基于人工智能、手动和全局阈值分割的人类下颌骨分割方案的真实性。

IF 3.4 2区 医学 Q1 DENTISTRY, ORAL SURGERY & MEDICINE
Andrea Kristine T Hernandez, Vinicius Dutra, Tien-Min G Chu, Chao-Chieh Yang, Wei-Shao Lin
{"title":"基于人工智能、手动和全局阈值分割的人类下颌骨分割方案的真实性。","authors":"Andrea Kristine T Hernandez, Vinicius Dutra, Tien-Min G Chu, Chao-Chieh Yang, Wei-Shao Lin","doi":"10.1111/jopr.70008","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>To compare the trueness of artificial intelligence (AI)-based, manual, and global segmentation protocols by superimposing the resulting segmented 3D models onto reference gold standard surface scan models.</p><p><strong>Materials and methods: </strong>Twelve dry human mandibles were used. A cone beam computed tomography (CBCT) scanner was used to scan the mandibles, and the acquired digital imaging and communications in medicine (DICOM) files were segmented using three protocols: global thresholding, manual, and AI-based segmentation (Diagnocat; Diagnocat, San Francisco, CA). The segmented files were exported as study 3D models. A structured light surface scanner (GoSCAN Spark; Creaform 3D, Levis, Canada) was used to scan all mandibles, and the resulting reference 3D models were exported. The study 3D models were compared with the respective reference 3D models by using a mesh comparison software (Geomagic Design X; 3D Systems Inc, Rock Hill, SC). Root mean square (RMS) error values were recorded to measure the magnitude of deviation (trueness), and color maps were obtained to visualize the differences. Comparisons of the trueness of three segmentation methods for differences in RMS were made using repeated measures analysis of variance (ANOVA). A two-sided 5% significance level was used for all tests in the software program.</p><p><strong>Results: </strong>AI-based segmentations had significantly higher RMS values than manual segmentations for the entire mandible (p < 0.001), alveolar process (p < 0.001), and body of the mandible (p < 0.001). AI-based segmentations had significantly lower RMS values than manual segmentations for the condyles (p = 0.018) and ramus (p = 0.013). No significant differences were found between the AI-based and manual segmentations for the coronoid process (p = 0.275), symphysis (p = 0.346), and angle of the mandible (p = 0.344). Global thresholding had significantly higher RMS values than manual segmentations for the alveolus (p < 0.001), angle of the mandible (p < 0.001), body of the mandible (p < 0.001), condyles (p < 0.001), coronoid (p = 0.002), entire mandible (p < 0.001), ramus (p < 0.001), and symphysis (p < 0.001). Global thresholding had significantly higher RMS values than AI-based segmentation for the alveolar process (p = 0.002), angle of the mandible (p < 0.001), body of the mandible (p < 0.001), condyles (p < 0.001), coronoid (p = 0.017), mandible (p < 0.001), ramus (p < 0.001), and symphysis (p < 0.001).</p><p><strong>Conclusion: </strong>AI-based segmentations produced lower RMS values, indicating truer 3D models, compared to global thresholding, and showed no significant differences in some areas compared to manual segmentation. Thus, AI-based segmentation offers a level of segmentation trueness acceptable for use as an alternative to manual or global thresholding segmentation protocols.</p>","PeriodicalId":49152,"journal":{"name":"Journal of Prosthodontics-Implant Esthetic and Reconstructive Dentistry","volume":" ","pages":""},"PeriodicalIF":3.4000,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Trueness of artificial intelligence-based, manual, and global thresholding segmentation protocols for human mandibles.\",\"authors\":\"Andrea Kristine T Hernandez, Vinicius Dutra, Tien-Min G Chu, Chao-Chieh Yang, Wei-Shao Lin\",\"doi\":\"10.1111/jopr.70008\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Purpose: </strong>To compare the trueness of artificial intelligence (AI)-based, manual, and global segmentation protocols by superimposing the resulting segmented 3D models onto reference gold standard surface scan models.</p><p><strong>Materials and methods: </strong>Twelve dry human mandibles were used. A cone beam computed tomography (CBCT) scanner was used to scan the mandibles, and the acquired digital imaging and communications in medicine (DICOM) files were segmented using three protocols: global thresholding, manual, and AI-based segmentation (Diagnocat; Diagnocat, San Francisco, CA). The segmented files were exported as study 3D models. A structured light surface scanner (GoSCAN Spark; Creaform 3D, Levis, Canada) was used to scan all mandibles, and the resulting reference 3D models were exported. The study 3D models were compared with the respective reference 3D models by using a mesh comparison software (Geomagic Design X; 3D Systems Inc, Rock Hill, SC). Root mean square (RMS) error values were recorded to measure the magnitude of deviation (trueness), and color maps were obtained to visualize the differences. Comparisons of the trueness of three segmentation methods for differences in RMS were made using repeated measures analysis of variance (ANOVA). A two-sided 5% significance level was used for all tests in the software program.</p><p><strong>Results: </strong>AI-based segmentations had significantly higher RMS values than manual segmentations for the entire mandible (p < 0.001), alveolar process (p < 0.001), and body of the mandible (p < 0.001). AI-based segmentations had significantly lower RMS values than manual segmentations for the condyles (p = 0.018) and ramus (p = 0.013). No significant differences were found between the AI-based and manual segmentations for the coronoid process (p = 0.275), symphysis (p = 0.346), and angle of the mandible (p = 0.344). Global thresholding had significantly higher RMS values than manual segmentations for the alveolus (p < 0.001), angle of the mandible (p < 0.001), body of the mandible (p < 0.001), condyles (p < 0.001), coronoid (p = 0.002), entire mandible (p < 0.001), ramus (p < 0.001), and symphysis (p < 0.001). Global thresholding had significantly higher RMS values than AI-based segmentation for the alveolar process (p = 0.002), angle of the mandible (p < 0.001), body of the mandible (p < 0.001), condyles (p < 0.001), coronoid (p = 0.017), mandible (p < 0.001), ramus (p < 0.001), and symphysis (p < 0.001).</p><p><strong>Conclusion: </strong>AI-based segmentations produced lower RMS values, indicating truer 3D models, compared to global thresholding, and showed no significant differences in some areas compared to manual segmentation. Thus, AI-based segmentation offers a level of segmentation trueness acceptable for use as an alternative to manual or global thresholding segmentation protocols.</p>\",\"PeriodicalId\":49152,\"journal\":{\"name\":\"Journal of Prosthodontics-Implant Esthetic and Reconstructive Dentistry\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":3.4000,\"publicationDate\":\"2025-07-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Prosthodontics-Implant Esthetic and Reconstructive Dentistry\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1111/jopr.70008\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"DENTISTRY, ORAL SURGERY & MEDICINE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Prosthodontics-Implant Esthetic and Reconstructive Dentistry","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/jopr.70008","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"DENTISTRY, ORAL SURGERY & MEDICINE","Score":null,"Total":0}
引用次数: 0

摘要

目的:通过将所得到的分割3D模型叠加到参考金标准表面扫描模型上,比较基于人工智能(AI)、手动和全局分割协议的真实性。材料和方法:使用12块干燥的人下颌骨。使用锥形束计算机断层扫描(CBCT)扫描仪扫描下颌骨,并使用三种协议对获得的数字成像和医学通信(DICOM)文件进行分割:全局阈值分割、手动分割和基于人工智能的分割(diagnostics;诊断,旧金山,加州)。将分割后的文件导出为研究三维模型。结构光表面扫描仪(GoSCAN Spark;使用Creaform 3D, Levis, Canada)对所有下颌骨进行扫描,并导出相应的参考3D模型。利用网格对比软件(Geomagic Design X;3D系统公司,岩石山,南卡罗来纳州)。记录均方根(RMS)误差值来衡量偏差的大小(真实度),并获得彩色图来显示差异。采用重复测量方差分析(ANOVA)比较三种分割方法对RMS差异的正确率。在软件程序中,所有测试均采用双侧5%显著性水平。结果:对于整个下颌骨,人工智能分割的RMS值明显高于人工分割(p结论:与全局阈值相比,人工智能分割产生的RMS值更低,表明3D模型更真实,并且在某些区域与人工分割相比没有显着差异。因此,基于人工智能的分割提供了一种可接受的分割真实性水平,可作为手动或全局阈值分割协议的替代方案。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Trueness of artificial intelligence-based, manual, and global thresholding segmentation protocols for human mandibles.

Purpose: To compare the trueness of artificial intelligence (AI)-based, manual, and global segmentation protocols by superimposing the resulting segmented 3D models onto reference gold standard surface scan models.

Materials and methods: Twelve dry human mandibles were used. A cone beam computed tomography (CBCT) scanner was used to scan the mandibles, and the acquired digital imaging and communications in medicine (DICOM) files were segmented using three protocols: global thresholding, manual, and AI-based segmentation (Diagnocat; Diagnocat, San Francisco, CA). The segmented files were exported as study 3D models. A structured light surface scanner (GoSCAN Spark; Creaform 3D, Levis, Canada) was used to scan all mandibles, and the resulting reference 3D models were exported. The study 3D models were compared with the respective reference 3D models by using a mesh comparison software (Geomagic Design X; 3D Systems Inc, Rock Hill, SC). Root mean square (RMS) error values were recorded to measure the magnitude of deviation (trueness), and color maps were obtained to visualize the differences. Comparisons of the trueness of three segmentation methods for differences in RMS were made using repeated measures analysis of variance (ANOVA). A two-sided 5% significance level was used for all tests in the software program.

Results: AI-based segmentations had significantly higher RMS values than manual segmentations for the entire mandible (p < 0.001), alveolar process (p < 0.001), and body of the mandible (p < 0.001). AI-based segmentations had significantly lower RMS values than manual segmentations for the condyles (p = 0.018) and ramus (p = 0.013). No significant differences were found between the AI-based and manual segmentations for the coronoid process (p = 0.275), symphysis (p = 0.346), and angle of the mandible (p = 0.344). Global thresholding had significantly higher RMS values than manual segmentations for the alveolus (p < 0.001), angle of the mandible (p < 0.001), body of the mandible (p < 0.001), condyles (p < 0.001), coronoid (p = 0.002), entire mandible (p < 0.001), ramus (p < 0.001), and symphysis (p < 0.001). Global thresholding had significantly higher RMS values than AI-based segmentation for the alveolar process (p = 0.002), angle of the mandible (p < 0.001), body of the mandible (p < 0.001), condyles (p < 0.001), coronoid (p = 0.017), mandible (p < 0.001), ramus (p < 0.001), and symphysis (p < 0.001).

Conclusion: AI-based segmentations produced lower RMS values, indicating truer 3D models, compared to global thresholding, and showed no significant differences in some areas compared to manual segmentation. Thus, AI-based segmentation offers a level of segmentation trueness acceptable for use as an alternative to manual or global thresholding segmentation protocols.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
7.90
自引率
15.00%
发文量
171
审稿时长
6-12 weeks
期刊介绍: The Journal of Prosthodontics promotes the advanced study and practice of prosthodontics, implant, esthetic, and reconstructive dentistry. It is the official journal of the American College of Prosthodontists, the American Dental Association-recognized voice of the Specialty of Prosthodontics. The journal publishes evidence-based original scientific articles presenting information that is relevant and useful to prosthodontists. Additionally, it publishes reports of innovative techniques, new instructional methodologies, and instructive clinical reports with an interdisciplinary flair. The journal is particularly focused on promoting the study and use of cutting-edge technology and positioning prosthodontists as the early-adopters of new technology in the dental community.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信