Evaluation of the performance of two software artificial intelligence-based by means of the measurements according to Mcnamara’s Analysis in lateral cephalometric radiographs
| Autor(a) principal: | |
|---|---|
| Data de Publicação: | 2022 |
| Outros Autores: | , , , , , |
| Tipo de documento: | Artigo |
| Idioma: | por |
| Título da fonte: | Research, Society and Development |
| Texto Completo: | https://rsdjournal.org/index.php/rsd/article/view/35820 |
Resumo: | 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<0.01) was observed only in the perpendicular A-N measurement. As for WebCephTM, when comparing with the examiner there was a significant difference between factors two to six and ten. And compared to CEFBOT, there was divergence in the same factors plus factor eleven. In addition, WebCephTM did not identify the measurements Nfa-Nfp and Bfa-Bfp. CEFBOT showed reproducibility and reliability in identifying the cephalometric landmarks determined by McNamara's analysis but required human supervision. WebCeph showed almost perfect agreement in the markings, but six measurements were different from the examiner and two were not performed by the application. |
| id |
UNIFEI_08c3288373d2125882a09df20822a412 |
|---|---|
| oai_identifier_str |
oai:ojs.pkp.sfu.ca:article/35820 |
| network_acronym_str |
UNIFEI |
| network_name_str |
Research, Society and Development |
| repository_id_str |
|
| spelling |
Evaluation of the performance of two software artificial intelligence-based by means of the measurements according to Mcnamara’s Analysis in lateral cephalometric radiographsEvaluación del rendimiento de dos softwares con inteligencia artificial mediante las medidas generadas por el análisis de Mcnamara en radiografías cefalométricas lateralesAvaliação da performance de dois softwares com inteligência artificial por meio das medidas geradas pela análise de Mcnamara em telerradiografia cefalométrica lateralInteligência artificialOrtodontiaAprendizado de máquinaRadiologiaDiagnóstico.Inteligência artificialOrtodonciaAprendizaje automáticoRadiologíaDetección.Artificial intelligenceOrthodonticsMachine learningRadiologyDiagnosis.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<0.01) was observed only in the perpendicular A-N measurement. As for WebCephTM, when comparing with the examiner there was a significant difference between factors two to six and ten. And compared to CEFBOT, there was divergence in the same factors plus factor eleven. In addition, WebCephTM did not identify the measurements Nfa-Nfp and Bfa-Bfp. CEFBOT showed reproducibility and reliability in identifying the cephalometric landmarks determined by McNamara's analysis but required human supervision. WebCeph showed almost perfect agreement in the markings, but six measurements were different from the examiner and two were not performed by the application.El objetivo de este estudio fue comparar el rendimiento de dos programas informáticos con IA en la telerradiografía cefalométrica lateral, evaluando la reproducibilidad y la fiabilidad de las medidas lineales y angulares del análisis de McNamara. Treinta telerradiografías cefalométricas fueron marcadas mediante el método digital por el examinador en Radiocef (RadioMemory). Posteriormente, la muestra se marcó utilizando la IA del software CEFBOT (RadioMemory) y WebCephTM (AssembleCircle) para evaluar la reproducibilidad y la fiabilidad en relación con el examinador y el software en cuestión. Para calibrar el examinador y evaluar la fiabilidad de las marcas del examinador, del CEFBOT y del WebCephTM, se utilizó el coeficiente de correlación intraclase (CCI), así como la prueba ANOVA y la prueba posterior de Tukey evaluaron la reproducibilidad del software, utilizando los puntos de referencia cefalométricos que componen el análisis de McNamara. El CCI medio del examinador, del CEFBOT y del WebCeph fue de 0,960, 0,940 y 0,954, respectivamente, lo que indica una concordancia casi perfecta. Al comparar el CEFBOT con el examinador, se observaron diferencias estadísticas (p<0,01) sólo en la medición perpendicular A-N. Al comparar WebCephTM con el examinador, se observó una diferencia significativa entre los factores dos a seis y diez. En comparación con el CEFBOT, hubo divergencia en los mismos factores más el factor once. Además, WebCephTM no identificó las medidas Nfa-Nfp y Bfa-Bfp. El CEFBOT mostró reproducibilidad y fiabilidad en la identificación de los puntos de referencia cefalométricos determinados por el análisis de McNamara, pero requirió supervisión humana. WebCeph mostró una concordancia casi perfecta en las marcas, pero seis mediciones fueron diferentes a las del examinador y dos no fueron realizadas por la aplicación.O objetivo do trabalho foi comparar a performance de dois softwares com IA em telerradiografia cefalométrica lateral, por meio da avaliação da reprodutibilidade e confiabilidade das medidas lineares e angulares da análise de McNamara. Foram marcadas 30 telerradiografias cefalométricas por meio do método digital pelo examinador no Radiocef (RadioMemory). Posteriormente, a amostra foi marcada por meio da IA dos softwares CEFBOT (RadioMemory) e WebCephTM (AssembleCircle), para avaliação da reprodutibilidade e confiabilidade, em relação ao examinador e os softwares em questão. Para calibrar o examinador e avaliar a confiabilidade das marcações do examinador, CEFBOT, e WebCephTM utilizou o Coeficiente de Correlação Intraclasse (ICC), bem como, o teste ANOVA e pós teste de Tukey avaliou a reprodutibilidade dos softwares, por meio dos pontos cefalométricos que compõem a análise de McNamara. O ICC médio do examinador, CEFBOT e do WebCeph foram 0.960, 0.940 e 0.954, respectivamente, indicando concordância quase perfeita. Ao comparar CEFBOT com examinador, observou-se diferença estatística (p<0.01) apenas na medida A-N perpendicular. Quanto ao WebCephTM, ao comparar com o examinador houve diferença significativa entre os fatores dois ao seis e o dez. E comparado ao CEFBOT, houve divergência nos mesmos fatores somado ao fator onze. Além disso, o WebCephTM não identificou as medidas Nfa-Nfp e Bfa-Bfp. O CEFBOT apresentou reprodutibilidade e confiabilidade na identificação dos pontos cefalométricos determinados pela análise de McNamara, mas necessitando de supervisão humana. O WebCeph apresentou concordância quase perfeita nas marcações, porém seis medidas apresentaram-se diferentes do examinador e duas não foram realizadas pela aplicação.Research, Society and Development2022-10-19info:eu-repo/semantics/articleinfo:eu-repo/semantics/publishedVersionapplication/pdfhttps://rsdjournal.org/index.php/rsd/article/view/3582010.33448/rsd-v11i14.35820Research, Society and Development; Vol. 11 No. 14; e73111435820Research, Society and Development; Vol. 11 Núm. 14; e73111435820Research, Society and Development; v. 11 n. 14; e731114358202525-3409reponame:Research, Society and Developmentinstname:Universidade Federal de Itajubá (UNIFEI)instacron:UNIFEIporhttps://rsdjournal.org/index.php/rsd/article/view/35820/30121Copyright (c) 2022 Laura Luiza Trindade de Souza; Thaisa Pinheiro Silva; William José e Silva Filho; Bruno Natan Santana Lima; Amanda Caroline Nascimento Meireles; Iris Tamara de Santana Oliveira; Wilton Mitsunari Takeshitahttps://creativecommons.org/licenses/by/4.0info:eu-repo/semantics/openAccess Souza, Laura Luiza Trindade deSilva, Thaisa Pinheiro Silva Filho, William José e Lima, Bruno Natan SantanaMeireles, Amanda Caroline NascimentoOliveira, Iris Tamara de Santana Takeshita, Wilton Mitsunari 2022-11-08T13:36:27Zoai:ojs.pkp.sfu.ca:article/35820Revistahttps://rsdjournal.org/index.php/rsd/indexPUBhttps://rsdjournal.org/index.php/rsd/oairsd.articles@gmail.com2525-34092525-3409opendoar:2024-01-17T09:50:35.621998Research, Society and Development - Universidade Federal de Itajubá (UNIFEI)false |
| dc.title.none.fl_str_mv |
Evaluation of the performance of two software artificial intelligence-based by means of the measurements according to Mcnamara’s Analysis in lateral cephalometric radiographs Evaluación del rendimiento de dos softwares con inteligencia artificial mediante las medidas generadas por el análisis de Mcnamara en radiografías cefalométricas laterales Avaliação da performance de dois softwares com inteligência artificial por meio das medidas geradas pela análise de Mcnamara em telerradiografia cefalométrica lateral |
| title |
Evaluation of the performance of two software artificial intelligence-based by means of the measurements according to Mcnamara’s Analysis in lateral cephalometric radiographs |
| spellingShingle |
Evaluation of the performance of two software artificial intelligence-based by means of the measurements according to Mcnamara’s Analysis in lateral cephalometric radiographs Souza, Laura Luiza Trindade de Inteligência artificial Ortodontia Aprendizado de máquina Radiologia Diagnóstico. Inteligência artificial Ortodoncia Aprendizaje automático Radiología Detección. Artificial intelligence Orthodontics Machine learning Radiology Diagnosis. |
| title_short |
Evaluation of the performance of two software artificial intelligence-based by means of the measurements according to Mcnamara’s Analysis in lateral cephalometric radiographs |
| title_full |
Evaluation of the performance of two software artificial intelligence-based by means of the measurements according to Mcnamara’s Analysis in lateral cephalometric radiographs |
| title_fullStr |
Evaluation of the performance of two software artificial intelligence-based by means of the measurements according to Mcnamara’s Analysis in lateral cephalometric radiographs |
| title_full_unstemmed |
Evaluation of the performance of two software artificial intelligence-based by means of the measurements according to Mcnamara’s Analysis in lateral cephalometric radiographs |
| title_sort |
Evaluation of the performance of two software artificial intelligence-based by means of the measurements according to Mcnamara’s Analysis in lateral cephalometric radiographs |
| author |
Souza, Laura Luiza Trindade de |
| author_facet |
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 Takeshita, Wilton Mitsunari |
| author_role |
author |
| author2 |
Silva, Thaisa Pinheiro Silva Filho, William José e Lima, Bruno Natan Santana Meireles, Amanda Caroline Nascimento Oliveira, Iris Tamara de Santana Takeshita, Wilton Mitsunari |
| author2_role |
author author author author author author |
| dc.contributor.author.fl_str_mv |
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 Takeshita, Wilton Mitsunari |
| dc.subject.por.fl_str_mv |
Inteligência artificial Ortodontia Aprendizado de máquina Radiologia Diagnóstico. Inteligência artificial Ortodoncia Aprendizaje automático Radiología Detección. Artificial intelligence Orthodontics Machine learning Radiology Diagnosis. |
| topic |
Inteligência artificial Ortodontia Aprendizado de máquina Radiologia Diagnóstico. Inteligência artificial Ortodoncia Aprendizaje automático Radiología Detección. Artificial intelligence Orthodontics Machine learning Radiology Diagnosis. |
| description |
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<0.01) was observed only in the perpendicular A-N measurement. As for WebCephTM, when comparing with the examiner there was a significant difference between factors two to six and ten. And compared to CEFBOT, there was divergence in the same factors plus factor eleven. In addition, WebCephTM did not identify the measurements Nfa-Nfp and Bfa-Bfp. CEFBOT showed reproducibility and reliability in identifying the cephalometric landmarks determined by McNamara's analysis but required human supervision. WebCeph showed almost perfect agreement in the markings, but six measurements were different from the examiner and two were not performed by the application. |
| publishDate |
2022 |
| dc.date.none.fl_str_mv |
2022-10-19 |
| dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
| format |
article |
| status_str |
publishedVersion |
| dc.identifier.uri.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/35820 10.33448/rsd-v11i14.35820 |
| url |
https://rsdjournal.org/index.php/rsd/article/view/35820 |
| identifier_str_mv |
10.33448/rsd-v11i14.35820 |
| dc.language.iso.fl_str_mv |
por |
| language |
por |
| dc.relation.none.fl_str_mv |
https://rsdjournal.org/index.php/rsd/article/view/35820/30121 |
| dc.rights.driver.fl_str_mv |
https://creativecommons.org/licenses/by/4.0 info:eu-repo/semantics/openAccess |
| rights_invalid_str_mv |
https://creativecommons.org/licenses/by/4.0 |
| eu_rights_str_mv |
openAccess |
| dc.format.none.fl_str_mv |
application/pdf |
| dc.publisher.none.fl_str_mv |
Research, Society and Development |
| publisher.none.fl_str_mv |
Research, Society and Development |
| dc.source.none.fl_str_mv |
Research, Society and Development; Vol. 11 No. 14; e73111435820 Research, Society and Development; Vol. 11 Núm. 14; e73111435820 Research, Society and Development; v. 11 n. 14; e73111435820 2525-3409 reponame:Research, Society and Development instname:Universidade Federal de Itajubá (UNIFEI) instacron:UNIFEI |
| instname_str |
Universidade Federal de Itajubá (UNIFEI) |
| instacron_str |
UNIFEI |
| institution |
UNIFEI |
| reponame_str |
Research, Society and Development |
| collection |
Research, Society and Development |
| repository.name.fl_str_mv |
Research, Society and Development - Universidade Federal de Itajubá (UNIFEI) |
| repository.mail.fl_str_mv |
rsd.articles@gmail.com |
| _version_ |
1797052725768224768 |