Three-dimensional virtual planning in mandibular advancement surgery: soft tissue prediction based on deep learning. R ter Horst, H van Weert, T Loonen, S Bergé, S Vinayahalingam, F Baan, T Maal, G de Jong, T Xi.

3dMD Customer Research, Computer Science | Computer Vision, Medical, 3dMDface, Oral and Maxillofacial, Orthognathic

This study focused on developing a novel deep-learning (DL)-based algorithm to predict the virtual soft tissue profile after mandibular advancement surgery and comparing its accuracy with the mass tensor model (MTM).

Automatic Assessment of 3-Dimensional Facial Soft Tissue Symmetry Before and After Orthognathic Surgery Using a Machine Learning Model. LJ Lo, CT Yang, CT Ho, CH Liao, HH Lin.

3dMD Customer Research, Computer Science | Computer Vision, Medical, 3dMDface, Craniofacial/Cleft, Plastics

This study applied the transfer learning model with a convolutional neural network based on 3-dimensional (3D) contour line features to evaluate the facial symmetry before and after OGS. A total of 158 patients were recruited in a retrospective cohort study for the assessment and comparison of facial symmetry before and after OGS from January 2018 to March 2020. Three-dimensional facial photographs were captured by the 3dMD face system in a natural head position, with eyes looking forward, relaxed facial muscles, and habitual dental occlusion before and at least 6 months after surgery.

Changes in the craniofacial structures and esthetic perceptions of soft-tissue profile alterations after distalization and Herbst appliance treatment. EC Irezli, A Baysal.

3dMD Customer Research, Dental, 3dMDface, Orthodontics

Dentoskeletal and soft-tissue treatment changes were examined objectively by cephalometric analysis and stereophotogrammetry, respectively. Pre- and posttreatment profile views were evaluated subjectively by orthodontists and laypeople using the 7-point Likert scale. Intra- and intergroup comparisons for the repeated measurements were performed with 2-way variance analysis. Bonferroni test was used for multiple comparisons (P ≤0.05).