A Comparative Analysis of Artificial Intelligence and Manual Methods for Three-Dimensional Anatomical Landmark Identification in Dentofacial Treatment Planning

• DOI: 10.3390/bioengineering11040318
• Publication Date: 2024-03-27T17:39:56Z
• Authors: Hee-Ju Ahn; Soo-Hwan Byun; Sae-Hoon Baek; Sang-Yoon Park; Sang-Min Yi; In-Young Park; Sung-Woon On; Jong-Cheol Kim; Byoung-Eun Yang
• Keywords: Landmark; Identification; Tracing; Surgical Planning

With the growing demand for orthognathic surgery and other facial treatments, accurate identification of anatomical landmarks has become crucial. Recent advancements have shifted towards using three-dimensional radiologic analysis instead traditional two-dimensional methods, as it allows more precise treatment planning, primarily relying on direct by clinicians. However, manual tracing can be time-consuming, mainly when dealing with a large number patients. This study compared accuracy reliability identifying artificial intelligence (AI) identification. Thirty patients over 19 years old who underwent pre-orthodontic had scans were selected. Thirteen indicators identified both AI methods. The four experienced clinicians, multiple ANOVA was performed to analyze results. results revealed minimal significant differences between tracing, maximum deviation less than 2.83 mm. indicates that utilizing identify reliable method in planning surgery. Our findings suggest landmark enhance reliability, ultimately benefiting clinicians