Artificial Intelligence in the Surgery-First Approach: Harnessing Deep Learning for Enhanced Condylar Reshaping Analysis: A Retrospective Study

Background: The surgery-first approach (SFA) in orthognathic surgery eliminates the need for pre-surgical orthodontic treatment, significantly reducing overall treatment time. However, reliance on a compromised occlusion introduces risks of condylar displacement and remodeling. This study employs artificial intelligence (AI) and deep learning to analyze condylar behavior, comparing the outcomes of SFA to the traditional surgery-late approach (SLA). Methods: A retrospective analysis was conducted on 77 patients (18 SFA and 59 SLA) treated at Perugia Hospital between 2016 and 2022. Preoperative (T0) and 12-month postoperative (T1) cone-beam computed tomography (CBCT) scans were analyzed using the 3D Slicer software and its Dental Segmentator extension, powered by a convolutional neural network (CNN). This automated approach reduced segmentation time from 7 h to 5 min. Pre- and postoperative 3D models were compared to assess linear and rotational deviations in condylar morphology, stratified via dentoskeletal classification and surgical techniques. Results: Both the SFA and SLA achieved high surgical accuracy (<2 mm linear deviation and <2° rotational deviation). The SFA and SLA exhibited similar rates of condylar surface remodeling, with minor differences in resorption and formation across dentoskeletal classifications. Mean surface changes were 0.41 mm (SFA) and 0.36 mm (SLA, p < 0.05). Conclusions: Deep learning enables rapid, precise CBCT analysis and shows promise for the early detection of condylar changes. The SFA does not increase adverse effects on condylar morphology compared to SLA, supporting its safety and efficacy when integrated with AI technologies.