The increased availability and affordability of 3D scanning technology due to recent advancements have made pre and post-operative analysis for facial surgeries more convenient and accurate through the use of 3D patient scans. However, to perform a more comprehensive analysis using area and volume measurements, it is necessary to develop new software tools that include the appropriate algorithms. Without the right algorithms, any software tool cannot perform its intended tasks effectively. In this study, we introduce two algorithms along with their open-source code to calculate the surface area and volume of a specific subsection of a 3D model. The first algorithm partitions the area/volume into smaller segmentations and applies raycasting to find the points on the face surface, and then finds an approximate measurement depending on the resolution selected. In contrast, the second algorithm utilizes the vertex information stored in the 3D model file to calculate the area and volume measurements for the designated region. The advantage of the second algorithm is that it examines every point in the model, resulting in the highest degree of precision possible. We have also used ChatGPT to generate the code for area/volume calculation and found that the logic of the ChatGPT-generated code is surprisingly similar to the second algorithm. We have presented the results of the measurements on certain regions of the face for both of the algorithms and compared the temporal performance of the algorithms.
Facial landmark detection, a crucial aspect of face recognition, is widely used in various fields, such as facial surgeries, biometrics, and surveillance systems. With the advancement of affordable and capable 3D scanning technologies, research on automatically detecting facial landmarks on 3D models is gaining momentum. Utilizing the geometric properties of 3D facial models, researchers have developed algorithms for various landmarks with varying levels of accuracy. In this study, we reviewed existing literature and developed algorithms for thirty-eight landmarks using geometric properties and statistical information about facial measurements. The algorithms for thirty landmarks are original contributions to the literature. We provide the implementation of all the algorithms as open-source Python code, along with the pseudocode for both our algorithms and those found in the literature. To the best of our knowledge, this study covers the largest number of facial landmark detection algorithms based on the geometric properties of 3D models. This is the first study that provides the implementation of the algorithms along with detailed pseudocode. The results of the algorithms are presented by calculating the mean, median, standard deviation, minimum, and maximum of the errors and depicting the histogram for each landmark over a hundred 3D facial scans. The results show that geometric properties and statistics can be utilized to achieve more robust solutions for facial landmark detection.
AI applications are becoming more and more prevalent each day. ChatGPT is a recent AI tool that has amazed many people with its capabilities. It is expected that large language model solutions like ChatGPT will provide unique solutions and transform many industries. In many medical educational institutions, it is desired that medical students experience simulated patient encounters before meeting with real patients. These simulations can be designed to closely mimic the experience of a real-life patient encounter, allowing students to practice communication and history-taking skills in a realistic setting. Designing dialogues for these simulations is an important and time-consuming challenge. In this study, we evaluate if ChatGPT, an AI tool based on GPT-3, can generate adequate patient-doctor dialogues that can be utilized for medical student training. We analyze patient-doctor dialogues generated by ChatGPT for ten common ENT diseases and discuss the pros and cons of these dialogues. We believe the patient-doctor dialogues provided by ChatGPT can be a good starting point for teaching medical students how to communicate with patients.
Machine Learning started to provide solutions to various challenges in many fields, including medicine. The objective assessment of rhinoplasty results has been a challenge since the assessment of beauty is subjective in nature. This study explores if Machine Learning can be used to accomplish the complex task of objective evaluating the outcome evaluation and automated scoring for rhinoplasty. We introduce a methodology to map the aesthetics of visual appearance to the quantified measurements of presurgery, planned outcome, and post-surgery using machine learning. To develop the methodology, we generated synthetic 3D models utilizing artificial intelligence tools and applied various nasal deformities to simulate the pre-surgery, planned outcome, and post-surgery scans of rhinoplasty patients. The simulated outcomes were scored by reviewing the 3D visuals and corresponding measurements to prepare the training data for machine learning models. AutoGluon AutoML framework is used to generate the best-performing machine learning model. We successfully developed machine learning models with accuracy between 82% to 88% depending on the scoring method. We also identified the measurements that are highly influential in determining the scores. This is the first study that correlates the visual appearance and quantitative facial measurements of simulated rhinoplasty outcomes. The results suggest that an AI-based objective rhinoplasty outcome scoring tool is possible when machine learning algorithms are trained using consensus scores along with patients' pre-surgery, planned, and post-surgery measurements. This study introduces a methodology regarding how to map the aesthetics of visual appearance to the quantified measurements of pre-surgery, planned outcome, and post-surgery using machine learning.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.