Convolutional Neural Networks (CNNs) have long dominated image analysis in dentistry, reaching remarkable results in a range of different tasks. However, Transformer-based architectures, originally proposed for Natural Language Processing, are also promising for dental image analysis. The present study aimed to compare CNNs with Transformers for different image analysis tasks in dentistry. Two CNNs (U-Net, DeepLabV3+), two Hybrids (SwinUNETR, UNETR) and two Transformer-based architectures (TransDeepLab, SwinUnet) were compared on three dental segmentation tasks on different image modalities. Datasets consisted of (1) 1881 panoramic radiographs used for tooth segmentation, (2) 1625 bitewings used for tooth structure segmentation, and (3) 2689 bitewings for caries lesions segmentation. All models were trained and evaluated using 5-fold cross-validation. CNNs were found to be significantly superior over Hybrids and Transformer-based architectures for all three tasks. (1) Tooth segmentation showed mean±SD F1-Score of 0.89±0.009 for CNNs, 0.86±0.015 for Hybrids and 0.83±0.22 for Transformer-based architectures. (2) In tooth structure segmentation CNNs also outperformed with 0.85±0.008 compared to Hybrids 0.84±0.005 and Transformers 0.83±0.011. (3) Even more pronounced results were found for caries lesions segmentation; 0.49±0.031 for CNNs, 0.39±0.072 for Hybrids and 0.32±0.039 for Transformer-based architectures. CNNs significantly outperformed Transformer-based architectures and their Hybrids on three segmentation tasks (teeth, tooth structures, caries lesions) on varying dental data modalities (panoramic and bitewing radiographs). As deep-learning-based image analysis is part of modern dentistry, practitioners and dental researchers should be aware of strength and limitations of modern model architectures for dental-image analysis. Models that demonstrate optimal performance in other domains do not necessarily constitute the optimal selection for the purpose of dental imaging.

The imbalanced nature of real-world datasets is an ongoing challenge in the field of machine and deep learning. In medicine and in dentistry, most data samples represent patients not affected by pathologies, and on imagery, pathologic image areas are often smaller than healthy ones. Selecting suitable loss functions during deep learning is essential and may help to overcome the resulting imbalance. We assessed six different loss functions for one exemplary task, tooth structure segmentation on bitewing radiographs, for their performance. Six different loss functions (Focal Loss, Dice Loss, Tversky Loss and hybrid losses of Cross-Entropy and Dice Loss, Focal and Dice Loss, Focal and Generalized Dice Loss) were compared on a tooth structure segmentation task of 1,625 bitewing radiographs. Training was performed using three different model architectures (U-Net, Linknet, DeepLavbV3+) over a 5-fold cross-validation. Tooth structures consisted of the classes (occurrence in% of samples/captures areas measured on pixel level) enamel (100 %/25 %), dentin (100 %/50 %), root canal (100 %/10 %), filling (81 %/8 %) and crown (28 %/5 %). Hybrid loss functions significantly outperformed standalone ones and provided robust results over the different architectures for the classes enamel, dentin, root canal and filling. Specifically, the Dice Focal loss reached high performance to conquer both image level and pixel level class imbalance, respectively. In dental use cases it is often important to predict minority classes such as pathologies accurately. Using specific loss function may be an effective strategy to overcome data imbalance when training deep learning models.

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.

(1) Background: We aimed to identify factors associated with the presence of apical lesions (AL) in panoramic radiographs and to evaluate the predictive value of the identified factors. (2) Methodology: Panoramic radiographs from 1071 patients (age: 11–93 a, mean: 50.6 a ± 19.7 a) with 27,532 teeth were included. Each radiograph was independently assessed by five experienced dentists for AL. A range of shallow machine learning algorithms (logistic regression, k-nearest neighbor, decision tree, random forest, support vector machine, adaptive and gradient boosting) were employed to identify factors at both the patient and tooth level associated with AL and to predict AL. (3) Results: AL were detected in 522 patients (48.7%) and 1133 teeth (4.1%), whereas males showed a significantly higher prevalence than females (52.5%/44.8%; p < 0.05). Logistic regression found that an existing root canal treatment was the most important risk factor (adjusted Odds Ratio 16.89; 95% CI: 13.98–20.41), followed by the tooth type ‘molar’ (2.54; 2.1–3.08) and the restoration with a crown (2.1; 1.67–2.63). Associations between factors and AL were stronger and accuracy higher when using fewer complex models like decision tree (F1 score: 0.9 (0.89–0.9)). (4) Conclusions: The presence of AL was higher in root-canal treated teeth, those with crowns and molars. More complex machine learning models did not outperform less-complex ones.

Objectives: We assessed the costs of dental services in statutorily insured, very old (geriatric) Germans. Methods: A comprehensive sample of very old (≥75 years) people insured at a large Northeastern statutory insurer was followed over 6 years (2012–2017). We assessed dental services costs for: (1) examination, assessments and advice, (2) operative, (3) surgical, (4) prosthetic, (5) periodontal, (6) preventive and (7) outreach services. Association of utilization with: (1) sex, (2) age, (3) region, (4) social hardship status, (5) International Disease Classification (ICD-10) diagnoses and (6) Diagnoses Related Groups (DRGs) was explored. Results: 404,610 individuals with a mean (standard deviation, SD) age 81.9 (5.4 years) were followed, 173,733 did not survive follow-up. Total mean costs were 129.61 (310.97) euro per capita; the highest costs were for prosthetic (54.40, SD 242.89 euro) and operative services (28.40, SD 68.38 euro), examination/advice (21.15, SD 28.77 euro), prevention (13.31, SD 49.79 euro), surgery (5.91, SD 23.91 euro), outreach (4.81, SD 28.56 euro) and periodontal services (1.64, SD 7.39 euro). The introduction of new fee items for outreach and preventive services between 2012 and 2017 was reflected in costs. Total costs decreased with increasing age, and this was also found for all service blocks except outreach and preventive services. Costs were higher in those with social hardship status, and in Berlin than Brandenburg and Mecklenburg-Western Pomerania. Certain general health conditions were associated with increased or decreased costs. Conclusions: Costs were associated with sex, social hardship status, place of living and general health conditions. Clinical significance: Dental services costs for the elderly in Germany are unequally distributed and, up to a certain age or health status, generated by invasive interventions mainly. Policy makers should incentivize preventive services earlier on and aim to distribute expenses more equally.

(1) Background: We aimed to identify factors associated with the presence of apical lesions (AL) on panoramic radiographs and to evaluate the predictive value of the identified factors. (2) Methodology: Panoramic radiographs from 1071 patients (age: 11-93 a, mean: 50.6 a ± 19.7 a) with 27532 teeth were included. Each radiograph was independently assessed by five experienced dentists for AL. A range of shallow machine learning algorithms (logistic regression, k-nearest neighbor, decision tree, random forest, support vector machine, adaptive and gradient boosting) were employed to identify factors on patient and tooth level associated with AL and to predict AL. (3) Results: AL were detected in 522 patients (48.7%) and 1133 teeth (4.1%), whereas males showed a significantly higher prevalence than females (52.5%/44.8%; p<0.05). Logistic regression found that an existing root canal treatment was the most important risk factor (adjusted Odds Ratio 16.89; 95% CI: 13.98-20.41), followed by the tooth type ‘molar’ (2.54; 2.1-3.08) and the restoration with a crown (2.1; 1.67-2.63). Associations between factors and AL were stronger and accuracy higher when using less complex models like decision tree (F1 score: 0.9 (0.89-0.9)). (4) Conclusions: The presence of AL was higher in root-canal treated teeth, those with crowns and molars. More complex machine learning models did not outperform less complex ones.