accomplishment underscores the potential of AI to assist surgeons during interventions. This study exemplifies the positive impact AI applications can have on surgical procedures.