Deep Learning–Assisted CBCT Analysis of Condylar Changes After Mandibular Setback Surgery

Balel Y., Akbulut N., Akbulut S.

BRITISH JOURNAL OF ORAL AND MAXILLOFACIAL SURGERY, cilt.1, sa.1, ss.1, 2026 (SCI-Expanded, Scopus)

Özet

Objective

This study aimed to assess condylar changes using a fully automated deep learning–based Cone-beam computed tomography(CBCT) workflow.

Materials and Methods

Pre- and postoperative CBCT scans of 50 skeletal Class III patients(100 condyles) were analyzed using a fully automated pipeline integrating nnU-Net–based segmentation, rigid surface registration, and standardized surface cropping. Condylar changes were quantified using volumetric and linear measurements and surface-based metrics.

Results

Segmentation accuracy was high(Dice: mandible 0.98, condyle 0.99). Mean condylar volume changes ranged from −12.3(6.2) to −0.03(11.1) mm3 on the left and from −11.3(10.7) to −0.95(12.6) mm3 on the right. Significant inter-side volume differences were observed in left and right rotation groups(p=0.003), but not in the non-rotation group(p=0.442). Mandibular rotation direction significantly affected condylar volume change bilaterally(p=0.039). Surface-based metrics differed significantly among rotation groups(p=0.036). Condylar volume change showed a negative correlation with preoperative volume(r=−0.44 to −0.77, p<0.001).

Conclusions

Condylar remodeling after mandibular set-back surgery is rotation-dependent and regionally heterogeneous. The proposed automated CBCT-based workflow enables reproducible, operator-independent quantification of condylar changes and provides a standardized framework for postoperative assessment.