Artificial Intelligence (AI) is increasingly being applied to a wide range of fields, including healthcare. In the case of rhinoplasty, AI can be used to measure facial angles, which are important for assessing facial harmony and beauty. The traditional method for measuring these angles is manual, which is time-consuming and requires expertise. The manual method is susceptible to errors, as landmark identification can be subjective, and angle calculation can be affected by factors such as the orientation of the face in the photo. A new methodology for automating the process of measuring facial angles using AI is being proposed to diminish errors and achieve precise measurements. The methodology is based on the use of MediaPipe, an open-source framework from Google that provides a machine-learning solution for detecting and tracking facial landmarks, being able to detect and track up to 468 facial landmarks in an image. Some of these landmarks are used to create a 3D projection of the face, estimating the facial angles desired. The results showed that the methodology has an average absolute error of less than 4%, which is comparable to the error of the manual method performed by a trained professional. The results of this work demonstrate that the proposed methodology is an effective tool for automating the process of measuring facial angles. The methodology has a performance comparable to the manual method performed by a trained professional but with a significant reduction in time. The proposed methodology has several advantages over the manual method, being more accurate, as it is not subject to human errors in landmark identification and angle calculation. It’s faster, as it can be performed in seconds. Lastly, it is more reproducible, as the results do not depend on the experience of the operator. This proposal has the potential to improve the accuracy, efficiency, and reproducibility of the assessment of facial angles in rhinoplasty.

NEED TO BE UPDATE