Artificial intelligence in dental research: Checklist for authors, reviewers, readers

Schwendicke, Falk; Singh, Tarry; Lee, Jae Hong; Gaudin, Robert; Chaurasia, Akhilanand; Wiegand, Thomas; Uribe, Sergio; Krois, Joachim

doi:10.1016/j.jdent.2021.103610

Cited by 177 publications

(113 citation statements)

References 15 publications

Supporting

Mentioning

110

Contrasting

Unclassified

Order By: Relevance

“…AI models are bringing greater efficiency and accuracy, capitalizing on the interest, capabilities, and skills of those involved [ 48 ]. Effective and efficient interprofessional and clinician-patient interactions have evolved using these new ways, with AI students have new ways of learning through research and the data collected can be efficiently utilized for forensic and epidemiological uses [ 49 , 50 ]. Extensive research has been carried out on the application, benefits, and comparison of AI with human skills around the globe.…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence Techniques: Analysis, Application, and Outcome in Dentistry—A Systematic Review

Ahmed

Abbasi

Zuberi

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

Objective. The objective of this systematic review was to investigate the quality and outcome of studies into artificial intelligence techniques, analysis, and effect in dentistry. Materials and Methods. Using the MeSH keywords: artificial intelligence (AI), dentistry, AI in dentistry, neural networks and dentistry, machine learning, AI dental imaging, and AI treatment recommendations and dentistry. Two investigators performed an electronic search in 5 databases: PubMed/MEDLINE (National Library of Medicine), Scopus (Elsevier), ScienceDirect databases (Elsevier), Web of Science (Clarivate Analytics), and the Cochrane Collaboration (Wiley). The English language articles reporting on AI in different dental specialties were screened for eligibility. Thirty-two full-text articles were selected and systematically analyzed according to a predefined inclusion criterion. These articles were analyzed as per a specific research question, and the relevant data based on article general characteristics, study and control groups, assessment methods, outcomes, and quality assessment were extracted. Results. The initial search identified 175 articles related to AI in dentistry based on the title and abstracts. The full text of 38 articles was assessed for eligibility to exclude studies not fulfilling the inclusion criteria. Six articles not related to AI in dentistry were excluded. Thirty-two articles were included in the systematic review. It was revealed that AI provides accurate patient management, dental diagnosis, prediction, and decision making. Artificial intelligence appeared as a reliable modality to enhance future implications in the various fields of dentistry, i.e., diagnostic dentistry, patient management, head and neck cancer, restorative dentistry, prosthetic dental sciences, orthodontics, radiology, and periodontics. Conclusion. The included studies describe that AI is a reliable tool to make dental care smooth, better, time-saving, and economical for practitioners. AI benefits them in fulfilling patient demand and expectations. The dentists can use AI to ensure quality treatment, better oral health care outcome, and achieve precision. AI can help to predict failures in clinical scenarios and depict reliable solutions. However, AI is increasing the scope of state-of-the-art models in dentistry but is still under development. Further studies are required to assess the clinical performance of AI techniques in dentistry.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence Techniques: Analysis, Application, and Outcome in Dentistry—A Systematic Review

Ahmed

Abbasi

Zuberi

et al. 2021

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…We further visualized the salient areas of the images that had most importance in the models' output, i.e., by leveraging XAI. Reporting of this study follows the Standards for Reporting of Diagnostic Accuracy Studies (STARD) guidelines [5], the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) [6], and the Checklist for Artificial Intelligence in Dental Research [7].…”

Section: Methodsmentioning

confidence: 99%

Classification of Dental Radiographs Using Deep Learning

Cejudo

Chaurasia

Feldberg

et al. 2021

JCM

Self Cite

View full text Add to dashboard Cite

Objectives: To retrospectively assess radiographic data and to prospectively classify radiographs (namely, panoramic, bitewing, periapical, and cephalometric images), we compared three deep learning architectures for their classification performance. Methods: Our dataset consisted of 31,288 panoramic, 43,598 periapical, 14,326 bitewing, and 1176 cephalometric radiographs from two centers (Berlin/Germany; Lucknow/India). For a subset of images L (32,381 images), image classifications were available and manually validated by an expert. The remaining subset of images U was iteratively annotated using active learning, with ResNet-34 being trained on L, least confidence informative sampling being performed on U, and the most uncertain image classifications from U being reviewed by a human expert and iteratively used for re-training. We then employed a baseline convolutional neural networks (CNN), a residual network (another ResNet-34, pretrained on ImageNet), and a capsule network (CapsNet) for classification. Early stopping was used to prevent overfitting. Evaluation of the model performances followed stratified k-fold cross-validation. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to provide visualizations of the weighted activations maps. Results: All three models showed high accuracy (>98%) with significantly higher accuracy, F1-score, precision, and sensitivity of ResNet than baseline CNN and CapsNet (p < 0.05). Specificity was not significantly different. ResNet achieved the best performance at small variance and fastest convergence. Misclassification was most common between bitewings and periapicals. For bitewings, model activation was most notable in the inter-arch space for periapicals interdentally, for panoramics on bony structures of maxilla and mandible, and for cephalometrics on the viscerocranium. Conclusions: Regardless of the models, high classification accuracies were achieved. Image features considered for classification were consistent with expert reasoning.

show abstract

“…The Mann-Kendall (M-K) test was employed to evaluate the impact of context information on the classification performance [8]. Reporting of this study follows the STARD guideline [9] and the Checklist for Artificial Intelligence in Dental Research [10].…”

Section: Methodsmentioning

confidence: 99%

Impact of Image Context on Deep Learning for Classification of Teeth on Radiographs

Krois

Schneider

Schwendicke

2021

JCM

Self Cite

View full text Add to dashboard Cite

Objectives: We aimed to assess the impact of image context information on the accuracy of deep learning models for tooth classification on panoramic dental radiographs. Methods: Our dataset contained 5008 panoramic radiographs with a mean number of 25.2 teeth per image. Teeth were segmented bounding-box-wise and classified by one expert; this was validated by another expert. Tooth segments were cropped allowing for different context; the baseline size was 100% of each box and was scaled up to capture 150%, 200%, 250% and 300% to increase context. On each of the five generated datasets, ResNet-34 classification models were trained using the Adam optimizer with a learning rate of 0.001 over 25 epochs with a batch size of 16. A total of 20% of the data was used for testing; in subgroup analyses, models were tested only on specific tooth types. Feature visualization using gradient-weighted class activation mapping (Grad-CAM) was employed to visualize salient areas. Results: F1-scores increased monotonically from 0.77 in the base-case (100%) to 0.93 on the largest segments (300%; p = 0.0083; Mann–Kendall-test). Gains in accuracy were limited between 200% and 300%. This behavior was found for all tooth types except canines, where accuracy was much higher even for smaller segments and increasing context yielded only minimal gains. With increasing context salient areas were more widely distributed over each segment; at maximum segment size, the models assessed minimum 3–4 teeth as well as the interdental or inter-arch space to come to a classification. Conclusions: Context matters; classification accuracy increased significantly with increasing context.

show abstract

Artificial intelligence in dental research: Checklist for authors, reviewers, readers

Cited by 177 publications

References 15 publications

Artificial Intelligence Techniques: Analysis, Application, and Outcome in Dentistry—A Systematic Review

Artificial Intelligence Techniques: Analysis, Application, and Outcome in Dentistry—A Systematic Review

Classification of Dental Radiographs Using Deep Learning

Impact of Image Context on Deep Learning for Classification of Teeth on Radiographs

Contact Info

Product

Resources

About