1. Evaluación del rendimiento de dos softwares con inteligencia artificial mediante las medidas generadas por el análisis de Mcnamara en radiografías cefalométricas laterales
- Author
-
Souza, Laura Luiza Trindade de, Silva, Thaisa Pinheiro, Silva Filho, William José e, Lima, Bruno Natan Santana, Meireles, Amanda Caroline Nascimento, Oliveira, Iris Tamara de Santana, and Takeshita, Wilton Mitsunari
- Subjects
Artificial intelligence ,Radiología ,Radiologia ,Orthodontics ,Aprendizado de máquina ,Inteligência artificial ,Diagnosis ,Aprendizaje automático ,Ortodoncia ,Detección ,Machine learning ,Diagnóstico ,Radiology ,Ortodontia - Abstract
The aim of this study was to compare the performance of two software programs with AI in lateral cephalometric teleradiography by assessing the reproducibility and reliability of the linear and angular measurements of McNamara's analysis. Thirty cephalometric teleradiographs were marked using the digital method by the examiner in Radiocef (RadioMemory). Subsequently, the sample was marked using the CEFBOT (RadioMemory) and WebCephTM (AssembleCircle) software AI to evaluate the reproducibility and reliability of the examiner and the software. To calibrate the examiner and evaluate the reliability of the examiner, CEFBOT, and WebCephTM markings, the Intraclass Correlation Coefficient (ICC) was used, as well as the ANOVA test and Tukey's post-test evaluated the reproducibility of the software, using the cephalometric landmarks that comprise McNamara's analysis. The mean ICC of the examiner, CEFBOT and WebCeph were 0.960, 0.940 and 0.954, respectively, indicating almost perfect agreement. When comparing CEFBOT with examiner, statistical difference (p
- Published
- 2022