Rutger Ter Horst1, Hanneke van Weert2, Tom Loonen3, Stefaan Bergé4, Shank Vinayahalingam5, Frank Baan6, Thomas Maal7, Guido de Jong8, Tong Xi9. 1. Department of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands. Electronic address: Rutger.terHorst@radboudumc.nl. 2. Department of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands. Electronic address: Hanneke.vanWeert@radboudumc.nl. 3. Radboudumc 3D Lab, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands. Electronic address: Tom.Loonen@radboudumc.nl. 4. Department of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands. Electronic address: Stefaan.Berge@radboudumc.nl. 5. Department of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands; Radboudumc 3D Lab, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands. Electronic address: Shankeeth.Vinayahalingam@radboudumc.nl. 6. Radboudumc 3D Lab, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands. Electronic address: Frank.Baan@radboudumc.nl. 7. Department of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands; Radboudumc 3D Lab, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands. Electronic address: Thomas.Maal@radboudumc.nl. 8. Department of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands; Radboudumc 3D Lab, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands; Department of Neurosurgery, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands. Electronic address: Guido.deJong@radboudumc.nl. 9. Department of Oral and Maxillofacial Surgery, Radboud University Nijmegen Medical Centre, Geert Grooteplein Zuid 10, 6525, GA, Nijmegen, the Netherlands. Electronic address: tong.xi@radboudumc.nl.
Abstract
The study aimed at developing a deep-learning (DL)-based algorithm to predict the virtual soft tissue profile after mandibular advancement surgery, and to compare its accuracy with the mass tensor model (MTM). Subjects who underwent mandibular advancement surgery were enrolled and divided into a training group and a test group. The DL model was trained using 3D photographs and CBCT data based on surgically achieved mandibular displacements (training group). Soft tissue simulations generated by DL and MTM based on the actual surgical jaw movements (test group) were compared with soft-tissue profiles on postoperative 3D photographs using distance mapping in terms of mean absolute error in the lower face, lower lip, and chin regions. 133 subjects were included - 119 in the training group and 14 in the test group. The mean absolute error for DL-based simulations of the lower face region was 1.0 ± 0.6 mm and was significantly lower (p = 0.02) compared with MTM-based simulations (1.5 ± 0.5 mm). CONCLUSION: The DL-based algorithm can predict 3D soft tissue profiles following mandibular advancement surgery. With a clinically acceptable mean absolute error. Therefore, it seems to be a relevant option for soft tissue prediction in orthognathic surgery. Therefore, it seems to be a relevant options.
The study aimed at developing a deep-learning (DL)-based algorithm to predict the virtual soft tissue profile after mandibular advancement surgery, and to compare its accuracy with the mass tensor model (MTM). Subjects who underwent mandibular advancement surgery were enrolled and divided into a training group and a test group. The DL model was trained using 3D photographs and CBCT data based on surgically achieved mandibular displacements (training group). Soft tissue simulations generated by DL and MTM based on the actual surgical jaw movements (test group) were compared with soft-tissue profiles on postoperative 3D photographs using distance mapping in terms of mean absolute error in the lower face, lower lip, and chin regions. 133 subjects were included - 119 in the training group and 14 in the test group. The mean absolute error for DL-based simulations of the lower face region was 1.0 ± 0.6 mm and was significantly lower (p = 0.02) compared with MTM-based simulations (1.5 ± 0.5 mm). CONCLUSION: The DL-based algorithm can predict 3D soft tissue profiles following mandibular advancement surgery. With a clinically acceptable mean absolute error. Therefore, it seems to be a relevant option for soft tissue prediction in orthognathic surgery. Therefore, it seems to be a relevant options.
Keywords:
3D face analysis; Artificial intelligence; Deep learning; Mandibular advancement surgery; Mass tensor model; Orthognathic surgery; Soft tissue prediction