Turn Your Vision into Reality-AI-Powered Pre-operative Outcome Simulation in Rhinoplasty Surgery.
Artificial intelligence
Computer simulation
Generative adversarial networks
Nose reshaping
Pre-operative simulation
Rhinoplasty
Journal
Aesthetic plastic surgery
ISSN: 1432-5241
Titre abrégé: Aesthetic Plast Surg
Pays: United States
ID NLM: 7701756
Informations de publication
Date de publication:
22 May 2024
22 May 2024
Historique:
received:
06
02
2024
accepted:
28
03
2024
medline:
23
5
2024
pubmed:
23
5
2024
entrez:
22
5
2024
Statut:
aheadofprint
Résumé
The increasing demand and changing trends in rhinoplasty surgery emphasize the need for effective doctor-patient communication, for which Artificial Intelligence (AI) could be a valuable tool in managing patient expectations during pre-operative consultations. To develop an AI-based model to simulate realistic postoperative rhinoplasty outcomes. We trained a Generative Adversarial Network (GAN) using 3,030 rhinoplasty patients' pre- and postoperative images. One-hundred-one study participants were presented with 30 pre-rhinoplasty patient photographs followed by an image set consisting of the real postoperative versus the GAN-generated image and asked to identify the GAN-generated image. The study sample (48 males, 53 females, mean age of 31.6 ± 9.0 years) correctly identified the GAN-generated images with an accuracy of 52.5 ± 14.3%. Male study participants were more likely to identify the AI-generated images compared with female study participants (55.4% versus 49.6%; p = 0.042). We presented a GAN-based simulator for rhinoplasty outcomes which used pre-operative patient images to predict accurate representations that were not perceived as different from real postoperative outcomes. 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 .
Sections du résumé
BACKGROUND
BACKGROUND
The increasing demand and changing trends in rhinoplasty surgery emphasize the need for effective doctor-patient communication, for which Artificial Intelligence (AI) could be a valuable tool in managing patient expectations during pre-operative consultations.
OBJECTIVE
OBJECTIVE
To develop an AI-based model to simulate realistic postoperative rhinoplasty outcomes.
METHODS
METHODS
We trained a Generative Adversarial Network (GAN) using 3,030 rhinoplasty patients' pre- and postoperative images. One-hundred-one study participants were presented with 30 pre-rhinoplasty patient photographs followed by an image set consisting of the real postoperative versus the GAN-generated image and asked to identify the GAN-generated image.
RESULTS
RESULTS
The study sample (48 males, 53 females, mean age of 31.6 ± 9.0 years) correctly identified the GAN-generated images with an accuracy of 52.5 ± 14.3%. Male study participants were more likely to identify the AI-generated images compared with female study participants (55.4% versus 49.6%; p = 0.042).
CONCLUSION
CONCLUSIONS
We presented a GAN-based simulator for rhinoplasty outcomes which used pre-operative patient images to predict accurate representations that were not perceived as different from real postoperative outcomes.
LEVEL OF EVIDENCE III
METHODS
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 .
Identifiants
pubmed: 38777929
doi: 10.1007/s00266-024-04043-9
pii: 10.1007/s00266-024-04043-9
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
© 2024. The Author(s).
Références
Grand View Research (2020) Rhinoplasty market size, share & trends analysis report by treatment type (augmentation, reduction), by technique, by region (North America, Europe, APAC, Latin America, MEA), and segment forecasts, 2021–2028
American Society of Plastic Surgeons (ASPS) (2023) 2022 ASPS procedural statistics release. https://www.plasticsurgery.org/documents/News/Statistics/2022/plastic-surgery-statistics-report-2022.pdf . Accessed 9 Feb 2024
Knoedler S, Knoedler L, Wu M et al (2023) Incidence and risk factors of postoperative complications after rhinoplasty: a multi-institutional ACS-NSQIP analysis. J Craniofac Surg 34:1722–1726
doi: 10.1097/SCS.0000000000009553
pubmed: 37487058
Knoedler L, Odenthal J, Prantl L et al (2023) Artificial intelligence-enabled simulation of gluteal augmentation: a helpful tool in preoperative outcome simulation? J Plast Reconstr Aesthet Surg 80:94–101
doi: 10.1016/j.bjps.2023.01.039
pubmed: 37001299
Chartier C, Gfrerer L, Knoedler L, Austen WG Jr (2023) Artificial intelligence-enabled evaluation of pain sketches to predict outcomes in headache surgery. Plast Reconstr Surg 151:405–411
doi: 10.1097/PRS.0000000000009855
pubmed: 36696328
Knoedler L, Miragall M, Kauke-Navarro M et al (2022) A ready-to-use grading tool for facial palsy examiners-automated grading system in facial palsy patients made easy. J Pers Med 12:1739
doi: 10.3390/jpm12101739
pubmed: 36294878
pmcid: 9605133
Knoedler L, Baecher H, Kauke-Navarro M et al (2022) Towards a reliable and rapid automated grading system in facial palsy patients: facial palsy surgery meets computer science. J Clin Med 11:4998
doi: 10.3390/jcm11174998
pubmed: 36078928
pmcid: 9457271
Chartier C, Watt A, Lin O et al (2021) BreastGAN: artificial intelligence-enabled breast augmentation simulation. Aesthet Surg J Open Forum 4:ojab052
doi: 10.1093/asjof/ojab052
pubmed: 35072073
pmcid: 8781773
Bashiri Bawil M, Rahavi S, Sadeghi M, Zoroofi R (2020) Preoperative computer simulation in rhinoplasty using previous postoperative images. Facial Plast Surg Aesth Med 22:406–411
doi: 10.1089/fpsam.2019.0016
Isola P, Zhu J-Y, Zhou T, Efros AA (2017) Image-to-image translation with conditional adversarial networks, pp 1125-1134
Tseng CC, Patel R, Desai AD et al (2022) Assessing patient satisfaction following blepharoplasty using social media reviews. Aesthet Surg J 42(3):NP179–NP185
doi: 10.1093/asj/sjab345
pubmed: 34537846
Rohrich RJ, Ahmad J (2011) Rhinoplasty. Plast Reconstr Surg 128:49e–73e
doi: 10.1097/PRS.0b013e31821e7191
pubmed: 21788798
Hammond DC, Garcia J (2016) Global Study on 3D benefits within the aesthetics field. White paper
Kumar AR, Ishii M, Papel I et al (2020) The health utility and valuation of cosmetic rhinoplasty. Facial Plast Surg Aesthet Med 22:268–273
doi: 10.1089/fpsam.2020.0011
pubmed: 32282229
Zachow S, Muigg P, Hildebrandt T, Doleisch H, Hege HC (2009) Visual exploration of nasal airflow. IEEE Trans Vis Comput Graph 15:1407–1414
doi: 10.1109/TVCG.2009.198
pubmed: 19834215
Lekakis G, Hens G, Claes P, Hellings PW (2019) Three-dimensional morphing and its added value in the rhinoplasty consult. Plast Reconstr Surg Glob Open 7:e2063
doi: 10.1097/GOX.0000000000002063
pubmed: 30859032
pmcid: 6382239
Ma L, Xiao D, Kim D et al (2023) Simulation of postoperative facial appearances via geometric deep learning for efficient orthognathic surgical planning. IEEE Trans Med Imaging 42:336–345
doi: 10.1109/TMI.2022.3180078
pubmed: 35657829
pmcid: 10037541
Apaydin F, Akyildiz S, Hecht DA, Toriumi DM (2009) Rhinobase: a comprehensive database, facial analysis, and picture-archiving software for rhinoplasty. Arch Facial Plast Surg 11:209–211
doi: 10.1001/archfaci.2009.35
pubmed: 19451458