Application of artificial intelligence in identification of dental implants system: literature review

Journal of Dental Implant Research 2020³â 39±Ç 4È£ p.48 ~ p.52

ÀÓÈ£°æ(Lim Ho-Kyung) - Korea University Guro Hospital Department of Oral and Maxillofacial Surgery
±Ç¿¹Áø(Kwon Yeh-Jin) - Korea University Guro Hospital Department of Oral and Maxillofacial Surgery
ÀÌÀǼ®(Lee Eui-Seok) - Korea University Guro Hospital Department of Oral and Maxillofacial Surgery

Abstract

Artificial intelligence (AI) can be used for broad field and have also applied in dental field. Although there have not been many studies on AI related to dental implants, research to identify implant systems in radiographic images using AI is being tried actively. The purpose of this study is to review articles related to application of AI for identification of dental implants system. A systematic review was conducted using Pubmed and Scopus databases to identify articles about AI and dental implants system in English literature. Factors such as Implant system, Data modality, Sample Size, Training time, Validation method, AI method, Accuracy, Sensitivity, Specificity, and Area under the receiver operating characteristic curve (AUC) were extracted from 4 articles. In the literatures, all of the research adopted to pretrained convolutional neural networks as AI method. AI accuracy to find correct implant system was ranged from 51 to 99.5 percent.

Å°¿öµå

Artificial intelligence, Machine learning, Deep learning, Dental implant
¿ø¹® ¹× ¸µÅ©¾Æ¿ô Á¤º¸
µîÀçÀú³Î Á¤º¸
ÁÖÁ¦ÄÚµå
ÁÖÁ¦¸í(Target field)
¿¬±¸´ë»ó(Population)
¿¬±¸Âü¿©(Sample size)
´ë»ó¼ºº°(Gender)
Áúº´Æ¯¼º(Condition Category)
¿¬±¸È¯°æ(Setting)
¿¬±¸¼³°è(Study Design)
¿¬±¸±â°£(Period)
ÁßÀç¹æ¹ý(Intervention Type)
ÁßÀç¸íĪ(Intervention Name)
Å°¿öµå(Keyword)
À¯È¿¼º°á°ú(Recomendation)
Factors such as Implant system, Data modality, Sample Size, Training time, Validation method, AI method, Accuracy, Sensitivity, Specificity, and Area under the receiver operating characteristic curve (AUC) were extracted from 4 articles. In the literatures, all of the research adopted to pretrained convolutional neural networks as AI method.
¿¬±¸ºñÁö¿ø(Fund Source)
±Ù°Å¼öÁØÆò°¡(Evidence Hierarchy)
ÃâÆdz⵵(Year)
Âü¿©ÀúÀÚ¼ö(Authors)
´ëÇ¥ÀúÀÚ
DOI
KCDÄÚµå
ICD 03
°Ç°­º¸ÇèÄÚµå