Robotic data acquisition with deep learning enables cell image-based prediction of transcriptomic phenotypes.

Single-cell whole-transcriptome analysis is the gold standard approach to identifying molecularly defined cell phenotypes. However, this approach cannot be used for dynamics measurements such as live-cell imaging. Here, we developed a multifunctional robot, the automated live imaging and cell picking system (ALPS) and used it to perform single-cell RNA sequencing for microscopically observed cells with multiple imaging modes. Using robotically obtained data that linked cell images and the whole transcriptome, we successfully predicted transcriptome-defined cell phenotypes in a noninvasive manner using cell image-based deep learning. This noninvasive approach opens a window to determine the live-cell whole transcriptome in real time. Moreover, this work, which is based on a data-driven approach, is a proof of concept for determining the transcriptome-defined phenotypes (i.e., not relying on specific genes) of any cell from cell images using a model trained on linked datasets.

Medical Microrobots.

Scientists around the world have long aimed to produce miniature robots that can be controlled inside the human body to aid doctors in identifying and treating diseases. Such microrobots hold the potential to access hard-to-reach areas of the body through the natural lumina. Wireless access has the potential to overcome drawbacks of systemic therapy, as well as to enable completely new minimally invasive procedures. The aim of this review is fourfold: first, to provide a collection of valuable anatomical and physiological information on the target working environments together with engineering tools for the design of medical microrobots; second, to provide a comprehensive updated survey of the technological state of the art in relevant classes of medical microrobots; third, to analyze currently available tracking and closed-loop control strategies compatible with the in-body environment; and fourth, to explore the challenges still in place, to steer and inspire future research.

Ten-year functional and oncological outcomes of a prospective randomized controlled trial comparing laparoscopic versus robot-assisted radical prostatectomy.

BACKGROUND: Among prostate cancer (PCa) treatment options, mini-invasive surgical approaches have gained a wide diffusion in the last decades. The aim of this study was to present oncological, functional, and quality of life data after 10 years of follow-up of a prospective randomized controlled trial (RCT) (ISRCTN11552140) comparing robot-assisted radical prostatectomy (RARP) versus laparoscopic radical prostatectomy (LRP) for the treatment of PCa. METHODS: Patients with localized PCa were randomized to undergo LRP or RARP between January 2010 and January 2011. Functional (continence and potency) and oncological (prostate-specific antigen, biochemical recurrence [BCR] and BCR-free survival [BCRFS]) variables were evaluated. BCRFS curves were estimated by the Kaplan-Meier method and compared using the log-rank test. Machine learning partial least square-discriminant analysis (PLS-DA) was used to identify the variables characterizing more the patients who underwent RARP or LRP. RESULTS: Seventy-five of the originally enrolled 120 patients remained on follow-up for 10 years; 40 (53%) underwent RARP and 35 (47%) LRP. Continence and potency recovery rates did not show significant differences (p = 0.068 and p = 0.56, respectively), despite a Δ12% for continence and Δ8% for potency in favor of the robotic approach. However, the quality of continence (in terms of International Consultation on Incontinence Questionnaire-Short Form [ICIQ-SF] score) and erection (in terms of International Index of Erectile Function-5 [IIEF-5] score) was significantly better after 10 years in the robotic group (p = 0.02 and p < 0.001). PLS-DA revealed that LRP was characterized by the worst functional-related outcomes analyzing the entire follow-up period. Four (10%) and six (17%) patients experienced BCR in RARP and LRP groups, respectively (p = 0.36), with an overall 10-year BCR-free survival of 88% and 78% (p = 0.16). CONCLUSIONS: Comparable continence and potency rates were observed between RARP and LRP after a 10-year follow-up. However, the RARP group exhibited superior totally dry rate and erection quality. No difference in terms of oncological outcomes was found.

Single-center retrospective assessment of robotic-assisted simultaneous pancreas-kidney transplants: Exploring clinical utility.

The diabetic population is witnessing a rise in obesity rates, creating specific hurdles for individuals seeking pancreas transplantation because they are frequently disqualified due to their elevated body weight. Introducing a robotic-assisted approach to transplantation has been proven to yield improved outcomes, particularly in patients with obesity. A retrospective analysis was conducted between January 2015 and September 2023. The study included a total of 140 patients, with 16 receiving robotic-assisted simultaneous pancreas-kidney transplantation (RSPK) and 124 undergoing open approach simultaneous pancreas-kidney transplantation (OSPK) during the study period. The median age was 45 (36.8-52.7) and 44.5 years (36.8-51.8) (RSPK vs OSPK, P = .487). There were no significant differences in demographics except body mass index (RSPK vs OSPK, 34.9 vs 28.1, P < .001) and a higher percentage of patients with high cardiac risk in the RSPK group. The robotic approach has a lengthier overall operative time and warm ischemia time. Surgical and nonsurgical complications at 30-days and 1-year grafts and patient survival (93.8% vs 96.8%, RSPK vs OSPK, P = .521) were similar. Our findings suggest that employing robotic assistance in simultaneous pancreas-kidney transplantation is safe. Wider adoption and utilization of this technique could potentially improve transplant accessibility for individuals with obesity and diabetes.

Privacy-proof Live Surgery Streaming: Development and Validation of a Low-cost, Real-time Robotic Surgery Anonymization Algorithm.

OBJECTIVE: Develop a pioneer surgical anonymization algorithm for reliable and accurate real-time removal of out-of-body images validated across various robotic platforms. BACKGROUND: The use of surgical video data has become a common practice in enhancing research and training. Video sharing requires complete anonymization, which, in the case of endoscopic surgery, entails the removal of all nonsurgical video frames where the endoscope can record the patient or operating room staff. To date, no openly available algorithmic solution for surgical anonymization offers reliable real-time anonymization for video streaming, which is also robotic-platform and procedure-independent. METHODS: A data set of 63 surgical videos of 6 procedures performed on four robotic systems was annotated for out-of-body sequences. The resulting 496.828 images were used to develop a deep learning algorithm that automatically detected out-of-body frames. Our solution was subsequently benchmarked against existing anonymization methods. In addition, we offer a postprocessing step to enhance the performance and test a low-cost setup for real-time anonymization during live surgery streaming. RESULTS: Framewise anonymization yielded a receiver operating characteristic area under the curve score of 99.46% on unseen procedures, increasing to 99.89% after postprocessing. Our Robotic Anonymization Network outperforms previous state-of-the-art algorithms, even on unseen procedural types, despite the fact that alternative solutions are explicitly trained using these procedures. CONCLUSIONS: Our deep learning model, Robotic Anonymization Network, offers reliable, accurate, and safe real-time anonymization during complex and lengthy surgical procedures regardless of the robotic platform. The model can be used in real time for surgical live streaming and is openly available.

Short-term Outcomes of Robotic Versus Open Pancreatoduodenectomy: Propensity Score-matched Analysis.

OBJECTIVE: The goal of the current study was to investigate the perioperative outcomes of robotic pancreaticoduodenectomy (RPD) and open pancreaticoduodenectomy (OPD) in a high-volume center. BACKGROUND: Despite RPDs prospective advantages over OPD, current evidence comparing the 2 has been limited and has prompted further investigation. The aim of this study was to compare both approaches while including the learning curve phase for RPD. METHODS: A 1:1 propensity score-matched analysis of a prospective database of RPD with OPD (2017-2022) at a high-volume center was performed. The main outcomes were overall- and pancreas-specific complications. RESULTS: Of 375 patients who underwent PD (OPD n=276; RPD n=99), 180 were included in propensity score-matched analysis (90 per group). RPD was associated with less blood loss [500 (300-800) vs 750 (400-1000) mL; P =0.006] and more patients without a complication (50% vs 19%; P <0.001). Operative time was longer [453 (408-529) vs 306 (247-362) min; P <0.001]; in patients with ductal adenocarcinoma, fewer lymph nodes were harvested [24 (18-27) vs 33 (27-39); P <0.001] with RPD versus OPD. There were no significant differences for major complications (38% vs 47%; P =0.291), reoperation rate (14% vs 10%; P =0.495), postoperative pancreatic fistula (21% vs 23%; P =0.858), and patients with the textbook outcome (62% vs 55%; P =0.452). CONCLUSIONS: Including the learning phase, RPD can be safely implemented in high-volume settings and shows potential for improved perioperative outcomes versus OPD. Pancreas-specific morbidity was unaffected by the robotic approach. Randomized trials with specifically trained pancreatic surgeons and expanded indications for the robotic approach are needed.

Nationwide use and Outcome of Minimally Invasive Distal Pancreatectomy in IDEAL Stage IV following a Training Program and Randomized Trial.

OBJECTIVE: To assess the nationwide long-term uptake and outcomes of minimally invasive distal pancreatectomy (MIDP) after a nationwide training program and randomized trial. BACKGROUND: Two randomized trials demonstrated the superiority of MIDP over open distal pancreatectomy (ODP) in terms of functional recovery and hospital stay. Data on implementation of MIDP on a nationwide level are lacking. METHODS: Nationwide audit-based study including consecutive patients after MIDP and ODP in 16 centers in the Dutch Pancreatic Cancer Audit (2014 to 2021). The cohort was divided into three periods: early implementation, during the LEOPARD randomized trial, and late implementation. Primary endpoints were MIDP implementation rate and textbook outcome. RESULTS: Overall, 1496 patients were included with 848 MIDP (56.5%) and 648 ODP (43.5%). From the early to the late implementation period, the use of MIDP increased from 48.6% to 63.0% and of robotic MIDP from 5.5% to 29.7% ( P <0.001). The overall use of MIDP (45% to 75%) and robotic MIDP (1% to 84%) varied widely between centers ( P <0.001). In the late implementation period, 5/16 centers performed >75% of procedures as MIDP. After MIDP, in-hospital mortality and textbook outcome remained stable over time. In the late implementation period, ODP was more often performed in ASA score III-IV (24.9% vs. 35.7%, P =0.001), pancreatic cancer (24.2% vs. 45.9%, P <0.001), vascular involvement (4.6% vs. 21.9%, P <0.001), and multivisceral involvement (10.5% vs. 25.3%, P <0.001). After MIDP, shorter hospital stay (median 7 vs. 8 d, P <0.001) and less blood loss (median 150 vs. 500 mL, P <0.001), but more grade B/C postoperative pancreatic fistula (24.4% vs. 17.2%, P =0.008) occurred as compared to ODP. CONCLUSION: A sustained nationwide implementation of MIDP after a successful training program and randomized trial was obtained with satisfactory outcomes. Future studies should assess the considerable variation in the use of MIDP between centers and, especially, robotic MIDP.

Comparison of Short-term and Three-year Oncological Outcomes Between Robotic and Laparoscopic Gastrectomy for Gastric Cancer: A Large Multicenter Cohort Study.

OBJECTIVE: To compare the short-term and long-term outcomes between robotic gastrectomy (RG) and laparoscopic gastrectomy (LG) for gastric cancer. BACKGROUND: The clinical outcomes of RG over LG have not yet been effectively demonstrated. METHODS: This retrospective cohort study included 3599 patients with gastric cancer who underwent radical gastrectomy at eight high-volume hospitals in China from January 2015 to June 2019. Propensity score matching was performed between patients who received RG and LG. The primary end point was 3-year disease-free survival (DFS). RESULTS: After 1:1 propensity score matching, 1034 pairs of patients were enrolled in a balanced cohort for further analysis. The 3-year DFS in the RG and LG was 83.7% and 83.1% ( P =0.745), respectively, and the 3-year overall survival was 85.2% and 84.4%, respectively ( P =0.647). During 3 years of follow-up, 154 patients in the RG and LG groups relapsed (cumulative incidence of recurrence: 15.0% vs 15.0%, P =0.988). There was no significant difference in the recurrence sites between the 2 groups (all P >0.05). Sensitivity analysis showed that RG had comparable 3-year DFS (77.4% vs 76.7%, P =0.745) and overall survival (79.7% vs 78.4%, P =0.577) to LG in patients with advanced (pathologic T2-4a) disease, and the recurrence pattern within 3 years was also similar between the 2 groups (all P >0.05). RG had less intraoperative blood loss, lower conversion rate, and shorter hospital stays than LG (all P >0.05). CONCLUSIONS: For resectable gastric cancer, including advanced cases, RG is a safe approach with comparable 3-year oncological outcomes to LG when performed by experienced surgeons.

Propensity Score-Matching Analysis Comparing Robotic Versus Laparoscopic Limited Liver Resections of the Posterosuperior Segments: An International Multicenter Study.

OBJECTIVE: The purpose of this study was to compare the outcomes of robotic limited liver resections (RLLR) versus laparoscopic limited liver resections (LLLR) of the posterosuperior segments. BACKGROUND: Both laparoscopic and robotic liver resections have been used for tumors in the posterosuperior liver segments. However, the comparative performance and safety of both approaches have not been well examined in the existing literature. METHODS: This is a post hoc analysis of a multicenter database of 5446 patients who underwent RLLR or LLLR of the posterosuperior segments (I, IVa, VII, and VIII) at 60 international centers between 2008 and 2021. Data on baseline demographics, center experience and volume, tumor features, and perioperative characteristics were collected and analyzed. Propensity score-matching (PSM) analysis (in both 1:1 and 1:2 ratios) was performed to minimize selection bias. RESULTS: A total of 3510 cases met the study criteria, of whom 3049 underwent LLLR (87%), and 461 underwent RLLR (13%). After PSM (1:1: and 1:2), RLLR was associated with a lower open conversion rate [10 of 449 (2.2%) vs 54 of 898 (6.0%); P =0.002], less blood loss [100 mL [IQR: 50-200) days vs 150 mL (IQR: 50-350); P <0.001] and a shorter operative time (188 min (IQR: 140-270) vs 222 min (IQR: 158-300); P <0.001]. These improved perioperative outcomes associated with RLLR were similarly seen in a subset analysis of patients with cirrhosis-lower open conversion rate [1 of 136 (0.7%) vs 17 of 272 (6.2%); P =0.009], less blood loss [100 mL (IQR: 48-200) vs 160 mL (IQR: 50-400); P <0.001], and shorter operative time [190 min (IQR: 141-258) vs 230 min (IQR: 160-312); P =0.003]. Postoperative outcomes in terms of readmission, morbidity and mortality were similar between RLLR and LLLR in both the overall PSM cohort and cirrhosis patient subset. CONCLUSIONS: RLLR for the posterosuperior segments was associated with superior perioperative outcomes in terms of decreased operative time, blood loss, and open conversion rate when compared with LLLR.

Robotic Versus Conventional or Endoscopic-assisted Nipple-sparing Mastectomy and Immediate Prosthesis Breast Reconstruction in the Management of Breast Cancer: A Prospectively Designed Multicenter Trial Comparing Clinical Outcomes, Medical Cost, and Patient-reported Outcomes (RCENSM-P).

OBJECTIVE: To compare the clinical and patient-reported outcomes of minimal access and conventional nipple-sparing mastectomy (C-NSM). The secondary outcomes investigated included medical costs and oncological safety. BACKGROUND: Minimal-access NSM has been increasingly applied in the treatment of patients with breast cancer. However, prospective multicenter trials comparing robotic-assisted NSM (R-NSM) versus C-NSM or endoscopic-assisted NSM (E-NSM) are lacking. METHODS: A prospectively designed 3-arm multicenter, nonrandomized trial (NCT04037852) was conducted from October 1, 2019 to December 31, 2021, to compare R-NSM with C-NSM or E-NSM. RESULTS: A total of 73 R-NSM, 74 C-NSM, and 84 E-NSM procedures were enrolled. The median wound length and operation time of C-NSM was (9 cm, 175 minutes), (4 cm, and 195 minutes) in R-NSM, and (4 cm and 222 minutes) in E-NSM. Complications were comparable among the groups. Better wound healing was observed in the minimal-access NSM group. The R-NSM procedure was 4000 and 2600 United States Dollars more expensive than C-NSM and E-NSM, respectively. Wound/scar and postoperative acute pain evaluation favored the use of minimal access NSM over C-NSM. Quality of life in terms of chronic breast/chest pain, mobility, and range of motion of the upper extremity showed no significant differences. The preliminary oncologic results showed no differences among the 3 groups. CONCLUSIONS: R-NSM or E-NSM is a safe alternative if compared with C-NSM in terms of perioperative morbidities, especially with better wound healing. The advantage of minimal access groups was higher wound-related satisfaction. Higher costs remain one of the major limiting factors in the widespread adoption of R-NSM.

Robotic Versus Laparoscopic Liver Resection in Various Settings: An International Multicenter Propensity Score Matched Study of 10.075 Patients.

OBJECTIVE: To compare the perioperative outcomes of robotic liver surgery (RLS) and laparoscopic liver surgery (LLS) in various settings. BACKGROUND: Clear advantages of RLS over LLS have rarely been demonstrated, and the associated costs of robotic surgery are generally higher than those of laparoscopic surgery. Therefore, the exact role of the robotic approach in minimally invasive liver surgery remains to be defined. METHODS: In this international retrospective cohort study, the outcomes of patients who underwent RLS and LLS for all indications between 2009 and 2021 in 34 hepatobiliary referral centers were compared. Subgroup analyses were performed to compare both approaches across several types of procedures: (1) minor resections in the anterolateral (2, 3, 4b, 5, and 6) or (2) posterosuperior segments (1, 4a, 7, 8), and (3) major resections (≥3 contiguous segments). Propensity score matching was used to mitigate the influence of selection bias. The primary outcome was textbook outcome in liver surgery (TOLS), previously defined as the absence of intraoperative incidents ≥grade 2, postoperative bile leak ≥grade B, severe morbidity, readmission, and 90-day or in-hospital mortality with the presence of an R0 resection margin in case of malignancy. The absence of a prolonged length of stay was added to define TOLS+. RESULTS: Among the 10.075 included patients, 1.507 underwent RLS and 8.568 LLS. After propensity score matching, both groups constituted 1.505 patients. RLS was associated with higher rates of TOLS (78.3% vs 71.8%, P < 0.001) and TOLS+ (55% vs 50.4%, P = 0.026), less Pringle usage (39.1% vs 47.1%, P < 0.001), blood loss (100 vs 200 milliliters, P < 0.001), transfusions (4.9% vs 7.9%, P = 0.003), conversions (2.7% vs 8.8%, P < 0.001), overall morbidity (19.3% vs 25.7%, P < 0.001), and microscopically irradical resection margins (10.1% vs. 13.8%, P = 0.015), and shorter operative times (190 vs 210 minutes, P = 0.015). In the subgroups, RLS tended to have higher TOLS rates, compared with LLS, for minor resections in the posterosuperior segments (n = 431 per group, 75.9% vs 71.2%, P = 0.184) and major resections (n = 321 per group, 72.9% vs 67.5%, P = 0.086), although these differences did not reach statistical significance. CONCLUSIONS: While both produce excellent outcomes, RLS might facilitate slightly higher TOLS rates than LLS.

Integrated Sensors for Soft Medical Robotics.

Minimally invasive procedures assisted by soft robots for surgery, diagnostics, and drug delivery have unprecedented benefits over traditional solutions from both patient and surgeon perspectives. However, the translation of such technology into commercialization remains challenging. The lack of perception abilities is one of the obstructive factors paramount for a safe, accurate and efficient robot-assisted intervention. Integrating different types of miniature sensors onto robotic end-effectors is a promising trend to compensate for the perceptual deficiencies in soft robots. For example, haptic feedback with force sensors helps surgeons to control the interaction force at the tool-tissue interface, impedance sensing of tissue electrical properties can be used for tumor detection. The last decade has witnessed significant progress in the development of multimodal sensors built on the advancement in engineering, material science and scalable micromachining technologies. This review article provides a snapshot on common types of integrated sensors for soft medical robots. It covers various sensing mechanisms, examples for practical and clinical applications, standard manufacturing processes, as well as insights on emerging engineering routes for the fabrication of novel and high-performing sensing devices.

Robotic-Assisted In-Bed Mobilization in Ventilated ICU Patients With COVID-19: An Interventional, Randomized, Controlled Pilot Study (ROBEM II Study).

OBJECTIVES: The COVID-19 pandemic significantly impacted global healthcare systems, particularly in managing critically ill mechanically ventilated patients. This study aims to assess the feasibility of robotic-assisted mobilization in COVID-19 patients. DESIGN: Randomized controlled pilot study. SETTING: Four COVID-19 specialized ICUs at Charité-Universitätsmedizin Berlin (March 2021 to February 2022). PATIENTS: Twenty critically ill COVID-19 patients expected to require greater than 24 hours of ventilation. INTERVENTIONS: A 5-day intervention phase with bid robotic-assisted mobilization greater than or equal to 20 minutes and follow-up at day 180, compared with standard care. MEASUREMENTS AND MAIN RESULTS: Intervention sessions were conducted in 98.9% according to protocol, with one session missing due to staff shortage. Primary outcome was the mobilization level measured with the ICU Mobility Scale (IMS) and Surgical ICU Optimal Mobilization Score (SOMS), assessed until day 5 or extubation. Safety events were recorded during mobilization. The median IMS and SOMS were 0 (0-0.16) and 1 (1-1.03) in the intervention group, and 0 (0-0.15) ( p = 0.77) and 0.8 (0.65-1.20) ( p = 0.08) in the standard care group, respectively. Significant secondary outcomes included average number of mobilization sessions (intervention: 8.5 [7.75-10] vs. standard care: 4.5 [3.5-5]; p = 0.001), total mobilization time (intervention: 232.5 min [187.25-266.5 min] vs. standard care: 147.5 min [107.5-167.5 min]; p = 0.011), and healthcare providers per session (intervention: 2 [2-2] vs. standard care: 1 [1-1.4]; p = 0.001) during intervention. Four safety events (hypertension and agitation, n = 2 each) in the intervention group and none in the standard care group were reported. CONCLUSIONS: Robotic-assisted mobilization in mechanically ventilated COVID-19 patients appears to be safe and feasible.

Robotic and laparoscopic right lobe living donation compared to the open approach: A multicenter study on 1194 donor hepatectomies.

Due to the success of minimally invasive liver surgery, laparoscopic and robotic minimally invasive donor hepatectomies (MIDH) are increasingly performed worldwide. We conducted a retrospective, multicentre, propensity score-matched analysis on right lobe MIDH by comparing the robotic, laparoscopic, and open approaches to assess the feasibility, safety, and early outcomes of MIDHs. From January 2016 until December 2020, 1194 donors underwent a right donor hepatectomy performed with a robotic (n = 92), laparoscopic (n = 306), and open approach (n = 796) at 6 high-volume centers. Donor and recipients were matched for different variables using propensity score matching (1:1:2). Donor outcomes were recorded, and postoperative pain was measured through a visual analog scale. Recipients' outcomes were also analyzed. Ninety-two donors undergoing robotic surgery were matched and compared to 92 and 184 donors undergoing laparoscopic and open surgery, respectively. Conversions to open surgery occurred during 1 (1.1%) robotic and 2 (2.2%) laparoscopic procedures. Robotic procedures had a longer operative time (493 ± 96 min) compared to laparoscopic and open procedures (347 ± 120 and 358 ± 95 min; p < 0.001) but were associated with reduced donor blood losses ( p < 0.001). No differences were observed in overall and major complications (≥ IIIa). Robotic hepatectomy donors had significantly less pain compared to the 2 other groups ( p < 0.001). Fifty recipients of robotic-procured grafts were matched to 50 and 100 recipients of laparoscopic and open surgery procured grafts, respectively. No differences were observed in terms of postoperative complications, and recipients' survival was similar ( p =0.455). In very few high-volume centers, robotic right lobe procurement has shown to be a safe procedure. Despite an increased operative and the first warm ischemia times, this approach is associated with reduced intraoperative blood losses and pain compared to the laparoscopic and open approaches. Further data are needed to confirm it as a valuable option for the laparoscopic approach in MIDH.

Automated Identification of Key Steps in Robotic-Assisted Radical Prostatectomy Using Artificial Intelligence.

PURPOSE: The widespread use of minimally invasive surgery generates vast amounts of potentially useful data in the form of surgical video. However, raw video footage is often unstructured and unlabeled, thereby limiting its use. We developed a novel computer-vision algorithm for automated identification and labeling of surgical steps during robotic-assisted radical prostatectomy (RARP). MATERIALS AND METHODS: Surgical videos from RARP were manually annotated by a team of image annotators under the supervision of 2 urologic oncologists. Full-length surgical videos were labeled to identify all steps of surgery. These manually annotated videos were then utilized to train a computer vision algorithm to perform automated video annotation of RARP surgical video. Accuracy of automated video annotation was determined by comparing to manual human annotations as the reference standard. RESULTS: A total of 474 full-length RARP videos (median 149 minutes; IQR 81 minutes) were manually annotated with surgical steps. Of these, 292 cases served as a training dataset for algorithm development, 69 cases were used for internal validation, and 113 were used as a separate testing cohort for evaluating algorithm accuracy. Concordance between artificial intelligence‒enabled automated video analysis and manual human video annotation was 92.8%. Algorithm accuracy was highest for the vesicourethral anastomosis step (97.3%) and lowest for the final inspection and extraction step (76.8%). CONCLUSIONS: We developed a fully automated artificial intelligence tool for annotation of RARP surgical video. Automated surgical video analysis has immediate practical applications in surgeon video review, surgical training and education, quality and safety benchmarking, medical billing and documentation, and operating room logistics.

Conversion to Radical Nephrectomy From Robotic Partial Nephrectomy Is Most Commonly Due to Anatomic and Oncologic Complexity.

PURPOSE: Partial nephrectomy is standard-of-care treatment for small renal masses. As utilization of partial nephrectomy increases and includes larger and complex tumors, the risk of conversion to radical nephrectomy likely increases. We evaluated incidence and reason for conversion to radical nephrectomy in patients scheduled for partial nephrectomy by surgeons participating in MUSIC (the Michigan Urologic Surgery Improvement Collaborative). MATERIALS AND METHODS: All patients in whom robotic partial nephrectomy was planned were stratified by completed procedure (robotic partial nephrectomy vs radical nephrectomy). Preoperative and intraoperative records were reviewed for preoperative assessment of difficulty and reason for conversion. Patient, tumor, pathologic, and practice variables were compared between cohorts. RESULTS: Of 650 patients scheduled for robotic partial nephrectomy, conversion to radical nephrectomy occurred in 27 (4.2%) patients. No conversions to open were reported. Preoperative documentation indicated a plan for possible conversion in 18 (67%) patients including partial with possible radical (n = 8), partial vs radical (n = 6), or likely radical nephrectomy (n = 4). Intraoperative documentation indicated that only 5 (19%) conversions were secondary to bleeding, with the remaining conversions due to tumor complexity and/or oncologic concerns. Patients undergoing conversion had larger (4.7 vs 2.8 cm, P < .001) and higher-complexity tumors (64% vs 6%, P < .001) with R.E.N.A.L. (for radius, exophytic/endophytic, nearness of tumor to collecting system, anterior/posterior, location relative to polar line) nephrometry score ≥ 10. The converted cases had a higher rate of ≥ pT3 (27% vs 8.4%, P = .008). CONCLUSIONS: There was a low rate of conversion from robotic partial to radical nephrectomy in the MUSIC-KIDNEY (Kidney mass: Identifying and Defining Necessary Evaluation and therapY) collaborative, and an even lower risk of conversion due to uncontrolled bleeding. Targeted review of each conversion identified appropriate decision-making based on oncologic risk in most cases.

Perioperative, Oncological, and Functional Outcomes Between Robot-Assisted Laparoscopic Prostatectomy and Open Radical Retropubic Prostatectomy: A Randomized Clinical Trial.

PURPOSE: Limited high-quality studies have compared robot-assisted laparoscopic prostatectomy (RALP) vs open retropubic radical prostatectomy. We sought to compare their postoperative outcomes in a randomized setting. MATERIALS AND METHODS: In a single center, 354 men with newly diagnosed prostate cancer were assessed for eligibility; 342 were randomized (1:1). The primary outcome was 90-day complication rates. Functional outcomes and quality of life were assessed over 18 months, and oncological outcomes, biochemical recurrence-free survival, and additional treatment over 36 months. RESULTS: From 2014 to 18, 327 patients underwent surgery (retropubic radical prostatectomy = 156, RALP = 171). Complications occurred in 27 (17.3%) vs 19 (11.1%; P = .107). Patients undergoing RALP experienced lower median bleeding (250.0 vs 719.5 mL; P < .001) and shorter hospitalization time. Urinary EPIC (Expanded Prostate Cancer Index Composite) median scores were better for RALP over 18 months, with higher continence rate at 3 months (80.5% vs 64.7%; P = .002), 6 months (90.1% vs 81.6%; P = .036) and 18 months (95.4% vs 78.8%; P < .001). Sexual EPIC and Sexual Health Inventory for Men median scores were higher with RALP up to 12 months, while the potency rate was superior at 3 months (23.9% vs 5.3%; P = .001) and 6 months (30.6% vs 6.9%; P < .001). Quality of life over the 18 months and oncological outcomes over 36 months were not significantly different between arms. CONCLUSIONS: Complications at 90 days were similar. RALP showed superior sexual outcomes at 1 year, improved urinary outcomes at 18 months, and comparable oncological outcomes at 36 months. TRIAL REGISTRATION: Prospective Analysis of Robot-Assisted Surgery; NCT02292914. https://clinicaltrials.gov/ct2/show/NCT02292914?cond=NCT02292914&draw=2&rank=1.

Prognostic Importance of Lymphovascular Invasion for Specific Subgroup of Patients with Prostate Cancer After Robot-Assisted Radical Prostatectomy (The MSUG94 Group).

OBJECTIVE: This study aimed to investigate whether lymphovascular invasion (LVI) was associated with oncological outcomes in patients with prostate cancer (PCa) undergoing robotic-assisted radical prostatectomy (RARP). METHODS: This retrospective multicenter cohort study was conducted on 3195 patients with PCa who underwent RARP in nine institutions in Japan. The primary endpoints were the associations between biochemical recurrence (BCR) and LVI and between BCR and clinicopathological covariates, while the secondary endpoints were the association between LVI and the site of clinical recurrence and metastasis-free survival (MFS). RESULTS: In total, 2608 patients met the inclusion criteria. At the end of the follow-up period, 311 patients (11.9%) were diagnosed with BCR and none died of PCa. In patients with pathological stage T2 (pT2) + negative resection margins (RM-), and pT3+ positive RM (RM+), LVI significantly worsened BCR-free survival (BRFS). For patients with PCa who had pT3 and RM+, the 2-year BRFS rate in those with LVI was significantly worse than in those without LVI. Patients with LVI had significantly worse MFS than those without LVI with respect to pT3, RM+, and pathological Gleason grade (pGG). In multivariate analysis, LVI was significantly associated with BRFS in patients with pT3 PCa, and with worse MFS in PCa patients with pT3, RM+, and pGG ≥ 4. CONCLUSIONS: LVI was an independent prognostic factor for recurrence and metastasis after RARP, particularly in patients with pT3 and RM+ PCa. Locally advanced PCa with positive LVI and RM+ requires careful follow-up because of the high likelihood of recurrence.

ASO Author Reflections: The Role of Robotic Surgery on Central Pancreatectomy.

Central pancreatectomy (CP) is indicated for benign or low-grade pancreatic tumors located in the neck or proximal pancreatic body. This procedure is demanding and has a high rate of postoperative complications. Minimally invasive surgery is now commonly used for CP but it is still unclear whether the robotic approach offers any advantages over conventional pancreatic minimally invasive surgery. Most studies on robotic CP are limited to case reports or case series; however, there are two important studies on this topic. Currently, the evidence on robotic CP remains limited, making it challenging to draw definitive conclusions in favor of one technique over the other. The use of a robotic platform, with its integrated tools such as intraoperative ultrasound, can guide the surgeon in performing this technically demanding procedure in a safer manner. The controversy regarding the best minimally invasive surgery approach for CP is still ongoing and requires further research.

Robotic Pancreatoduodenectomy in Portal Annular Pancreas Using a Hanging Maneuver with Indocyanine Green Fluorescence Imaging.

BACKGROUND: Sufficient knowledge and surgical management of portal annular pancreas (PAP) are essential for pancreatic surgery. As PAP is a relatively rare pancreatic anomaly, few studies have described surgical techniques for patients with PAP undergoing robotic pancreatoduodenectomy (RPD). PATIENTS AND METHODS: An 82-year-old female patient who underwent RPD presented with distal cholangiocarcinoma and type III PAP (the fusion of the uncinate process with the anteportal main pancreatic duct). After the Kocher maneuver and stomach transection, the pancreas was transected into the neck of the anteportal portion. The retroportal portion was dissected, encircled with hanging tape, and compressed. Blood supply from the mesenteric vessels was confirmed using indocyanine green (ICG) fluorescence imaging. Subsequently, the retroportal portion was stapled. CONCLUSIONS: This study demonstrates a unique surgical technique for type III PAP using the hanging maneuver with ICG fluorescence imaging. Surgeons should decide on the surgical strategy on the basis of the fusion and ductal anatomy of the pancreas.