Retzius-sparing versus standard robot-assisted laparoscopic prostatectomy for the treatment of clinically localized prostate cancer.

OBJECTIVES: To assess the effects of Retzius-sparing (RS) robotic-assisted laparoscopic prostatectomy (RALP) compared to standard RALP for the treatment of clinically localized prostate cancer. METHODS: We performed a systematic search of multiple databases and the grey literature with no restrictions on the language of publication or publication status, up until June 2020. We included randomized controlled trials (RCTs) comparing RS-RALP with standard RALP. We performed a meta-analysis using a random-effect model. The quality of evidence was assessed on an outcome basis according to the Grades of Recommendation, Assessment, Development and Evaluation (GRADE) approach. RESULTS: Our search identified six records of five unique RCTs, of which two were published studies, one was in press, and two were abstract proceedings. There were 571 randomized participants, of whom 502 completed the trials. The mean age of participants was 64.6 years and the mean prostate-specific antigen level was 6.9 ng/mL. Approximately 54.2% of participants had cT1c disease, 38.6% had cT2a-b disease, and 7.1% had cT2c disease. RS-RALP probably improves continence within 1 week after catheter removal (risk ratio [RR] 1.74, 95% confidence interval [CI] 1.41-2.14; I2 = 0%; studies = 4; participants = 410; moderate-certainty evidence). Assuming 335 per 1000 men undergoing standard RALP are continent at this time point, this corresponds to 248 more men per 1000 (137 more to 382 more) reporting continence recovery. RS-RALP may increase continence at 3 months after surgery compared to standard RALP (RR 1.33, 95% CI 1.06-1.68; I2 = 86%; studies = 5; participants = 526; low-certainty evidence). Assuming 750 per 1000 men undergoing standard RALP are continent at this time point, this corresponds to 224 more men per 1000 (41 more to 462 more) reporting continence recovery. We are very uncertain about the effects of RS-RALP on serious adverse events compared to standard RALP (RR 1.40, 95% CI 0.47-4.17; studies = 2; participants = 230; very low-certainty evidence). CONCLUSIONS: The findings of this review indicate that RS-RALP may result in better continence outcomes than standard RALP up to 6 months after surgery. Continence outcomes at 12 months may be similar. The disadvantages of RS-RALP may be higher positive surgical margin rates. We are very uncertain about the effect on biochemical recurrence-free survival and potency outcomes. Longer-term oncological and functional outcomes are lacking, and no preplanned subgroup analyses could be performed to explore the observed heterogeneity. Surgeons should discuss these trade-offs and the limitations of the evidence with their patients when considering this approach.

Retzius-sparing versus standard robotic-assisted laparoscopic prostatectomy for the treatment of clinically localized prostate cancer.

BACKGROUND: Robotic-assisted laparoscopic prostatectomy (RALP) is widely used to surgically treat clinically localized prostate cancer. It is typically performed using an approach (standard RALP) that mimics open retropubic prostatectomy by dissecting the so-called space of Retzius anterior to the bladder. An alternative, Retzius-sparing (or posterior approach) RALP (RS-RALP) has been described, which is reported to have better continence outcomes but may be associated with a higher risk of incomplete resection and positive surgical margins (PSM). OBJECTIVES: To assess the effects of RS-RALP compared to standard RALP for the treatment of clinically localized prostate cancer. SEARCH METHODS: We performed a comprehensive search of the Cochrane Library, MEDLINE, Embase, three other databases, trials registries, other sources of the grey literature, and conference proceedings, up to June 2020. We applied no restrictions on publication language or status. SELECTION CRITERIA: We included trials where participants were randomized to RS-RALP or standard RALP for clinically localized prostate cancer. DATA COLLECTION AND ANALYSIS: Two review authors independently classified and abstracted data from the included studies. Primary outcomes were: urinary continence recovery within one week after catheter removal, at three months after surgery, and serious adverse events. Secondary outcomes were: urinary continence recovery six and 12 months after surgery, potency recovery 12 months after surgery, positive surgical margins (PSM), biochemical recurrence-free survival (BCRFS), and urinary and sexual function quality of life. We performed statistical analyses using a random-effects model. We rated the certainty of evidence using the GRADE approach. MAIN RESULTS: Our search identified six records of five unique randomized controlled trials, of which two were published studies, one was in press, and two were abstract proceedings. There were 571 randomized participants, of whom 502 completed the trials. Mean age of participants was 64.6 years and mean prostate-specific antigen was 6.9 ng/mL. About 54.2% of participants had cT1c disease, 38.6% had cT2a-b disease, and 7.1 % had cT2c disease. Primary outcomes RS-RALP probably improves continence within one week after catheter removal (risk ratio (RR) 1.74, 95% confidence interval (CI) 1.41 to 2.14; I2 = 0%; studies = 4; participants = 410; moderate-certainty evidence). Assuming 335 per 1000 men undergoing standard RALP are continent at this time point, this corresponds to 248 more men per 1000 (137 more to 382 more) reporting continence recovery. RS-RALP may increase continence at three months after surgery compared to standard RALP (RR 1.33, 95% CI 1.06 to 1.68; I2 = 86%; studies = 5; participants = 526; low-certainty evidence). Assuming 750 per 1000 men undergoing standard RALP are continent at this time point, this corresponds to 224 more men per 1000 (41 more to 462 more) reporting continence recovery. We are very uncertain about the effects of RS-RALP on serious adverse events compared to standard RALP (RR 1.40, 95% CI 0.47 to 4.17; studies = 2; participants = 230; very low-certainty evidence). Secondary outcomes There is probably little to no difference in continence recovery at 12 months after surgery (RR 1.01, 95% CI 0.97 to 1.04; I2 = 0%; studies = 2; participants = 222; moderate-certainty evidence). Assuming 982 per 1000 men undergoing standard RALP are continent at this time point, this corresponds to 10 more men per 1000 (29 fewer to 39 more) reporting continence recovery.  We are very uncertain about the effect of RS-RALP on potency recovery 12 months after surgery (RR 0.98, 95% CI 0.54 to 1.80; studies = 1; participants = 55; very low-certainty evidence).  RS-RALP may increase PSMs (RR 1.95, 95% CI 1.19 to 3.20; I2 = 0%; studies = 3; participants = 308; low-certainty evidence) indicating a higher risk for prostate cancer recurrence. Assuming 129 per 1000 men undergoing standard RALP have positive margins, this corresponds to 123 more men per 1000 (25 more to 284 more) with PSMs. We are very uncertain about the effect of RS-RALP on BCRFS compared to standard RALP (hazard ratio (HR) 0.45, 95% CI 0.13 to 1.60; I2 = 32%; studies = 2; participants = 218; very low-certainty evidence). AUTHORS' CONCLUSIONS: Findings of this review indicate that RS-RALP may result in better continence outcomes than standard RALP up to six months after surgery. Continence outcomes at 12 months may be similar. Downsides of RS-RALP may be higher positive margin rates. We are very uncertain about the effect on BCRFS and potency outcomes. Longer-term oncologic and functional outcomes are lacking, and no preplanned subgroup analyses could be performed to explore the observed heterogeneity. Surgeons should discuss these trade-offs and the limitations of the evidence with their patients when considering this approach.

Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge.

Purpose: Clinicians rely on imaging features to calculate complexity of renal masses based on validated scoring systems. These scoring methods are labor-intensive and are subjected to interobserver variability. Artificial intelligence has been increasingly utilized by the medical community to solve such issues. However, developing reliable algorithms is usually time-consuming and costly. We created an international community-driven competition (KiTS19) to develop and identify the best system for automatic segmentation of kidneys and kidney tumors in contrast CT and report the results. Methods: A training and test set of CT scans that was manually annotated by trained individuals were generated from consecutive patients undergoing renal surgery for whom demographic, clinical and outcome data were available. The KiTS19 Challenge was a machine learning competition hosted on grand-challenge.org in conjunction with an international conference. Teams were given 3 months to develop their algorithm using a full-annotated training set of images and an unannotated test set was released for 2 weeks from which average Sørensen-Dice coefficient between kidney and tumor regions were calculated across all 90 test cases. Results: There were 100 valid submissions that were based on deep neural networks but there were differences in pre-processing strategies, architectural details, and training procedures. The winning team scored a 0.974 kidney Dice and a 0.851 tumor Dice resulting in 0.912 composite score. Automatic segmentation of the kidney by the participating teams performed comparably to expert manual segmentation but was less reliable when segmenting the tumor. Conclusion: Rapid advancement in automated semantic segmentation of kidney lesions is possible with relatively high accuracy when the data is released publicly, and participation is incentivized. We hope that our findings will encourage further research that would enable the potential of adopting AI into the medical field.

The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge.

There is a large body of literature linking anatomic and geometric characteristics of kidney tumors to perioperative and oncologic outcomes. Semantic segmentation of these tumors and their host kidneys is a promising tool for quantitatively characterizing these lesions, but its adoption is limited due to the manual effort required to produce high-quality 3D segmentations of these structures. Recently, methods based on deep learning have shown excellent results in automatic 3D segmentation, but they require large datasets for training, and there remains little consensus on which methods perform best. The 2019 Kidney and Kidney Tumor Segmentation challenge (KiTS19) was a competition held in conjunction with the 2019 International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI) which sought to address these issues and stimulate progress on this automatic segmentation problem. A training set of 210 cross sectional CT images with kidney tumors was publicly released with corresponding semantic segmentation masks. 106 teams from five continents used this data to develop automated systems to predict the true segmentation masks on a test set of 90 CT images for which the corresponding ground truth segmentations were kept private. These predictions were scored and ranked according to their average Sørensen-Dice coefficient between the kidney and tumor across all 90 cases. The winning team achieved a Dice of 0.974 for kidney and 0.851 for tumor, approaching the inter-annotator performance on kidney (0.983) but falling short on tumor (0.923). This challenge has now entered an "open leaderboard" phase where it serves as a challenging benchmark in 3D semantic segmentation.

Public Perceptions of Artificial Intelligence and Robotics in Medicine.

Objective: To understand better the public perception and comprehension of medical technology such as artificial intelligence (AI) and robotic surgery. In addition to this, to identify sensitivity to their use to ensure acceptability and quality of counseling. Subjects and Methods: A survey was conducted on a convenience sample of visitors to the MN Minnesota State Fair (n = 264). Participants were randomized to receive one of two similar surveys. In the first, a diagnosis was made by a physician and in the second by an AI application to compare confidence in human and computer-based diagnosis. Results: The median age of participants was 45 (interquartile range 28-59), 58% were female (n = 154) vs 42% male (n = 110), 69% had completed at least a bachelor's degree, 88% were Caucasian (n = 233) vs 12% ethnic minorities (n = 31) and were from 12 states, mostly from the Upper Midwest. Participants had nearly equal trust in AI vs physician diagnoses. However, they were significantly more likely to trust an AI diagnosis of cancer over a doctor's diagnosis when responding to the version of the survey that suggested that an AI could make medical diagnoses (p = 9.32e-06). Though 55% of respondents (n = 145) reported that they were uncomfortable with automated robotic surgery, the majority of the individuals surveyed (88%) mistakenly believed that partially autonomous surgery was already happening. Almost all (94%, n = 249) stated that they would be willing to pay for a review of medical imaging by an AI if available. Conclusion: Most participants express confidence in AI providing medical diagnoses, sometimes even over human physicians. Participants generally express concern with surgical AI, but they mistakenly believe that it is already being performed. As AI applications increase in medical practice, health care providers should be cognizant of the potential amount of misinformation and sensitivity that patients have to how such technology is represented.