Machine Learning in Dentistry: A Scoping Review

Arsiwala, Lubaina Tayeb; Chaurasia, Akhilanand; Müller, Anne; Krois, Joachim; Schwendicke, Falk

doi:10.3390/jcm12030937

Cited by 31 publications

(16 citation statements)

References 185 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to eliminate any biases that might cause a negative effect on the generalizability [ 79 ], the whole OPG database of the faculty of dentistry, a total of 8138 OPGs that were acquired by 3 different OPG devices, were obtained from the archive of the Near East University, Department of Dentomaxillofacial Radiology.…”

Section: Methodsmentioning

confidence: 99%

Automatic Segmentation of Teeth, Crown–Bridge Restorations, Dental Implants, Restorative Fillings, Dental Caries, Residual Roots, and Root Canal Fillings on Orthopantomographs: Convenience and Pitfalls

et al. 2023

View full text Add to dashboard Cite

Background: The aim of our study is to provide successful automatic segmentation of various objects on orthopantomographs (OPGs). Methods: 8138 OPGs obtained from the archives of the Department of Dentomaxillofacial Radiology were included. OPGs were converted into PNGs and transferred to the segmentation tool’s database. All teeth, crown–bridge restorations, dental implants, composite–amalgam fillings, dental caries, residual roots, and root canal fillings were manually segmented by two experts with the manual drawing semantic segmentation technique. Results: The intra-class correlation coefficient (ICC) for both inter- and intra-observers for manual segmentation was excellent (ICC > 0.75). The intra-observer ICC was found to be 0.994, while the inter-observer reliability was 0.989. No significant difference was detected amongst observers (p = 0.947). The calculated DSC and accuracy values across all OPGs were 0.85 and 0.95 for the tooth segmentation, 0.88 and 0.99 for dental caries, 0.87 and 0.99 for dental restorations, 0.93 and 0.99 for crown–bridge restorations, 0.94 and 0.99 for dental implants, 0.78 and 0.99 for root canal fillings, and 0.78 and 0.99 for residual roots, respectively. Conclusions: Thanks to faster and automated diagnoses on 2D as well as 3D dental images, dentists will have higher diagnosis rates in a shorter time even without excluding cases.

show abstract

Section: Methodsmentioning

confidence: 99%

Automatic Segmentation of Teeth, Crown–Bridge Restorations, Dental Implants, Restorative Fillings, Dental Caries, Residual Roots, and Root Canal Fillings on Orthopantomographs: Convenience and Pitfalls

et al. 2023

View full text Add to dashboard Cite

show abstract

“…AI is currently under investigation in dentistry for a range of purposes, with a particular focus on identifying normal and abnormal structures, diagnosing diseases, and forecasting treatment results [ 10 ]. Moreover, machine learning (ML) has been utilized for various tasks in dentistry, utilizing diverse methodologies and utilizing vastly different reporting metrics [ 35 ]. AI can be used by dental professionals as an extra tool to decrease their workload and enhance the precision and accuracy of diagnosis, decision-making, treatment planning, prediction of treatment outcomes, and disease prognosis [ 36 ].…”

Section: Reviewmentioning

confidence: 99%

ChatGPT in Dentistry: A Comprehensive Review

Alhaidry¹,

Fatani²,

Alrayes³

et al. 2023

Cureus

View full text Add to dashboard Cite

Chat generative pre-trained transformer (ChatGPT) is an artificial intelligence chatbot that uses natural language processing that can respond to human input in a conversational manner. ChatGPT has numerous applications in the health care system including dentistry; it is used in diagnoses and for assessing disease risk and scheduling appointments. It also has a role in scientific research. In the dental field, it has provided many benefits such as detecting dental and maxillofacial abnormalities on panoramic radiographs and identifying different dental restorations. Therefore, it helps in decreasing the workload. But even with these benefits, one should take into consideration the risks and limitations of this chatbot. Few articles mentioned the use of ChatGPT in dentistry. This comprehensive review represents data collected from 66 relevant articles using PubMed and Google Scholar as databases. This review aims to discuss all relevant published articles on the use of ChatGPT in dentistry.

show abstract

“…In natural scenes of images this seems to be a relatively easy task for annotators as humans process such visual data without actively thinking about it. However, object detection has long moved beyond natural image scenes and has become an important component of medical image analysis [1,2].…”

Section: Introductionmentioning

confidence: 99%

Impact of Noisy Labels on Dental Deep Learning—Calculus Detection on Bitewing Radiographs

Duchrau

Schneider

Krasowski

et al. 2023

JCM

Self Cite

View full text Add to dashboard Cite

Supervised deep learning requires labelled data. On medical images, data is often labelled inconsistently (e.g., too large) with varying accuracies. We aimed to assess the impact of such label noise on dental calculus detection on bitewing radiographs. On 2584 bitewings calculus was accurately labeled using bounding boxes (BBs) and artificially increased and decreased stepwise, resulting in 30 consistently and 9 inconsistently noisy datasets. An object detection network (YOLOv5) was trained on each dataset and evaluated on noisy and accurate test data. Training on accurately labeled data yielded an mAP50: 0.77 (SD: 0.01). When trained on consistently too small BBs model performance significantly decreased on accurate and noisy test data. Model performance trained on consistently too large BBs decreased immediately on accurate test data (e.g., 200% BBs: mAP50: 0.24; SD: 0.05; p < 0.05), but only after drastically increasing BBs on noisy test data (e.g., 70,000%: mAP50: 0.75; SD: 0.01; p < 0.05). Models trained on inconsistent BB sizes showed a significant decrease of performance when deviating 20% or more from the original when tested on noisy data (mAP50: 0.74; SD: 0.02; p < 0.05), or 30% or more when tested on accurate data (mAP50: 0.76; SD: 0.01; p < 0.05). In conclusion, accurate predictions need accurate labeled data in the training process. Testing on noisy data may disguise the effects of noisy training data. Researchers should be aware of the relevance of accurately annotated data, especially when testing model performances.

show abstract

Machine Learning in Dentistry: A Scoping Review

Cited by 31 publications

References 185 publications

Automatic Segmentation of Teeth, Crown–Bridge Restorations, Dental Implants, Restorative Fillings, Dental Caries, Residual Roots, and Root Canal Fillings on Orthopantomographs: Convenience and Pitfalls

Automatic Segmentation of Teeth, Crown–Bridge Restorations, Dental Implants, Restorative Fillings, Dental Caries, Residual Roots, and Root Canal Fillings on Orthopantomographs: Convenience and Pitfalls

ChatGPT in Dentistry: A Comprehensive Review

Impact of Noisy Labels on Dental Deep Learning—Calculus Detection on Bitewing Radiographs

Contact Info

Product

Resources

About