Thaísa Pinheiro Silva1, Mariana Mendonça Hughes2, Liciane Dos Santos Menezes3, Maria de Fátima Batista de Melo4, Paulo Henrique Luiz de Freitas5, Wilton Mitsunari Takeshita6. 1. Departament of Oral Diagnosis, Piracicaba Dental School, University of Campinas, Piracicaba, São Paulo, Brasil. 2. Department of Dentistry, Undergraduate student of Dentistry, Federal University of Sergipe, Sergipe, Brazil. 3. Department of Dentistry, Federal University of Bahia, Salvador, Brazil. 4. Department of Dentistry, PhD in Oral Radiology, Federal University of Sergipe, Sergipe, Brazil. 5. Department of Dentistry, PhD in Oral Life Sciences (OMF Surgery), Federal University of Sergipe at Lagarto, Sergipe, Brazil. 6. Department of Dentistry, PhD in Oral Radiology and Postdoctoral in Integrated Dentistry, Professor of Oral Radiology, Oral Diagnosis and Bioestatistics, Federal University of Sergipe, Sergipe, Brazil.
Abstract
OBJECTIVE: To assess the reliability of CEFBOT, an artificial intelligence (AI)-based cephalometry software, for cephalometric landmark annotation and linear and angular measurements according to Arnett's analysis. METHODS: Thirty lateral cephalometric radiographs acquired with a Carestream CS 9000 3D unit (Carestream Health Inc., Rochester/NY) were used in this study. The 66 landmarks and the 10 selected linear and angular measurements of Arnett's analysis were identified on each radiograph by a trained human examiner (control) and by CEFBOT (RadioMemory Ltd., Belo Horizonte, Brazil). For both methods, landmark annotations and measurements were duplicated with an interval of 15 days between measurements and the intraclass correlation coefficient (ICC) was calculated to determine reliability. The numerical values obtained with the two methods were compared by a t-test for independent variables. RESULTS: CEFBOT was able to perform all but one of the 10 measurements. ICC values > 0.94 were found for the remaining eight measurements, while the Frankfurt horizontal plane - true horizontal line (THL) angular measurement showed the lowest reproducibility (human, ICC = 0.876; CEFBOT, ICC = 0.768). Measurements performed by the human examiner and by CEFBOT were not statistically different. CONCLUSION: Within the limitations of our methodology, we concluded that the AI contained in the CEFBOT software can be considered a promising tool for enhancing the capacities of human radiologists.
OBJECTIVE: To assess the reliability of CEFBOT, an artificial intelligence (AI)-based cephalometry software, for cephalometric landmark annotation and linear and angular measurements according to Arnett's analysis. METHODS: Thirty lateral cephalometric radiographs acquired with a Carestream CS 9000 3D unit (Carestream Health Inc., Rochester/NY) were used in this study. The 66 landmarks and the 10 selected linear and angular measurements of Arnett's analysis were identified on each radiograph by a trained human examiner (control) and by CEFBOT (RadioMemory Ltd., Belo Horizonte, Brazil). For both methods, landmark annotations and measurements were duplicated with an interval of 15 days between measurements and the intraclass correlation coefficient (ICC) was calculated to determine reliability. The numerical values obtained with the two methods were compared by a t-test for independent variables. RESULTS: CEFBOT was able to perform all but one of the 10 measurements. ICC values > 0.94 were found for the remaining eight measurements, while the Frankfurt horizontal plane - true horizontal line (THL) angular measurement showed the lowest reproducibility (human, ICC = 0.876; CEFBOT, ICC = 0.768). Measurements performed by the human examiner and by CEFBOT were not statistically different. CONCLUSION: Within the limitations of our methodology, we concluded that the AI contained in the CEFBOT software can be considered a promising tool for enhancing the capacities of human radiologists.
Entities:
Keywords:
Artificial Intelligence; Cephalometry; Deep learning; Machine learning; Orthognathic Surgery
Authors: Andrej Thurzo; Viera Jančovičová; Miroslav Hain; Milan Thurzo; Bohuslav Novák; Helena Kosnáčová; Viera Lehotská; Ivan Varga; Peter Kováč; Norbert Moravanský Journal: Molecules Date: 2022-06-23 Impact factor: 4.927