Variables influencing the device-dependent approaches in digitally analysing jaw movement—a systematic review

Farook, Taseef Hasan; Rashid, Farah; Alam, Mohammad Khursheed; Dudley, James

doi:10.1007/s00784-022-04835-w

Cited by 23 publications

(28 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In both cases, the sensitivity and specificity were above 90%. If oral photographs were collected as data from 100 clinics, there would likely be over a thousand variations from a lack of image standardisation alone [ 15 ].…”

Section: Discussionmentioning

confidence: 99%

“…To date, image standardisation has been a serious limitation in digital dentistry, owing to geographic variations in ambient light, operator-induced errors, and availability of high-end imaging hardware [ 10 , 15 ]. Said variables can rarely be addressed in rural clinics with limited resources, thereby limiting the possibilities of automated diagnostics and advanced tele-dentistry applications.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Visual Diagnostics of Dental Caries through Deep Learning of Non-Standardised Photographs Using a Hybrid YOLO Ensemble and Transfer Learning Model

Tareq

Faisal

Islam

et al. 2023

IJERPH

Self Cite

View full text Add to dashboard Cite

Background: Access to oral healthcare is not uniform globally, particularly in rural areas with limited resources, which limits the potential of automated diagnostics and advanced tele-dentistry applications. The use of digital caries detection and progression monitoring through photographic communication, is influenced by multiple variables that are difficult to standardize in such settings. The objective of this study was to develop a novel and cost-effective virtual computer vision AI system to predict dental cavitations from non-standardised photographs with reasonable clinical accuracy. Methods: A set of 1703 augmented images was obtained from 233 de-identified teeth specimens. Images were acquired using a consumer smartphone, without any standardised apparatus applied. The study utilised state-of-the-art ensemble modeling, test-time augmentation, and transfer learning processes. The “you only look once” algorithm (YOLO) derivatives, v5s, v5m, v5l, and v5x, were independently evaluated, and an ensemble of the best results was augmented, and transfer learned with ResNet50, ResNet101, VGG16, AlexNet, and DenseNet. The outcomes were evaluated using precision, recall, and mean average precision (mAP). Results: The YOLO model ensemble achieved a mean average precision (mAP) of 0.732, an accuracy of 0.789, and a recall of 0.701. When transferred to VGG16, the final model demonstrated a diagnostic accuracy of 86.96%, precision of 0.89, and recall of 0.88. This surpassed all other base methods of object detection from free-hand non-standardised smartphone photographs. Conclusion: A virtual computer vision AI system, blending a model ensemble, test-time augmentation, and transferred deep learning processes, was developed to predict dental cavitations from non-standardised photographs with reasonable clinical accuracy. This model can improve access to oral healthcare in rural areas with limited resources, and has the potential to aid in automated diagnostics and advanced tele-dentistry applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Visual Diagnostics of Dental Caries through Deep Learning of Non-Standardised Photographs Using a Hybrid YOLO Ensemble and Transfer Learning Model

Tareq

Faisal

Islam

et al. 2023

IJERPH

Self Cite

View full text Add to dashboard Cite

show abstract

“…84 Additionally, mandibular and condylar growth, kinematic dysfunction of the neuromuscular system, shortened dental arches, previous orthodontic treatment, variations in habitual head posture, temporomandibular joint disorders, fricative phonetics, and to a limited extent, parafunctional habits and unbalanced occlusal contact were identified as confounding variables that shaped jaw movement trajectories, but were not highly dependent on age, gender, or diet. 84 Li et al 31 evaluated the accuracy of an experimental jaw tracking system. A maxillary and mandibular complete denture mounted on a semi-adjustable articulator were used to perform small opening and excursive movements.…”

Section: Digital Jaw Tracking Systemsmentioning

confidence: 99%

“…84 The authors concluded that realistic variations in jaw tracking device accuracy ranged from 50 to 330 μm across the digital systems with very low interoperator reliability for motion tracking from photographs. 84 Additionally, mandibular and condylar growth, kinematic dysfunction of the neuromuscular system, shortened dental arches, previous orthodontic treatment, variations in habitual head posture, temporomandibular joint disorders, fricative phonetics, and to a limited extent, parafunctional habits and unbalanced occlusal contact were identified as confounding variables that shaped jaw movement trajectories, but were not highly dependent on age, gender, or diet. 84 Li et al 31 evaluated the accuracy of an experimental jaw tracking system.…”

Section: Digital Jaw Tracking Systemsmentioning

confidence: 99%

An overview of the digital occlusion technologies: Intraoral scanners, jaw tracking systems, and computerized occlusal analysis devices

Revilla‐León

Kois

Zeitler³

et al. 2023

J Esthet Restor Dent

View full text Add to dashboard Cite

Objectives Within the development of digital technologies, dental professionals aim to integrate virtual diagnostic articulated casts obtained by using intraoral scanners (IOSs), the mandibular motion of the patient recorded by using an optical jaw tracking system, and the information provided by computerized occlusal analysis systems. This article describes the various digital technologies available for obtaining the digital occlusion of a patient and outlines its challenges and limitations. Overview The factors that influence the accuracy of the maxillomandibular relationship of diagnostic casts obtained by using IOSs are reviewed, as well as the occurrence of occlusal collisions or mesh interpenetrations. Different jaw tracking systems with varying digital technologies including ultrasonic systems, photometric devices, and artificial intelligence algorithms are reviewed. Computerized occlusal analysis systems for detecting occlusal contacts in a time sequential manner with the pressure distribution on the occlusal surfaces are reviewed. Conclusions Digital technologies provide powerful diagnostic and design tools for prosthodontic care. However, the accuracy of these digital technologies for acquiring and analyzing the static and dynamic occlusion need to be further analyzed. Clinical Significance Efficiently implementing digital technologies into dental practice requires an understanding of the limitations and state of current development of the digital acquisition methods for digitizing the static and dynamic occlusion of a patient by using IOSs, digital jaw trackers, and computerized occlusal analysis devices.

show abstract

“…Supervised learning occurs when the radiomic data are labelled by human operators prior to AI training while un‐supervised learning is when the AI is capable of training with the data without human intervention 5 . Successful implementation of deep learning in clinical dentistry is primarily seen in supervised or partially unsupervised (semi‐supervised) learning owing to numerous clinical and hardware‐dependent variables, that are yet to be fully understood 6–8 …”

Section: Introductionmentioning

confidence: 99%

Automation and deep (machine) learning in temporomandibular joint disorder radiomics: A systematic review

Farook

Dudley

2023

J of Oral Rehabilitation

Self Cite

View full text Add to dashboard Cite

Objective This review aimed to systematically analyse the influence of clinical variables, diagnostic parameters and the overall image acquisition process on automation and deep learning in TMJ disorders. Methods Articles were screened in late 2022 according to a predefined eligibility criteria adhering to the PRISMA protocol. Eligible studies were extracted from databases hosted by MEDLINE, EBSCOHost, Scopus, PubMed and Web of Science. Critical appraisals were performed on individual studies following Nature Medicine's MI‐CLAIM checklist while a combined appraisal of the image acquisition procedures was conducted using Cochrane's GRADE approach. Results Twenty articles were included for full review following eligibility screening. The average experience possessed by the clinical operators within the eligible studies was 13.7 years. Bone volume, trabecular number and separation, and bone surface‐to‐volume ratio were clinical radiographic parameters while disc shape, signal intensity, fluid collection, joint space narrowing and arthritic changes were successful parameters used in MRI‐based deep machine learning. Entropy was correlated to sclerosis in CBCT and was the most stable radiomic parameter in MRI while contrast was the least stable across thermography and MRI. Adjunct serum and salivary biomarkers, or clinical questionnaires only marginally improved diagnostic outcomes through deep learning. Substantial data was classified as unusable and subsequently discarded owing to a combination of suboptimal image acquisition and data augmentation procedures. Inadequate identification of the participant characteristics and multiple studies utilising the same dataset and data acquisition procedures accounted for serious risks of bias. Conclusion Deep‐learned models diagnosed osteoarthritis as accurately as clinicians from 2D and 3D radiographs but, in comparison, performed poorly when detecting disc disorders from MRI datasets. Complexities in clinical classification criteria; non‐standardised diagnostic parameters; errors in image acquisition; cognitive, contextual or implicit biases were influential variables that generally affected analyses of inflammatory joint changes and disc disorders.

show abstract

Variables influencing the device-dependent approaches in digitally analysing jaw movement—a systematic review

Cited by 23 publications

References 46 publications

Visual Diagnostics of Dental Caries through Deep Learning of Non-Standardised Photographs Using a Hybrid YOLO Ensemble and Transfer Learning Model

Visual Diagnostics of Dental Caries through Deep Learning of Non-Standardised Photographs Using a Hybrid YOLO Ensemble and Transfer Learning Model

An overview of the digital occlusion technologies: Intraoral scanners, jaw tracking systems, and computerized occlusal analysis devices

Automation and deep (machine) learning in temporomandibular joint disorder radiomics: A systematic review

Contact Info

Product

Resources

About