Deep Convolutional Neural Networks Based Analysis of Cephalometric Radiographs for Differential Diagnosis of Orthognathic Surgery Indications

Abstract

The aim of this study was to evaluate the deep convolutional neural networks (DCNNs) based on analysis of cephalometric radiographs for the differential diagnosis of the indications of orthognathic surgery. Among the DCNNs, Modified-Alexnet, MobileNet, and Resnet50 were used, and the accuracy of the models was evaluated by performing 4-fold cross validation. Additionally, gradient-weighted class activation mapping (Grad-CAM) was used to perform visualized interpretation to determine which region affected the DCNNs’ class classification. The prediction accuracy of the models was 96.4% for Modified-Alexnet, 95.4% for MobileNet, and 95.6% for Resnet50. According to the Grad-CAM analysis, the most influential regions for the DCNNs’ class classification were the maxillary and mandibular teeth, mandible, and mandibular symphysis. This study suggests that DCNNs-based analysis of cephalometric radiograph images can be successfully applied for differential diagnosis of the indications of orthognathic surgery.

Using deep learning to predict temporomandibular joint disc perforation based on magnetic resonance imaging

“…Yang et al reported favorable result for automated detection of cyst and tumor of the jaw in panoramic images 13 . Lee et al reported that cephalometric images can be applied for differential diagnosis of orthognathic surgery and orthodontic treatment based on deep convolutional neural networks with 95.4 ~ 96.4% success rate 14 . More recently, there are many attempts for diagnosis of osteoarthritis of the temporomandibular joint based on cone-beam computed tomographic image using machine learning 15 , 16 .…”

A Deep Learning Approach For Dental Implant Planning On Cone-Beam Computed Tomography Images

“…In recent years, arti cial intelligence systems have been used to support decision making processes in the diagnosis and treatment planning of physicians. The neural network machine learning system was used in various treatment plans such as radiation therapy and orthognathic surgery and promising results were obtained [40][41][42]. As it is known, radiographic imaging plays an important role in the planning of dental implants.…”

Dental Characteristics of Different Types of Cleft and Non-cleft Individuals

“…examination in such gatherings and populace is yet to be researched. Irrelevant mistake in the estimations; exact, automated, basic, brisk, savvy, future orthodontic computerized apparatuses; and different types of cleft examples are the novelty of the current examination ( Lee et al, 2020 ; Kunz et al, 2020 ). The current investigation results may help the clinician in approaching where the impacts of essential CLP medical procedures are on various DC, supporting the restoration procedure in subjects with various sorts of NSCLP in building up a positive administration convention.…”

“…Oral clefts show an assortment of clinical inconsistencies ( Batwa et al, 2018 ). Lee et al (2020) and Kunz et al (2020) uncovered artificial intelligence (A.I.) into dentistry, particularly in orthodontics ready to break down obscure Late.…”

“…at nearly a similar quality level as the ongoing highest-quality level estimated by a calibrated specialist. Lee et al (2020) used A.I.-driven profound convolutional neural system-based assessment of Late. Ceph.…”