The Surgeon's Digital Eye: Assessing Artificial Intelligence-generated Images in Breast Augmentation and Reduction

Arsany Yassa; Arya Akhavan; Solina Ayad; Olivia Ayad; Anthony Colon; Ashley Ignatiuk

doi:10.1097/GOX.0000000000006295

The Surgeon's Digital Eye: Assessing Artificial Intelligence-generated Images in Breast Augmentation and Reduction

Plast Reconstr Surg Glob Open. 2024 Dec 20;12(12):e6295. doi: 10.1097/GOX.0000000000006295. eCollection 2024 Dec.

Authors

Arsany Yassa¹, Arya Akhavan¹, Solina Ayad², Olivia Ayad^{3

4

5}, Anthony Colon¹, Ashley Ignatiuk¹

Affiliations

¹ From Division of Plastic and Reconstructive Surgery, Rutgers New Jersey Medical School, Newark, N.J.
² Department of Computer Engineering, The British University in Egypt - BUE, El Sherouk City, Egypt.
³ Arclivia: A Platform for Innovation & Research in AI Integration.
⁴ Department of Architecture and Territory, Mediterranean University of Reggio Calabria, Calabria, Italy.
⁵ Department of Landscape Architecture, International Credit Hours Engineering Programs of Ain Shams University, Cairo, Egypt.

Abstract

Background: Given the public's tendency to overestimate the capability of artificial intelligence (AI) in surgical outcomes for plastic surgery, this study assesses the accuracy of AI-generated images for breast augmentation and reduction, aiming to determine if AI technology can deliver realistic expectations and can be useful in a surgical context.

Methods: We used AI platforms GetIMG, Leonardo, and Perchance to create pre- and postsurgery images of breast augmentation and reduction. Board-certified plastic surgeons and plastic surgery residents evaluated these images using 11 metrics and divided them into 2 categories: realism and clinical value. Statistical analysis was conducted using analysis of variance and Tukey honestly significant difference post hoc tests. Images of the nipple-areolar complex were excluded due to AI's nudity restrictions.

Results: GetIMG (mean ± SD) (realism: 3.83 ± 0.81, clinical value: 3.13 ± 0.62), Leonardo (realism: 3.30 ± 0.69, clinical value: 2.94 ± 0.47), and Perchance (realism: 2.68 ± 0.77, clinical value: 2.88 ± 0.44) showed comparable realism and clinical value scores with no significant difference (P > 0.05). In specific metrics, GetIMG outperformed significantly in surgical relevance compared with the other models (P values: 0.02 and 0.03). Healing and scarring prediction is the metric that underperformed across models (2.25 ± 1.11 P ≤ 0.03). Panelists found some images "cartoonish" with unrealistic skin, indicating AI origin.

Conclusions: The AI models showed similar performance, with some images accurately predicting postsurgical outcomes, particularly breast size and volume in a bra. Despite this promise, the absence of detailed nipple-areola complex visualization is a significant limitation. Until these features and consistent representations of various body types and skin tones are achievable, the authors advise using actual patient photographs for consultations.