Convolutional neural networks (CNNs) are increasingly applied for medical image diagnostics. We performed a scoping review, exploring (1) use cases, (2) methodologies and (3) findings of studies ...applying CNN on dental image material.
Medline via PubMed, IEEE Xplore, arXiv were searched.
Full-text articles and conference-proceedings reporting CNN application on dental imagery were included.
Thirty-six studies, published 2015-2019, were included, mainly from four countries (South Korea, United States, Japan, China). Studies focussed on general dentistry (n = 15 studies), cariology (n = 5), endodontics (n = 2), periodontology (n = 3), orthodontics (n = 3), dental radiology (2), forensic dentistry (n = 2) and general medicine (n = 4). Most often, the detection, segmentation or classification of anatomical structures, including teeth (n = 9), jaw bone (n = 2) and skeletal landmarks (n = 4) was performed. Detection of pathologies focused on caries (n = 3). The most commonly used image type were panoramic radiographs (n = 11), followed by periapical radiographs (n = 8), Cone-Beam CT or conventional CT (n = 6). Dataset sizes varied between 10–5,166 images (mean 1,053). Most studies used medical professionals to label the images and constitute the reference test. A large range of outcome metrics was employed, hampering comparisons across studies. A comparison of the CNN performance against an independent test group of dentists was provided by seven studies; most studies found the CNN to perform similar to dentists. Applicability or impact on treatment decision was not assessed at all.
CNNs are increasingly employed for dental image diagnostics in research settings. Their usefulness, safety and generalizability should be demonstrated using more rigorous, replicable and comparable methodology.
CNNs may be used in diagnostic-assistance systems, thereby assisting dentists in a more comprehensive, systematic and faster evaluation and documentation of dental images. CNNs may become applicable in routine care; however, prior to that, the dental community should appraise them against the rules of evidence-based practice.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
We applied deep convolutional neural networks (CNNs) to detect periodontal bone loss (PBL) on panoramic dental radiographs. We synthesized a set of 2001 image segments from panoramic radiographs. Our ...reference test was the measured % of PBL. A deep feed-forward CNN was trained and validated via 10-times repeated group shuffling. Model architectures and hyperparameters were tuned using grid search. The final model was a seven-layer deep neural network, parameterized by a total number of 4,299,651 weights. For comparison, six dentists assessed the image segments for PBL. Averaged over 10 validation folds the mean (SD) classification accuracy of the CNN was 0.81 (0.02). Mean (SD) sensitivity and specificity were 0.81 (0.04), 0.81 (0.05), respectively. The mean (SD) accuracy of the dentists was 0.76 (0.06), but the CNN was not statistically significant superior compared to the examiners (p = 0.067/t-test). Mean sensitivity and specificity of the dentists was 0.92 (0.02) and 0.63 (0.14), respectively. A CNN trained on a limited amount of radiographic image segments showed at least similar discrimination ability as dentists for assessing PBL on panoramic radiographs. Dentists' diagnostic efforts when using radiographs may be reduced by applying machine-learning based technologies.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
We applied deep convolutional neural networks (CNNs) to detect apical lesions (ALs) on panoramic dental radiographs.
Based on a synthesized data set of 2001 tooth segments from panoramic radiographs, ...a custom-made 7-layer deep neural network, parameterized by a total number of 4,299,651 weights, was trained and validated via 10 times repeated group shuffling. Hyperparameters were tuned using a grid search. Our reference test was the majority vote of 6 independent examiners who detected ALs on an ordinal scale (0, no AL; 1, widened periodontal ligament, uncertain AL; 2, clearly detectable lesion, certain AL). Metrics were the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and positive/negative predictive values. Subgroup analysis for tooth types was performed, and different margins of agreement of the reference test were applied (base case: 2; sensitivity analysis: 6).
The mean (standard deviation) tooth level prevalence of both uncertain and certain ALs was 0.16 (0.03) in the base case. The AUC of the CNN was 0.85 (0.04). Sensitivity and specificity were 0.65 (0.12) and 0.87 (0.04,) respectively. The resulting positive predictive value was 0.49 (0.10), and the negative predictive value was 0.93 (0.03). In molars, sensitivity was significantly higher than in other tooth types, whereas specificity was lower. When only certain ALs were assessed, the AUC was 0.89 (0.04). Increasing the margin of agreement to 6 significantly increased the AUC to 0.95 (0.02), mainly because the sensitivity increased to 0.74 (0.19).
A moderately deep CNN trained on a limited amount of image data showed satisfying discriminatory ability to detect ALs on panoramic radiographs.
•Apical lesions (ALs) were detected on panoramic radiographs using neural networks.•A 7-layer deep network was trained on a limited amount of image segments.•The network showed high specificity and moderate sensitivity.•The overall discriminatory ability of the network was satisfactory.•Applying neural networks may assist dentists' in reliably and accurately detecting ALs.
Objectives
Dentistry is stuck between the one-size-fits-all approach towards diagnostics and therapy employed for a century and the era of stratified medicine. The present review presents the concept ...of precision dentistry, i.e., the next step beyond stratification into risk groups, and lays out where we stand, but also what challenges we have ahead for precision dentistry to come true.
Material and methods
Narrative literature review.
Results
Current approaches for enabling more precise diagnostics and therapies focus on stratification of individuals using clinical or social risk factors or indicators. Most research in dentistry does not focus on predictions — the key for precision dentistry — but on associations. We critically discuss why both approaches (focus on a limited number of risk factors or indicators and on associations) are insufficient and elaborate on what we think may allow to overcome the status quo.
Conclusions
Leveraging more diverse and broad data stemming from routine or unusual sources via advanced data analytics and testing the resulting prediction models rigorously may allow further steps towards more precise oral and dental care.
Clinical significance
Precision dentistry refers to tailoring diagnostics and therapy to an individual; it builds on modelling, prediction making and rigorous testing. Most studies in the dental domain focus on showing associations, and do not attempt to make any predictions. Moreover, the datasets used are narrow and usually collected purposively following a clinical reasoning. Opening routine data silos and involving uncommon data sources to harvest broad data and leverage them using advanced analytics could facilitate precision dentistry.
Full text
Available for:
CMK, EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
We aimed to apply deep learning to detect caries lesions of different radiographic extension on bitewings, hypothesizing it to be significantly more accurate than individual dentists.
3686 bitewing ...radiographs were assessed by four experienced dentists. Caries lesions were marked in a pixelwise fashion. The union of all pixels was defined as reference test. The data was divided into a training (3293), validation (252) and test dataset (141). We applied a convolutional neural network (U-Net) and used the Intersection-over-Union as validation metric. The performance of the trained neural network on the test dataset was compared against that of seven independent using tooth-level accuracy metrics. Stratification according to lesion depth (enamel lesions E1/2, dentin lesions into middle or inner third D2/3) was applied.
The neural network showed an accuracy of 0.80; dentists’ mean accuracy was significantly lower at 0.71 (min-max: 0.61−0.78, p < 0.05). The neural network was significantly more sensitive than dentists (0.75 versus 0.36 (0.19−0.65; p = 0.006), while its specificity was not significantly lower (0.83) than those of the dentists (0.91 (0.69−0.98; p > 0.05); p > 0.05). The neural network showed robust sensitivities at or above 0.70 for both initial and advanced lesions. Dentists largely showed low sensitivities for initial lesions (all except one dentist showed sensitivities below 0.25), while those for advanced ones were between 0.40 and 0.75.
To detect caries lesions on bitewing radiographs, a deep neural network was significantly more accurate than dentists.
Clinical significance: Deep learning may assist dentists to detect especially initial caries lesions on bitewings. The impact of using such models on decision-making should be explored.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
In this pilot study, we applied deep convolutional neural networks (CNNs) to detect caries lesions in Near-Infrared-Light Transillumination (NILT) images.
226 extracted posterior permanent human ...teeth (113 premolars, 113 molars) were allocated to groups of 2 + 2 teeth, and mounted in a pilot-tested diagnostic model in a dummy head. NILT images of single-tooth-segments were generated using DIAGNOcam (KaVo, Biberach). For each segment (on average 435 × 407 × 3 pixels), occlusal and/or proximal caries lesions were annotated by two experienced dentists using an in-house developed digital annotation tool. The pixel-based annotations were translated into binary class levels. We trained two state-of-the-art CNNs (Resnet18, Resnext50) and validated them via 10-fold cross validation. During the training process, we applied data augmentation (random resizing, rotations and flipping) and one-cycle-learning rate policy, setting the minimum and maximum learning rates to 10−5 and 10-3, respectively. Metrics for model performance were the area-under-the-receiver-operating-characteristics-curve (AUC), sensitivity, specificity, and positive/negative predictive values (PPV/NPV). Feature visualization was additionally applied to assess if the CNNs built on features dentists would also use.
The tooth-level prevalence of caries lesions was 41%. The two models performed similar on predicting caries on tooth segments of NILT images. The marginal better model with respect to AUC was Resnext50, where we retrained the last 9 network layers, using the Adam optimizer, a learning rate of 0.5 × 10−4, and a batch size of 10. The mean (95% CI) AUC was 0.74 (0.66-0.82). Sensitivity and specificity were 0.59 (0.47-0.70) and 0.76 (0.68-0.84) respectively. The resulting PPV was 0.63 (0.51-0.74), the NPV 0.73 (0.65-0.80). Visual inspection of model predictions found the model to be sensitive to areas affected by caries lesions.
A moderately deep CNN trained on a limited amount of NILT image data showed satisfying discriminatory ability to detect caries lesions.
CNNs may be useful to assist NILT-based caries detection. This could be especially relevant in non-conventional dental settings, like schools, care homes or rural outpost centers.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
We assessed the generalizability of deep learning models and how to improve it. Our exemplary use-case was the detection of apical lesions on panoramic radiographs. We employed two datasets of ...panoramic radiographs from two centers, one in Germany (Charité, Berlin, n = 650) and one in India (KGMU, Lucknow, n = 650): First, U-Net type models were trained on images from Charité (n = 500) and assessed on test sets from Charité and KGMU (each n = 150). Second, the relevance of image characteristics was explored using pixel-value transformations, aligning the image characteristics in the datasets. Third, cross-center training effects on generalizability were evaluated by stepwise replacing Charite with KGMU images. Last, we assessed the impact of the dental status (presence of root-canal fillings or restorations). Models trained only on Charité images showed a (mean ± SD) F1-score of 54.1 ± 0.8% on Charité and 32.7 ± 0.8% on KGMU data (p < 0.001/t-test). Alignment of image data characteristics between the centers did not improve generalizability. However, by gradually increasing the fraction of KGMU images in the training set (from 0 to 100%) the F1-score on KGMU images improved (46.1 ± 0.9%) at a moderate decrease on Charité images (50.9 ± 0.9%, p < 0.01). Model performance was good on KGMU images showing root-canal fillings and/or restorations, but much lower on KGMU images without root-canal fillings and/or restorations. Our deep learning models were not generalizable across centers. Cross-center training improved generalizability. Noteworthy, the dental status, but not image characteristics were relevant. Understanding the reasons behind limits in generalizability helps to mitigate generalizability problems.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Objectives
To assess how to control, detect, and treat secondary caries. This review serves to inform a joint ORCA/EFCD consensus process.
Methods
Systematic and non-systematic reviews were performed ...or consulted and narratively synthesized.
Results
Secondary (or recurrent) caries is defined as a lesion associated with restorations or sealants. While the restorative material itself has some influence on secondary caries, further factors like the presence and size of restoration gaps, patients’ caries risk, and the placing dentist’s experience seem more relevant. Current detection methods for secondary caries are only sparsely validated and likely prone for the risk of over-detection. In many patients, it might be prudent to prioritize specific detection methods to avoid invasive overtreatment. Detected secondary caries can be managed either by repair of the defective part of the restoration or its complete replacement.
Conclusions
There is sparse data towards the nature of secondary caries and how to control, detect, and treat it.
Clinical significance
Despite often claimed to be a major complication of restorations, there is surprisingly little data on secondary caries. Longer-term studies may be needed to identify differences in secondary caries risk between materials and to identify characteristic features of progressive lesions (i.e., those in need of treatment).
Aim
A range of predictors for tooth loss in periodontitis patients have been reported. We performed a systematic review and meta‐analysis to assess the consistency and magnitude of any association ...between a total of 12 predictors and tooth loss.
Materials and Methods
Medline/Embase/Central were searched for longitudinal studies investigating the association between predictors and tooth loss in periodontitis patients. Random‐effects meta‐analysis was performed, and study quality assessed.
Results
Twenty studies (15,422 patients, mean follow‐up: 12 years) were included. The mean annual tooth loss/patient was 0.12 (min./max: 0.01/0.36). Older patients (n = 8 studies; OR: 1.05, 95% CI: 1.03–1.08/year), non‐compliant ones (n = 11; 1.51, 1.06–2.16), diabetics (n = 7; 1.80, 1.26–2.57), those with IL‐1‐polymorphism (n = 3; 1.80; 1.29–2.52) and smokers (n = 15; 1.98, 1.58–2.48) had a significantly higher risk of tooth loss. Teeth with bone loss (n = 3; 1.04, 1.03–1.05/%), high probing pocket depth (n = 6; 3.19, 1.70–5.98), mobility (n = 4; 3.71, 1.65–8.38) and molars (n = 4; 4.22, 2.12–8.39), especially with furcation involvement (n = 5; 2.68, 1.75–4.08) also showed higher risks. Gender (n = 16; 0.95, 0.86–1.05) and endodontic affection (n = 3; 3.62, 0.99–13.2) were not significantly associated with tooth loss.
Conclusions
Older, non‐compliant, smoking or diabetic patients, and teeth with bone loss, high probing pocket depth, mobility, or molars, especially with furcation involvement showed higher risks of tooth loss.
Full text
Available for:
BFBNIB, CMK, FZAB, GIS, IJS, KILJ, NLZOH, NUK, OILJ, SAZU, SBCE, SBMB, UL, UM, UPUK
The aims of this study were to assess the trends in dental caries experience in the permanent dentition (i.e., the number of decayed, missing, or filled teeth, DMFT) in Germany from 1997-2014 and to ...project caries experience to 2030. Components of caries experience (decayed teeth, DT, missing teeth, MT, filled teeth, FT) from repeated waves (1997, 2005, 2014) of the nationally representative German Oral Health Studies were analyzed in 12-, 35-44-, and 65-74-year-olds. Weighted means were interpolated cross-sectionally by fitting piecewise-cubic spline-curves and were then subjected to longitudinal regression and combined with population estimates. In 1997, children (12-year-olds) had a mean caries experience (decayed, missing, filled teeth, DMFT) of 1.7 teeth; this experience decreased to 0.5 teeth in 2014. For 2030, an experience of 0.2 teeth is projected. In adults (35-44-year-olds), a decrease was recorded (1997: 16.1 teeth; 2014: 11.2 teeth). This decrease is expected to continue until 2030 (to 7.7 teeth). Similarly, in seniors (65-74-year-olds), a decrease was recorded (1997: 23.6 teeth; 2014: 17.7 teeth); this decrease is expected to continue until 2030 (to 14.9 teeth). While the number of missing teeth has decreased consistently across age groups, the number of filled and decayed teeth has increased in seniors and is expected to continue to increase. The cumulative caries experience has decreased from 1.1 billion DMFT in 2000 to 867 million in 2015 and is expected to decrease to 740 million in 2030. Caries experience in the permanent dentition has been decreasing substantially, mainly due to a decrease in missing teeth. Younger age groups also show fewer decayed and filled teeth, while in older groups, restorative needs have not decreased, as more teeth are retained. Concepts for addressing the emanating morbidity shifts are required.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK