An artifıcial ıntelligence approach to automatic tooth detection and numbering in panoramic radiographs

Abstract

Background Panoramic radiography is an imaging method for displaying maxillary and mandibular teeth together with their supporting structures. Panoramic radiography is frequently used in dental imaging due to its relatively low radiation dose, short imaging time, and low burden to the patient. We verified the diagnostic performance of an artificial intelligence (AI) system based on a deep convolutional neural network method to detect and number teeth on panoramic radiographs. Methods The data set included 2482 anonymized panoramic radiographs from adults from the archive of Eskisehir Osmangazi University, Faculty of Dentistry, Department of Oral and Maxillofacial Radiology. A Faster R-CNN Inception v2 model was used to develop an AI algorithm (CranioCatch, Eskisehir, Turkey) to automatically detect and number teeth on panoramic radiographs. Human observation and AI methods were compared on a test data set consisting of 249 panoramic radiographs. True positive, false positive, and false negative rates were calculated for each quadrant of the jaws. The sensitivity, precision, and F-measure values were estimated using a confusion matrix. Results The total numbers of true positive, false positive, and false negative results were 6940, 250, and 320 for all quadrants, respectively. Consequently, the estimated sensitivity, precision, and F-measure were 0.9559, 0.9652, and 0.9606, respectively. Conclusions The deep convolutional neural network system was successful in detecting and numbering teeth. Clinicians can use AI systems to detect and number teeth on panoramic radiographs, which may eventually replace evaluation by human observers and support decision making.

Comparison of detection performance of soft tissue calcifications using artificial intelligence in panoramic radiography

“…Several studies have reported that artificial intelligence helps in image reading, and that it helps clinicians 20,21 . In the field of dentistry, artificial intelligence research using panoramic photos has been actively conducted recently; most studies have been on tooth segmentation and tooth number matching [22][23][24] , detection of primary teeth 25 , and detection of taurodontism 26 , which is a tooth anomaly. Studies on artificial intelligence detection of osteoporosis in panoramic photos are also being actively conducted [27][28][29] .…”

A Convolutional Neural Network for Automatic Tooth Numbering in Panoramic Images

“…Bilgir et al [ 19 ] developed a Faster R-CNN to automatically number teeth on a database of 2,482 panoramic radiographs. This study achieved a precision of 0.9652.…”

A comprehensive artificial intelligence framework for dental diagnosis and charting

“…However, although these models have good performance in detecting abnormalities, they cannot recognize tooth numbers to provide detailed diagnostic information on individual teeth, therefore limiting the clinical application of these DL models. Recently, some DL models were developed to segment teeth [22], detect and assign tooth numbers on dental radiographs [23][24][25][26][27], diagnostic charting [28], or detect and classify each tooth into molar, premolar, canines, and incisors [29,30]. However, all of them were only applicable to panoramic radiographs [22][23][24][25][26][27][28][29][30].…”

“…Recently, some DL models were developed to segment teeth [22], detect and assign tooth numbers on dental radiographs [23][24][25][26][27], diagnostic charting [28], or detect and classify each tooth into molar, premolar, canines, and incisors [29,30]. However, all of them were only applicable to panoramic radiographs [22][23][24][25][26][27][28][29][30]. Furthermore, some studies have been conducted on detecting teeth and assigning tooth numbers in periapical radiographs [6,31,32] and bitewing radiographs [33,34].…”