Scholarlink

Purpose <p>The integration of artificial intelligence (AI) in orthognathic surgery has the potential to significantly enhance preoperative planning and postoperative evaluation by automating time-consuming tasks such as anatomical segmentation and alignment of imaging data.</p> Methods <p>This study investigates the efficiency and accuracy of an AI-based deep learning platform for segmenting 3D models of the maxillofacial region and aligning dental occlusion data with computed tomography (CT) scans. A total of 20 preoperative CT scans were retrospectively collected from patients who underwent bimaxillary orthognathic surgery. The AI platform automatically identified key anatomical structures, segmented them, and aligned STL files from dental scans with the corresponding DICOM files. Both segmentation times (operator and software) and file sizes were recorded.</p> Results <p>The average operator time was 38.9 s, while the mean AI software processing time was approximately 6 min and 59 s. The AI platform demonstrated precise alignment of STL and DICOM files, with no need for manual adjustments in any case.</p> Conclusions <p>The AI system significantly reduced segmentation times and demonstrated high accuracy, making it a valuable tool in orthognathic surgery workflows. While the results are promising, future studies should evaluate its performance across larger and more varied datasets.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Efficacy of Ai Enabled Software in Automatic Segmentation for Orthognathic Surgery

  • 期刊论文

  • 发表日期：

    2025年7月25日

查看全文
  • Jonathas Daniel Paggi Claus,
  • Matheus Spinella Almeida,
  • Hugo Jose Correia Lopes,
  • Bruno Bezerra de Souza

摘要

Purpose

The integration of artificial intelligence (AI) in orthognathic surgery has the potential to significantly enhance preoperative planning and postoperative evaluation by automating time-consuming tasks such as anatomical segmentation and alignment of imaging data.

Methods

This study investigates the efficiency and accuracy of an AI-based deep learning platform for segmenting 3D models of the maxillofacial region and aligning dental occlusion data with computed tomography (CT) scans. A total of 20 preoperative CT scans were retrospectively collected from patients who underwent bimaxillary orthognathic surgery. The AI platform automatically identified key anatomical structures, segmented them, and aligned STL files from dental scans with the corresponding DICOM files. Both segmentation times (operator and software) and file sizes were recorded.

Results

The average operator time was 38.9 s, while the mean AI software processing time was approximately 6 min and 59 s. The AI platform demonstrated precise alignment of STL and DICOM files, with no need for manual adjustments in any case.

Conclusions

The AI system significantly reduced segmentation times and demonstrated high accuracy, making it a valuable tool in orthognathic surgery workflows. While the results are promising, future studies should evaluate its performance across larger and more varied datasets.