Evaluation of artificial intelligence for detecting impacted third molars on cone-beam computed tomography scans

The Effectiveness of Semi-Automated and Fully Automatic Segmentation for Inferior Alveolar Canal Localization on CBCT Scans: A Systematic Review

“…All seven retrospective studies involve a total of 1288 human CBCT scans. Five out of seven studies used convolutional neural network algorithms [ 37 , 38 , 39 , 40 , 41 ], and in the other two studies, one used statistical shape models [ 42 ], and the other one tested a new automated method [ 43 ]. Despite the progress of AI within oral and maxillofacial radiology, the number of published studies testing AI algorithms for IAN/IANC detection on CBCT scans is relevantly low; from 2016 till the 22 of August 2021, only seven studies have been published and identified.…”

“…The U-net-like algorithms implemented by Diagnocat software (Diagnocat Inc, West Sacramento, CA, USA) were tested by Orhan et al [ 37 ] and Bayrakdar et al [ 39 ], respectively tested 85 and 75 CBCT scans as sample size. In each study, one oral and maxillofacial radiologist was involved in performing the reference test.…”

“…The sensitivity (90.2%) and specificity (95%) were only reported in Lui et al [ 38 ] study, while three studies [ 38 , 40 , 41 ] reported the accuracy without presenting the diagnostic odds. Kappa statistics and Kendall’s coefficient were reported respectively by Orhan et al [ 37 ] (0.762) and Liu et al [ 38 ] (0.901) in their studies to describe the level of agreement between the index and reference test. Liu et al [ 38 ] determined the reliability between the two investigators using Weighted Kappa (0.783) that indicated good results.…”

“…The major weaknesses for most of the selected and analyzed studies were the variation of indexes used for result presentation [ 37 , 38 , 39 , 40 , 41 , 42 , 43 ], the absence of clear exclusion criteria [ 37 , 38 , 39 , 42 , 43 ], and poor explanation of the reference test [ 37 , 39 , 42 , 43 ]. These weaknesses mainly affect the studies’ duplication process that is essential according to the standards for reporting of diagnostic accuracy studies (STARD) guidelines [ 44 ].…”

Current applications and development of artificial intelligence for digital dental radiography

“…Several ML method were used to develop automated diagnosis system of various dental diseases (e.g., dental caries, cracked teeth and periodontal bone loss) 118-120 and classification of various dental restoration. 121 On the other hand, DL was used to develop AI model using several dental radiography modality for automated diagnosis system common dental diseases 122 ; detect the presence of maxillary sinus pathologies [123][124][125] ; identification and classification of head and neck lymph node metastasis 126,127 ; detection and segmentation of the relationship between the mandibular canal and mandibular third molar position [128][129][130][131] ; detection of vertical root fracture 132,133 ; detection and classification of impacted maxillary supernumerary teeth 134 and mandibular third molar 135,136 ; classification of root morphology of the mandibular first molar 137 ; and diagnosis support in patients with Sjögren syndrome using CT images. 138 Considering the great potential of DL methods, the application and development will be greatly increased in near future.…”