Deep-learning systems for diagnosing cleft palate on panoramic radiographs in patients with cleft alveolus

Objectives The aim of the present study was to create effective deep learning-based models for diagnosing the presence or absence of cleft palate (CP) in patients with unilateral or bilateral cleft alveolus (CA) on panoramic radiographs. Methods The panoramic images of 491 patients who had unilatera...

Full description

Saved in:
Bibliographic Details
Published in:Oral radiology 2023-04, Vol.39 (2), p.349-354
Main Authors: Kuwada, Chiaki, Ariji, Yoshiko, Kise, Yoshitaka, Fukuda, Motoki, Nishiyama, Masako, Funakoshi, Takuma, Takeuchi, Rihoko, Sana, Airi, Kojima, Norinaga, Ariji, Eiichiro
Format: Article
Language:English
Subjects:
Alveoli
Birth defects
Classification
Cleft lip/palate
Cleft Palate - diagnostic imaging
Deep Learning
Dentistry
Humans
Imaging
Incisor
Medical diagnosis
Medicine
Oral and Maxillofacial Surgery
Original
Original Article
Radiography
Radiography, Panoramic
Radiology
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Objectives The aim of the present study was to create effective deep learning-based models for diagnosing the presence or absence of cleft palate (CP) in patients with unilateral or bilateral cleft alveolus (CA) on panoramic radiographs. Methods The panoramic images of 491 patients who had unilateral or bilateral cleft alveolus were used to create two models. Model A, which detects the upper incisor area on panoramic radiographs and classifies the areas into the presence or absence of CP, was created using both object detection and classification functions of DetectNet. Using the same data for developing Model A, Model B, which directly classifies the presence or absence of CP on panoramic radiographs, was created using classification function of VGG-16. The performances of both models were evaluated with the same test data and compared with those of two radiologists. Results The recall, precision, and F-measure were all 1.00 in Model A. The area under the receiver operating characteristic curve (AUC) values were 0.95, 0.93, 0.70, and 0.63 for Model A, Model B, and the radiologists, respectively. The AUCs of the models were significantly higher than those of the radiologists. Conclusions The deep learning-based models developed in the present study have potential for use in supporting observer interpretations of the presence of cleft palate on panoramic radiographs.
ISSN:0911-6028
1613-9674
DOI:10.1007/s11282-022-00644-9