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

<b>Background:</b> 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. Th...

Full description

Saved in:
Bibliographic Details
Main Authors: Umberto Committeri, Gabriele Monarchi, Massimiliano Gilli, Angela Rosa Caso, Federica Sacchi, Vincenzo Abbate, Stefania Troise, Giuseppe Consorti, Francesco Giovacchini, Valeria Mitro, Paolo Balercia, Antonio Tullio
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Life
Subjects:
Online Access:https://www.mdpi.com/2075-1729/15/2/134
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849719785708847104
author Umberto Committeri
Gabriele Monarchi
Massimiliano Gilli
Angela Rosa Caso
Federica Sacchi
Vincenzo Abbate
Stefania Troise
Giuseppe Consorti
Francesco Giovacchini
Valeria Mitro
Paolo Balercia
Antonio Tullio
author_facet Umberto Committeri
Gabriele Monarchi
Massimiliano Gilli
Angela Rosa Caso
Federica Sacchi
Vincenzo Abbate
Stefania Troise
Giuseppe Consorti
Francesco Giovacchini
Valeria Mitro
Paolo Balercia
Antonio Tullio
author_sort Umberto Committeri
collection DOAJ
description <b>Background:</b> 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). <b>Methods</b>: 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. <b>Results:</b> 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, <i>p</i> < 0.05). <b>Conclusions</b>: 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.
format Article
id doaj-art-67f4dbd21d6f471ebcbc66d5075f6820
institution DOAJ
issn 2075-1729
language English
publishDate 2025-01-01
publisher MDPI AG
record_format Article
series Life
spelling doaj-art-67f4dbd21d6f471ebcbc66d5075f68202025-08-20T03:12:05ZengMDPI AGLife2075-17292025-01-0115213410.3390/life15020134Artificial Intelligence in the Surgery-First Approach: Harnessing Deep Learning for Enhanced Condylar Reshaping Analysis: A Retrospective StudyUmberto Committeri0Gabriele Monarchi1Massimiliano Gilli2Angela Rosa Caso3Federica Sacchi4Vincenzo Abbate5Stefania Troise6Giuseppe Consorti7Francesco Giovacchini8Valeria Mitro9Paolo Balercia10Antonio Tullio11Department of Maxillo-Facial Surgery, Hospital of Perugia, Sant’Andrea delle Fratte, 06132 Perugia, ItalyDepartment of Medicine, Section of Maxillo-Facial Surgery, University of Siena, Viale Bracci, 53100 Siena, ItalyDepartment of Maxillo-Facial Surgery, Hospital of Perugia, Sant’Andrea delle Fratte, 06132 Perugia, ItalyDepartment of Medicine, Section of Maxillo-Facial Surgery, University of Siena, Viale Bracci, 53100 Siena, ItalyDepartment of Medicine, Section of Maxillo-Facial Surgery, University of Siena, Viale Bracci, 53100 Siena, ItalyDepartment of Maxillofacial Surgery, Federico II University of Naples, 80131 Naples, ItalyDepartment of Maxillofacial Surgery, Federico II University of Naples, 80131 Naples, ItalyDivision of Maxillofacial Surgery, Department of Neurological Sciences, Marche University Hospitals-Umberto I, 60126 Ancona, ItalyDepartment of Maxillo-Facial Surgery, Hospital of Perugia, Sant’Andrea delle Fratte, 06132 Perugia, ItalyDepartment of Maxillo-Facial Surgery, Hospital of Perugia, Sant’Andrea delle Fratte, 06132 Perugia, ItalyDivision of Maxillofacial Surgery, Department of Neurological Sciences, Marche University Hospitals-Umberto I, 60126 Ancona, ItalyDepartment of Surgery and Biomedical Sciences, Section of Maxillo-Facial Surgery, University of Perugia, 06129 Perugia, Italy<b>Background:</b> 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). <b>Methods</b>: 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. <b>Results:</b> 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, <i>p</i> < 0.05). <b>Conclusions</b>: 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.https://www.mdpi.com/2075-1729/15/2/134orthognathic surgerysurgery-first approachartificial intelligencedeep learning3D workflow
spellingShingle Umberto Committeri
Gabriele Monarchi
Massimiliano Gilli
Angela Rosa Caso
Federica Sacchi
Vincenzo Abbate
Stefania Troise
Giuseppe Consorti
Francesco Giovacchini
Valeria Mitro
Paolo Balercia
Antonio Tullio
Artificial Intelligence in the Surgery-First Approach: Harnessing Deep Learning for Enhanced Condylar Reshaping Analysis: A Retrospective Study
Life
orthognathic surgery
surgery-first approach
artificial intelligence
deep learning
3D workflow
title Artificial Intelligence in the Surgery-First Approach: Harnessing Deep Learning for Enhanced Condylar Reshaping Analysis: A Retrospective Study
title_full Artificial Intelligence in the Surgery-First Approach: Harnessing Deep Learning for Enhanced Condylar Reshaping Analysis: A Retrospective Study
title_fullStr Artificial Intelligence in the Surgery-First Approach: Harnessing Deep Learning for Enhanced Condylar Reshaping Analysis: A Retrospective Study
title_full_unstemmed Artificial Intelligence in the Surgery-First Approach: Harnessing Deep Learning for Enhanced Condylar Reshaping Analysis: A Retrospective Study
title_short Artificial Intelligence in the Surgery-First Approach: Harnessing Deep Learning for Enhanced Condylar Reshaping Analysis: A Retrospective Study
title_sort artificial intelligence in the surgery first approach harnessing deep learning for enhanced condylar reshaping analysis a retrospective study
topic orthognathic surgery
surgery-first approach
artificial intelligence
deep learning
3D workflow
url https://www.mdpi.com/2075-1729/15/2/134
work_keys_str_mv AT umbertocommitteri artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT gabrielemonarchi artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT massimilianogilli artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT angelarosacaso artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT federicasacchi artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT vincenzoabbate artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT stefaniatroise artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT giuseppeconsorti artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT francescogiovacchini artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT valeriamitro artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT paolobalercia artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy
AT antoniotullio artificialintelligenceinthesurgeryfirstapproachharnessingdeeplearningforenhancedcondylarreshapinganalysisaretrospectivestudy