Validation of Ideal Breast Characteristics With Breast Augmentation Patients.

Background: Breast augmentation procedures are one of the most commonly performed aesthetic procedures in the United States. Little work has focused on the general public's overall perception of the ideal breast or has validated them with patient photographs. Objectives: To validate crowdsourced perceptions of breasts with their alignment to the aesthetics of breast augmentation patients. Methods: A prospective cross-sectional study was performed using participants enrolled through the AmazonMechanical Turk crowdsourcing platform (Amazon Web Services, Amazon, Seattle, WA) to obtain participant opinions ofhow closely patient breasts aligned with previously obtained results of 4 ideal breast characteristics. Outcomes were reported based on the correlation between breast attractiveness and alignment to ideal breast characteristics, both before and after breast implant procedures. Results: 2306 responses from 737 participants reported patient photograph alignment with ideal breast projection proportion (1.0) as having the highest correlation to opinions of heightened aesthetic beauty (R = 0.98, P < 0.001), and ideal nipple direction (front) as having the lowest correlation to aesthetic beauty (R = 0.90, P < 0.001). Younger age groups (18-24) and participants with a high school diploma or less rated patients as less attractive, while married and wealthy individuals reported higher attraction levels. Conclusions: Crowdsourcing can be a useful tool for aesthetic surgery preferences and has helped reveal key takeaways. The importance of the 4 breast characteristics has been validated, with alignment to all 4 characteristics tested having a high correlation to preferences. Differences in preference across demographic groups are a topic to further investigate.

Public Perception of Ideal Breast Shape.

BACKGROUND: In the past decade, there has been a dramatic increase in trends related to body-shaping procedures. According to the American Society of Plastic Surgeons, nearly 300,000 breast augmentation procedures were conducted in 2019. Learning the ideal shape of a breast and which esthetics lead to public perception of the most attractive breast is beneficial to properly performing these procedures. OBJECTIVES: The authors aimed to quantify the public's perception of attraction to breast shape by measuring public opinion for various esthetic elements of breast anatomy and linking this to various demographic factors. METHODS: Survey responses were collected from 1000 users of Amazon Mechanical Turk to collect demographic data and ask users to rank preferences for randomized image panels of breast proportions. RESULTS: 960 responses were used for analysis. A majority of respondents were male (60%), with a plurality being 25 to 34 years old (49.3%). The most notable preferences between all groups were breast projection proportion and nipple direction, with preferences of 1.0 and frontal nipple direction, respectively. Breast width to shoulder width ratio also had a clear preference among the crowd, with 105% being the preferred percentage, and the 25 to 34 age group having a very strong preference for this. CONCLUSIONS: The authors used a crowdsourcing survey technique with randomized image panels to analyze ideal breast preference using images of various anatomical traits of the female breast. It was concluded that crowdsourcing can be a favorable technique for learning ideal overall preferences for specific anatomy.

Virtual Reality Warm-up Before Robot-assisted Surgery: A Randomized Controlled Trial.

TRIAL DESIGN: This was a randomized controlled trial. BACKGROUND: Intraoperative errors correlate with surgeon skill and skill declines with intervals of inactivity. The goals of this research were to identify the optimal virtual reality (VR) warm-up curriculum to prime a surgeon's technical skill and validate benefit in the operating room. MATERIALS AND METHODS: Surgeons were randomized to receive six trial sessions of a designated set of VR modules on the da Vinci Skills Simulator to identify optimal VR warm-up curricula to prime technical skill. After performing their curricula, warm-up effect was assessed based on performance on a criterion task. The optimal warm-up curriculum was chosen from the group with the best task time and video review-based technical skill. Robot-assisted surgery-experienced surgeons were then recruited to either receive or not receive warm-up before surgery. Skill in the first 15 min of surgery was assessed by blinded surgeon and crowdworker review as well as tool motion metrics. The intervention was performing VR warm-up before human robot-assisted surgery. Warm-up effect was measured using objective performance metrics and video review using the Global Evaluative Assessment of Robotic Skills tool. Linear mixed effects models with a random intercept for each surgeon and nonparametric modified Friedman tests were used for analysis. RESULTS: The group performing only a Running Suture task on the simulator was on average 31.3 s faster than groups performing other simulation tasks and had the highest Global Evaluative Assessment of Robotic Skills scores from 41 surgeons who participated. This was chosen as the optimal curriculum. Thereafter, 34 surgeons completed 347 surgeries with corresponding video and tool motion data. No statistically significant differences in skill were observed with the warm-up intervention. CONCLUSIONS: We conclude that a robotic VR warm-up before performing the early stages of surgery does not impact the technical skill of the surgeon.

Crowd-Sourced Reliability of an Assessment of Lower Facial Aging Using a Validated Visual Scale.

Reliable and valid assessments of the visual endpoints of aesthetic surgery procedures are needed. Currently, most assessments are based on the opinion of patients and their plastic surgeons. The objective of this research was to analyze the reliability of crowdworkers assessing de-identified photographs using a validated scale that depicts lower facial aging. METHODS: Twenty photographs of the facial nasolabial region of various non-identifiable faces were obtained for which various degrees of facial aging were present. Independent crowds of 100 crowd workers were tasked with assessing the degree of aging using a photograph numeric scale. Independent groups of crowdworkers were surveyed at 4 different times (weekday daytime, weekday nighttime, weekend daytime, weekend nighttime), once a week for 2 weeks. RESULTS: Crowds assessing midface region photographs had an overall correlation of R = 0.979 (weekday daytime R = 0.991; weekday nighttime R = 0.985; weekend daytime R = 0.997; weekend nighttime R = 0.985). Bland-Altman test for test-retest agreement showed a normal distribution of assessments over the various times tested, with the differences in the majority of photographs being within 1 SD of the average difference in ratings. CONCLUSIONS: Crowd assessments of facial aging in de-identified photographs displayed very strong concordance with each other, regardless of time of day or week. This shows promise toward obtaining reliable assessments of pre and postoperative results for aesthetic surgery procedures. More work must be done to quantify the reliability of assessments for other pretreatment states or the corresponding results following treatment.

Bidirectional long short-term memory for surgical skill classification of temporally segmented tasks.

PURPOSE: The majority of historical surgical skill research typically analyzes holistic summary task-level metrics to create a skill classification for a performance. Recent advances in machine learning allow time series classification at the sub-task level, allowing predictions on segments of tasks, which could improve task-level technical skill assessment. METHODS: A bidirectional long short-term memory (LSTM) network was used with 8-s windows of multidimensional time-series data from the Basic Laparoscopic Urologic Skills dataset. The network was trained on experts and novices from four common surgical tasks. Stratified cross-validation with regularization was used to avoid overfitting. The misclassified cases were re-submitted for surgical technical skill assessment to crowds using Amazon Mechanical Turk to re-evaluate and to analyze the level of agreement with previous scores. RESULTS: Performance was best for the suturing task, with 96.88% accuracy at predicting whether a performance was an expert or novice, with 1 misclassification, when compared to previously obtained crowd evaluations. When compared with expert surgeon ratings, the LSTM predictions resulted in a Spearman coefficient of 0.89 for suturing tasks. When crowds re-evaluated misclassified performances, it was found that for all 5 misclassified cases from peg transfer and suturing tasks, the crowds agreed more with our LSTM model than with the previously obtained crowd scores. CONCLUSION: The technique presented shows results not incomparable with labels which would be obtained from crowd-sourced labels of surgical tasks. However, these results bring about questions of the reliability of crowd sourced labels in videos of surgical tasks. We, as a research community, should take a closer look at crowd labeling with higher scrutiny, systematically look at biases, and quantify label noise.

Temporal variability of surgical technical skill perception in real robotic surgery.

PURPOSE: Summary score metrics, either from crowds of non-experts, faculty surgeons or from automated performance metrics, have been trusted as the prevailing method of reporting surgeon technical skill. The aim of this paper is to learn whether there exist significant fluctuations in the technical skill assessments of a surgeon throughout long durations of surgical footage. METHODS: A set of 12 videos of robotic surgery cases from common human patient robotic surgeries were used to evaluate the perceived technical skill at each individual minute of the surgical videos, which were originally 12-15 min in length. A linear mixed-effects model for each video was used to compare the ratings of each minute to those from every other minute in order to learn whether a change in scores over time can be detected and reliably measured apart from inter- and intrarater variation. RESULTS: Modeling the change over time of the global evaluative assessment of robotic skills scores significantly contributed to the prediction models for 11 of the 12 surgeons. This demonstrates that measurable changes in technical skill occur over time during robotic surgery. CONCLUSION: The findings from this research raise questions about the optimal duration of footage needed to be evaluated to arrive at an accurate rating of surgical technical skill for longer procedures. This may imply non-negligible label noise for supervised machine learning approaches. In the future, it may be necessary to report a surgeon's skill variability in addition to their mean score to have proper knowledge of a surgeon's overall skill level.

The effect of video playback speed on surgeon technical skill perception.

PURPOSE:  Finding effective methods of discriminating surgeon technical skill has proved a complex problem to solve computationally. Previous research has shown that obtaining non-expert crowd evaluations of surgical performances is as accurate as the gold standard, expert surgeon review. The aim of this research is: (1) to learn whether crowdsourced evaluators give higher ratings of technical skill to video of performances with increased playback speed, (2) its effect in discriminating skill levels, and (3) whether this increase is related to the evaluator consciously being aware that the video is manually manipulated. METHODS:  A set of ten peg transfer videos (five novices, five experts) were used to evaluate the perceived technical skill of the performers at each video playback speed used ([Formula: see text]). Objective metrics used for measuring technical skill were also computed for comparison by manipulating the corresponding kinematic data of each performance. Two videos of an expert and novice performing dry laboratory laparoscopic trials of peg transfer tasks were used to obtain evaluations at each playback speed ([Formula: see text]) of perception of whether a video is played at real-time playback speed or not. RESULTS:  We found that while both novices and experts had increased perceived technical skill as the video playback was increased, the amount of increase was significantly greater for experts. Each increase in the playback speed by [Formula: see text] was associated with, on average, a 0.72-point increase in the GOALS score (95% CI 0.60-0.84 point increase; [Formula: see text]) for expert videos and only a 0.24-point increase in the GOALS score (95% CI 0.13-0.36 point increase; [Formula: see text]) for novice videos. CONCLUSION:  Due to the differential increase in perceived technical skill due to increased playback speed for experts, the difference between novice and expert skill levels of surgical performances may be more easily discerned by manually increasing the video playback speed.