Performance of deep learning technology for evaluation of positioning quality in periapical radiography of the maxillary canine

Abstract

Objectives The aim of the present study was to create and test an automatic system for assessing the technical quality of positioning in periapical radiography of the maxillary canines using deep learning classification and segmentation techniques. Methods We created and tested two deep learning systems using 500 periapical radiographs (250 each of good- and bad-quality images). We assigned 350, 70, and 80 images as the training, validation, and test datasets, respectively. The learning model of system 1 was created with only the classification process, whereas system 2 consisted of both the segmentation and classification models. In each model, 500 epochs of training were performed using AlexNet and U-net for classification and segmentation, respectively. The segmentation results were evaluated by the intersection over union method, with values of 0.6 or more considered as success. The classification results were compared between the two systems. Results The segmentation performance of system 2 was recall, precision, and F measure of 0.937, 0.961, and 0.949, respectively. System 2 showed better classification performance values than those obtained by system 1. The area under the receiver operating characteristic curve values differed significantly between system 1 (0.649) and system 2 (0.927). Conclusions The deep learning systems we created appeared to have potential benefits in evaluation of the technical positioning quality of periapical radiographs through the use of segmentation and classification functions.

Deep learning and artificial intelligence in dental diagnostic imaging

“…Several studies have applied segmentation tasks to improve the accuracies of classification tasks. Mori et al [29] reported that in the classification task to determine whether a periapical radiograph was taken in the appropriate geometric position, the task's accuracy was improved by preliminary segmentation of the tooth that should be located in the centre of the image.…”

Untitled

“…The presence and size of a dental follicle will be highlighted, and it will be confirmed if there is coronal or root resorption, as well as the root pattern and integrity of the included tooth. Also, any obstruction present in the eruption path, supernumerary teeth, cysts, or different types of odontomas can be identified [18].…”

A Scoping Review of Machine Learning in Dental Radiography: Its Current Applications and Relevance in Dentistry

“…In the restorative section, the number of included papers were ve. With two relating to caries identi cation 39,40 , one involving the presence of a mandibular C Shaped canal 41 , one involving apical lesions 42 and the nal one relating to positioning quality of periapical radiographs 43 .…”

“…Mori et al 43 investigated the performance of an AI model in assessing the positioning quality of periapical maxillary canine radiographs. Two systems were compared, one only including classi cation (AlexNet) and the other including classi cation and segmentation (U-Net).…”