Ethics for AI in Plastic Surgery: Guidelines and Review.

INTRODUCTION: Artificial intelligence (AI) holds the potential to revolutionize medicine, offering vast improvements for plastic surgery. While human physicians are limited to one lifetime of experience, AI is poised to soon surpass human capabilities, as it draws on limitless information and continuous learning abilities. Nevertheless, as AI becomes increasingly prevalent in this domain, it gives rise to critical ethical considerations that must be addressed by professionals. MATERIALS AND METHODS: This work reviews the literature referring to the ethical challenges brought on by the ever-expanding use of AI in plastic surgery and offers guidelines for its application. RESULTS: Ethical challenges include the disclosure of use of AI by caregivers, validation of decision-making, data privacy, informed consent and autonomy, potential biases in AI systems, the opaque nature of AI models, questions of liability, and the need for regulations. CONCLUSIONS: There is a lack of consensus for the ethical use of AI in plastic surgery. Guidelines, such as those presented in this work, are needed within each discipline of medicine to respond to important ethical considerations for the safe use of AI. LEVEL OF EVIDENCE V: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Identification of Key Breast Features Using a Neural Network: Applications of Machine Learning in the Clinical Setting of Plastic Surgery.

BACKGROUND: In plastic surgery, evaluation of breast symmetry is an important aspect of clinical practice. Computer programs have been developed for this purpose, but most of them require operator input. Artificial intelligence has been introduced into many aspects of medicine. In plastic surgery, automated neural networks for breast evaluation could improve quality of care. In this work, the authors evaluate the identification of breast features with an ad hoc trained neural network. METHODS: An ad hoc convolutional neural network was developed on the YOLOV3 platform to detect key features of the breast that are commonly used in plastic surgery for symmetry evaluation. The program was trained with 200 frontal photographs of patients who underwent breast surgery and was tested on 47 frontal images of patients who underwent breast reconstruction after breast cancer surgery. RESULTS: The program was able to detect key features in 97.74% of cases (boundaries of the breast in 94 of 94 cases, the nipple-areola complex in 94 of 94 cases, and the suprasternal notch in 41 of 47 cases). Mean time of detection was 0.52 seconds. CONCLUSIONS: The ad hoc neural network was successful in localizing key breast features, with a total detection rate of 97.74%. Neural networks and machine learning have the potential to improve the evaluation of breast symmetry in plastic surgery by automated and quick detection of features used by surgeons in practice. More studies and development are needed to further knowledge in this area.

A Novel Artificial Intelligence Model for Symmetry Evaluation in Breast Cancer Patients.

INTRODUCTION: Artificial intelligence (AI) is a milestone for human technology. In medicine, AI is set to play an important role as we progress into a new era. In plastic surgery, AI can participate in breast symmetry assessment, which until now has been mainly subjective, allowing for inconsistencies. This study aims to improve this evaluation process by integrating a novel trained neural network with the breast symmetry calculator, BAS-Calc. MATERIALS AND METHODS: We combined the BAS-Calc tool with a custom-made neural network trained to automatically detect key features of the breast. This integrated system was tested on 81 images of patients who had undergone breast reconstruction post-breast cancer treatment. Its performance was evaluated against two human observers using statistical analysis. RESULTS: Our model successfully detected 399/405 (98.51%) of landmarks. Spearman and Pearson correlation indicated a strong positive relationship while Cohen's kappa demonstrated moderate to strong agreement between human observers and AI model. Notably, the average calculation time for the AI was 0.92 seconds, 16 times faster than the 14.09 seconds for humans. CONCLUSIONS: Our AI model successfully calculated breast symmetry from images of patients who had undergone reconstructive oncological breast surgery, demonstrating high correlation with human assessments and a markedly reduced processing time. As AI continues to evolve, it is poised to become a pivotal tool in Medicine. Therefore, it is crucial for medical professionals to proactively engage in implementing AI technologies safely and effectively. Further studies are required to broaden our understanding and maximize the potential benefits in this area. Takeaway bullet points Artificial intelligence (AI) is an upcoming force to be reckoned with. AI should find its way into practical applications in plastic surgery. AI can be applied to improve patient care and evaluate aesthetic results. In this work, we present a novel AI model that automatically evaluates breast symmetry. LEVEL OF EVIDENCE IV: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Human Beauty according to Artificial Intelligence.

This work explores the upcoming era of artificial intelligence (AI), its potential impact on societal norms and aesthetics, and the biases inherent in AI systems. With the ability to generate realistic human-like art and language, AI entities like DALL·E or Midjourney have significant cultural and economic implications, particularly in creative sectors. However, our study highlights potential biases in AI, demonstrated through a text-to-image model called Craiyon, which was found to generate oversized and sexually suggestive images of breasts when prompted with certain phrases. These results underline the influence of societal norms on AI and the risk of perpetuating harmful stereotypes or unrealistic beauty standards. We emphasize the need for vigilance in monitoring AI's learning processes and potential biases, particularly as AI starts playing a crucial role in shaping societal perceptions of beauty and self. More inclusive and diverse AI models are needed to better represent the complexity of human beauty and to avoid biases.

Age and Breast Reconstruction.

BACKGROUND: Breast reconstruction is frequently offered to cancer patients who undergo mastectomy. Older women tend to have lower rates of reconstruction mostly due to an age-based discretion. We aimed to assess the safety of this surgery in this population. METHODS: We conducted a single-center retrospective analysis of patients who underwent breast reconstruction following mastectomy between 2015 and 2020 at "Complejo Hospitalario Universitario de Albacete." Patients were classified according to age when the reconstruction process began (group A: < 65 years-group B: > 65 years). Differences in demographics and clinical data were analyzed using Student's t test and Chi-square test. Multivariable logistic regression models were used to estimate odds ratio (OR) and confidence intervals (CIs) for surgical complications according to age group. Propensity-score matching was used as a sensitivity analysis to test consistency among results. RESULTS: We included 304 women (266: group A-38: group B). Complete reconstruction was achieved in 48.1% of patients in group A vs 10.5% in group B (P < 0.001). After adjusting for potential confounders, age was not associated with an increased risk of surgical complications, neither overall (OR 0.88, 95%CI 0.40-1.95), early (OR 1.35, 95%CI 0.58-3.13) nor late (OR 1.05, 95%CI 0.40-2.81). Radiotherapy and smoking history were significant predictors for complications in every setting. CONCLUSIONS: In our cohort, age at breast reconstruction is not associated with a higher risk of surgical complications, in contrast to radiotherapy and smoking history. Therefore, age should not be a limiting factor when considering breast reconstruction. LEVEL OF EVIDENCE IV: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

A Free Tool for Breast Aesthetic Scale Computation.

BACKGROUND: Our work describes the concept of Breast Aesthetic Scale (BAS) as a score for quick and simple objective assessment of results in cosmetic breast surgery. It is obtained by running a software program that we created, based on the previous concept of Objective Breast Cosmesis Scale (OBCS). This was previously described to be used in the context of conservative breast cancer treatment to objectively assess the degree of asymmetry. We describe the implementation of BAS algorithm and study its reproducibility in a set of images. METHODS: A new multiplatform software was developed by us and named Breast Aesthetic Scale Calculator (BAS-Calc), which can be executed on Windows Mac, and Linux. A set of 25 photographs were studied with this software twice by 2 different surgeons. Intrarater and interrater variability were studied, as well as concordance with categorization by another symmetry assessment software available called Breast Analyzing Tool®. RESULTS: Concordance among raters was excellent (intraclass correlation coefficient = 0.953; Lin concordance and correlation coefficient = 0.950), as well as intrarater (0.952 and 0.965). Categorization of both systems (Breast Analyzing Tool and BAS-Calc) showed almost perfect concordance (Cohen κ = 0.920). CONCLUSIONS: Objective estimation of symmetry after breast surgery can be assessed with BAS-Calc. The "symmetric" and "asymmetric" categories are accurately discriminated by this free software, and it can be used by surgeons as a simple method for objective assessment of results in cosmetic breast surgery.

Visual Breast Asymmetry Assessment with Optical-Flow Algorithm.

Breast surgery is one of the most important procedures in cosmetic and reconstructive surgery. However, there is no ideal method to assess results. One of the greatest difficulties is the subjective aspect of evaluation. In recent years, several objective computer systems have been proposed and validated as assessment methods, such as BCCT®, OBCS®, GBAI©, etc. In this study, we propose a novel system named VIBA©, that uses an Optical Flow (OF) algorithm which objectively classifies results into symmetrical and asymmetrical categories, with a numerical score. Software was developed in MATLAB (MATLAB and Statistics Toolbox Release 2018b, The MathWorks, Inc., Natick, Massachusetts, USA) called VIBA-Calc© (VIBA stands for VIsual Breast Asymmetry). We compared our OF score with the well-established asymmetry scoring system called Objective Breast Cosmesis Scale (OBCS®). In order to do so, we studied 100 frontal photographs of patients who underwent aesthetic breast surgery between 2017 and 2018, from the senior author's private practice. VIBA-Calc© allows the user to load an image and then draw a rectangle containing both breasts. By simply clicking on a button, the program finds the midline of the rectangle and calculates the final score, as well as the color map of asymmetric regions. Classification into symmetric or asymmetric categories using OBCS and VIBA scores agreed in most cases. Concordance between both classification systems was almost perfect in the group of postoperative cases (k = 0.84; p < 0.001), and substantial in preoperative cases (k = 0.76; p < 0.001). Global Cohen's kappa coefficient was 0.80 (p < 0.001). VIBA© is a useful tool for pre- and post-operative evaluation of breasts, that could be used both in reconstructive and aesthetic surgery.

Use of Symmetry Assessment Methods in the Context of Breast Surgery.

BACKGROUND: Different procedures are available to help clinicians evaluate symmetry and cosmetic results in an objective manner after conservative breast cancer surgery. However, there are no similar methods in esthetic breast surgery, where the subjective assessment of the surgeon or the patient is usually considered the gold standard. The aim of this study is to evaluate the application of four software programs in the context of esthetic breast surgery and contrast their results with those of the subjective evaluation by a series of healthcare professionals. MATERIALS AND METHODS: Sixty cosmetic breast surgery images were studied using four software programs considered appropriate for the objective evaluation (BCCT3.core®, Breast Analyzing Tool®, Objective Breast Cosmesis Scale® and GBAI-Global Breast Asymmetry Index®). The same cases were assessed by a group of 100 health professionals through an online survey as a subjective evaluation method. RESULTS: Concordance among participants was high (κ = 0.753) as well as between three of the objective methods (BSI, OBCS, GBAI), but not with the BCCT parameter. There was no association between objective and subjective methods studied by the survey, according to the logistic regression model. The "symmetry" and "asymmetry" categories were accurately distinguished by the objective methods. CONCLUSIONS: Objective evaluation in esthetic breast surgery has less variability than subjective assessment, and the estimation is possible through certain software previously restricted to conservative breast cancer surgery. LEVEL OF EVIDENCE IV: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .