Loading...
Publication
Segmentação tridimensional do canal mandibular com inteligência artificial : estudo experimental
| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 682.04 KB | Adobe PDF |
Authors
Abstract(s)
Introdução: a identificação do canal mandibular é essencial para o planeamento seguro de procedimentos cirúrgicos em implantologia. A Inteligência Artificial (IA) tem sido proposta como ferramenta de apoio para a segmentação anatómica automatizada, mas a sua precisão requer validação. Objetivo: avaliar a precisão da segmentação tridimensional do canal mandibular por IA, comparando-a com a segmentação manual realizada por médicos dentistas júnior (MDJ) e com uma referência traçada por um operador experiente (gold standard – GS). Materiais e Métodos: foram analisados 10 exames de tomografia computorizada de feixe cónico (CBCT). Cada exame foi segmentado manualmente por três MDJ, automaticamente por IA e por um operador sénior (GS). As segmentações foram convertidas em modelos STL e comparadas no software Geomagic Control X, através da métrica Root Mean Square (RMS). Os dados foram analisados estatisticamente com ANOVA e testes post hoc utilizando o programa SPSS, versão 28 (IBM Corp.), com um nível de significância de α = 0,05. Resultados: a IA obteve valores médios de RMS inferiores aos das segmentações manuais em ambos os lados da mandíbula (direito: 0,7623; esquerdo: 0,8658), apresentando menor variabilidade (desvio padrão reduzido). Houve diferenças estatisticamente significativas entre as segmentações manuais e a IA (p < 0,001), e entre os diferentes operadores humanos. Conclusão: a IA demonstrou maior precisão e consistência na segmentação do canal mandibular em comparação com os MDJ, aproximando-se mais da segmentação de referência (GS). A IA pode representar uma ferramenta clínica fiável no planeamento de cirurgia de colocação de implantes, promovendo padronização e segurança.
Introduction: identification of the mandibular canal is critical for safe surgical planning in implant dentistry. Artificial Intelligence (AI) has been proposed as a tool for automated anatomical segmentation, but its accuracy requires validation. Objective: to evaluate the accuracy of three-dimensional mandibular canal segmentation using AI, compared with manual segmentation by junior dentists (JD) and a reference drawn by an experienced operator (gold standard – GS). Materials and Methods: ten cone-beam computed tomography (CBCT) scans were analyzed. Each scan was segmented manually by three junior dentists (JD), automatically by artificial intelligence (AI), and by a senior operator (gold standard – GS). The segmentations were converted into STL models and compared using Geomagic Control X software, based on the Root Mean Square (RMS) metric. Statistical analysis was performed using ANOVA and post hoc tests in SPSS software, version 28 (IBM Corp.), with a significance level of α = 0.05. Results: AI segmentation showed lower mean RMS values than manual segmentations on both mandibular sides (right: 0.7623; left: 0.8658) and demonstrated lower variability (reduced standard deviation). Statistically significant differences were found between AI and manual methods (p < 0.001), and among human operators. Conclusion: AI demonstrated higher precision and consistency in mandibular canal segmentation compared to JD, being closer to the reference (GS). AI may serve as a reliable clinical tool in implant planning, enhancing standardization and safety.
Introduction: identification of the mandibular canal is critical for safe surgical planning in implant dentistry. Artificial Intelligence (AI) has been proposed as a tool for automated anatomical segmentation, but its accuracy requires validation. Objective: to evaluate the accuracy of three-dimensional mandibular canal segmentation using AI, compared with manual segmentation by junior dentists (JD) and a reference drawn by an experienced operator (gold standard – GS). Materials and Methods: ten cone-beam computed tomography (CBCT) scans were analyzed. Each scan was segmented manually by three junior dentists (JD), automatically by artificial intelligence (AI), and by a senior operator (gold standard – GS). The segmentations were converted into STL models and compared using Geomagic Control X software, based on the Root Mean Square (RMS) metric. Statistical analysis was performed using ANOVA and post hoc tests in SPSS software, version 28 (IBM Corp.), with a significance level of α = 0.05. Results: AI segmentation showed lower mean RMS values than manual segmentations on both mandibular sides (right: 0.7623; left: 0.8658) and demonstrated lower variability (reduced standard deviation). Statistically significant differences were found between AI and manual methods (p < 0.001), and among human operators. Conclusion: AI demonstrated higher precision and consistency in mandibular canal segmentation compared to JD, being closer to the reference (GS). AI may serve as a reliable clinical tool in implant planning, enhancing standardization and safety.
Description
Keywords
Inteligência artificial Canal mandibular Nervo alveolar inferior Tomografia computorizada de feixe cónico Artificial intelligence Mandibular canal Inferior alveolar nerve Cone-beam computed tomography
Pedagogical Context
Citation
Publisher
CC License
Without CC licence