Sabahattin Bor, Saadet Çınarsoy Ciğerim, Seda Kotan
{"title":"Comparison of AI-assisted cephalometric analysis and orthodontist-performed digital tracing analysis.","authors":"Sabahattin Bor, Saadet Çınarsoy Ciğerim, Seda Kotan","doi":"10.1186/s40510-024-00539-x","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The aim of this study was to compare and evaluate three AI-assisted cephalometric analysis platforms-CephX, WeDoCeph, and WebCeph-with the traditional digital tracing method using NemoCeph software.</p><p><strong>Material and method: </strong>A total of 1500 lateral cephalometric films that met the inclusion criteria were classified as Class I, Class II, and Class III. Subsequently, 40 patients were randomly selected from each class. These selected films were uploaded to 3 AI-assisted cephalometric analysis platforms and analyzed without any manual intervention. The same films were also analyzed by an orthodontist using the NemoCeph program.</p><p><strong>Results: </strong>The results revealed significant differences in key angular measurements (ANB, FMA, IMPA, and NLA) across Class I, II, and III patients when comparing the four cephalometric analysis methods (WebCeph, WeDoCeph, CephX, and NemoCeph). Notably, ANB (p < 0.05), FMA (p < 0.001), IMPA (p < 0.001), and NLA (p < 0.001) varied significantly. Linear measurements also differed, with significant differences in U1-NA (p = 0.002) and Co-A (p = 0.002) in certain classes. Repeated measurement analysis revealed variation in SNA (p = 0.011) and FMA (p = 0.030), particularly in the Class II NemoCeph group, suggesting method-dependent variability.</p><p><strong>Conclusion: </strong>AI-assisted cephalometric analysis platforms such as WebCeph, WeDoCeph, and CephX give rise to notable variation in accuracy and reliability compared to traditional manual digital tracing, specifically in terms of angular and linear measurements. These results emphasize the importance of meticulous selection and assessment of analysis methods in orthodontic diagnostics and treatment planning.</p>","PeriodicalId":56071,"journal":{"name":"Progress in Orthodontics","volume":"25 1","pages":"41"},"PeriodicalIF":4.8000,"publicationDate":"2024-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11491421/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Progress in Orthodontics","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s40510-024-00539-x","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"Dentistry","Score":null,"Total":0}
引用次数: 0
Abstract
Background: The aim of this study was to compare and evaluate three AI-assisted cephalometric analysis platforms-CephX, WeDoCeph, and WebCeph-with the traditional digital tracing method using NemoCeph software.
Material and method: A total of 1500 lateral cephalometric films that met the inclusion criteria were classified as Class I, Class II, and Class III. Subsequently, 40 patients were randomly selected from each class. These selected films were uploaded to 3 AI-assisted cephalometric analysis platforms and analyzed without any manual intervention. The same films were also analyzed by an orthodontist using the NemoCeph program.
Results: The results revealed significant differences in key angular measurements (ANB, FMA, IMPA, and NLA) across Class I, II, and III patients when comparing the four cephalometric analysis methods (WebCeph, WeDoCeph, CephX, and NemoCeph). Notably, ANB (p < 0.05), FMA (p < 0.001), IMPA (p < 0.001), and NLA (p < 0.001) varied significantly. Linear measurements also differed, with significant differences in U1-NA (p = 0.002) and Co-A (p = 0.002) in certain classes. Repeated measurement analysis revealed variation in SNA (p = 0.011) and FMA (p = 0.030), particularly in the Class II NemoCeph group, suggesting method-dependent variability.
Conclusion: AI-assisted cephalometric analysis platforms such as WebCeph, WeDoCeph, and CephX give rise to notable variation in accuracy and reliability compared to traditional manual digital tracing, specifically in terms of angular and linear measurements. These results emphasize the importance of meticulous selection and assessment of analysis methods in orthodontic diagnostics and treatment planning.
期刊介绍:
Progress in Orthodontics is a fully open access, international journal owned by the Italian Society of Orthodontics and published under the brand SpringerOpen. The Society is currently covering all publication costs so there are no article processing charges for authors.
It is a premier journal of international scope that fosters orthodontic research, including both basic research and development of innovative clinical techniques, with an emphasis on the following areas:
• Mechanisms to improve orthodontics
• Clinical studies and control animal studies
• Orthodontics and genetics, genomics
• Temporomandibular joint (TMJ) control clinical trials
• Efficacy of orthodontic appliances and animal models
• Systematic reviews and meta analyses
• Mechanisms to speed orthodontic treatment
Progress in Orthodontics will consider for publication only meritorious and original contributions. These may be:
• Original articles reporting the findings of clinical trials, clinically relevant basic scientific investigations, or novel therapeutic or diagnostic systems
• Review articles on current topics
• Articles on novel techniques and clinical tools
• Articles of contemporary interest