Detecting caries lesions of different radiographic extension on bitewings using deep learning

Ros, Anselmo García Cantú; Gehrung, Sascha; Krois, Joachim; Chaurasia, Akhilanand; Rossi, Jesús Gómez; Gaudin, Robert; Elhennawy, Karim; Schwendicke, Falk

doi:10.1016/j.jdent.2020.103425

Cited by 202 publications

(180 citation statements)

References 19 publications

Supporting

Mentioning

146

Contrasting

Unclassified

Order By: Relevance

“…A model-based cost-effectiveness study was performed, building on a previously conducted diagnostic accuracy study (Garcia Cantu et al 2020), in which a CNN was trained, validated, and tested on 3,686 retrospectively collected bitewing radiographs from a German dental clinic. Bitewings had been assessed for proximal caries lesions by a total of 4 experts (reference test).…”

Section: Methodsmentioning

confidence: 99%

“…The accuracy data informing this group were built on a systematic review and meta-analysis (Schwendicke, Tzschoppe, et al 2015), assuming this to be the most robust data available. In addition, and for the purpose of sensitivity analyses, we used the diagnostic accuracies of 7 independent dentists who had evaluated the same test data of 141 bitewing radiographs on which the CNN had been tested (Garcia Cantu et al 2020). In the test group (AI), radiographic caries detection on bitewings provided every 2 y was assumed to be assisted by a diagnostic assistance system, based on a fully convolutional neural net, U-Net (Ronneberger et al 2015), that had been trained, validated, and tested as described elsewhere (Garcia Cantu et al 2020).…”

Section: Comparatorsmentioning

confidence: 99%

“…In addition, and for the purpose of sensitivity analyses, we used the diagnostic accuracies of 7 independent dentists who had evaluated the same test data of 141 bitewing radiographs on which the CNN had been tested (Garcia Cantu et al 2020). In the test group (AI), radiographic caries detection on bitewings provided every 2 y was assumed to be assisted by a diagnostic assistance system, based on a fully convolutional neural net, U-Net (Ronneberger et al 2015), that had been trained, validated, and tested as described elsewhere (Garcia Cantu et al 2020). The emanating accuracy differences between groups translated into different treatment decisions and thereby cost differences.…”

Section: Comparatorsmentioning

confidence: 99%

“…The learning process involves labeling an image and providing both the image and the label to the CNN, which iteratively adjusts itself to eventually be able to predict the presence of the labeled entity (a carious lesion) on unseen data. For detecting caries lesions, we previously trained, validated, and tested a fully convolutional neural network, U-net, yielding an accuracy superior to individual dentists (Garcia Cantu et al 2020). Notably, the CNN showed significantly higher sensitivity than dentists, especially for detecting early lesions (more details are provided below).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Cost-effectiveness of Artificial Intelligence for Proximal Caries Detection

et al. 2020

Self Cite

View full text Add to dashboard Cite

Artificial intelligence (AI) can assist dentists in image assessment, for example, caries detection. The wider health and cost impact of employing AI for dental diagnostics has not yet been evaluated. We compared the cost-effectiveness of proximal caries detection on bitewing radiographs with versus without AI. U-Net, a fully convolutional neural network, had been trained, validated, and tested on 3,293, 252, and 141 bitewing radiographs, respectively, on which 4 experienced dentists had marked carious lesions (reference test). Lesions were stratified for initial lesions (E1/E2/D1, presumed noncavitated, receiving caries infiltration if detected) and advanced lesions (D2/D3, presumed cavitated, receiving restorative care if detected). A Markov model was used to simulate the consequences of true- and false-positive and true- and false-negative detections, as well as the subsequent decisions over the lifetime of patients. A German mixed-payers perspective was adopted. Our health outcome was tooth retention years. Costs were measured in 2020 euro. Monte-Carlo microsimulations and univariate and probabilistic sensitivity analyses were conducted. The incremental cost-effectiveness ratio (ICER) and the cost-effectiveness acceptability at different willingness-to-pay thresholds were quantified. AI showed an accuracy of 0.80; dentists’ mean accuracy was significantly lower at 0.71 (minimum–maximum: 0.61–0.78, P < 0.05). AI was significantly more sensitive than dentists (0.75 vs. 0.36 [0.19–0.65]; P = 0.006), while its specificity was not significantly lower (0.83 vs. 0.91 [0.69–0.98]; P > 0.05). In the base-case scenario, AI was more effective (tooth retention for a mean 64 [2.5%–97.5%: 61–65] y) and less costly (298 [244–367] euro) than assessment without AI (62 [59–64] y; 322 [257–394] euro). The ICER was −13.9 euro/y (i.e., AI saved money at higher effectiveness). In the majority (>77%) of all cases, AI was less costly and more effective. Applying AI for caries detection is likely to be cost-effective, mainly as fewer lesions remain undetected. Notably, this cost-effectiveness requires dentists to manage detected early lesions nonrestoratively.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Comparatorsmentioning

confidence: 99%

Section: Comparatorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Cost-effectiveness of Artificial Intelligence for Proximal Caries Detection

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In einer kürzlich publizierten Studie wurde eine KI-Anwendung zur Diagnostik von frühen und vorangeschrittenen kariösen Läsionen an Approximalflächen auf Bissflügelröntgenbildern evaluiert [13]. Die KI war an insgesamt ca.…”

Section: Ki Für Kariesdiagnostikunclassified

Kariesdiagnostik mittels künstlicher Intelligenz: Zukunftsmusik oder Realität?

Schwendicke¹,

Krois²

2021

ZWR - Das Deutsche Zahnärzteblatt

Self Cite

View full text Add to dashboard Cite

Cost-effectiveness of Artificial Intelligence as a Decision-Support System Applied to the Detection and Grading of Melanoma, Dental Caries, and Diabetic Retinopathy

et al. 2022

Self Cite

View full text Add to dashboard Cite

Key Points Question Are existing artificial intelligence (AI) algorithms cost-effective for use as a decision-support system in dermatology, dentistry, and ophthalmology? Findings In this economic evaluation analyzing data from 3 Markov models used in previous cost-effectiveness studies, the use of AI was associated with a modest improvement in outcomes. All benefits were highly dependent on treatment effects assumed after diagnosis and were very sensitive to the fee paid for the use of AI. Meaning These results suggest that even when AI can achieve better diagnostic capacities than the average physician, this may not directly translate to better or cheaper care, and that analysis using this technology should be used on a case-by-case basis.

show abstract

Detecting caries lesions of different radiographic extension on bitewings using deep learning

Cited by 202 publications

References 19 publications

Cost-effectiveness of Artificial Intelligence for Proximal Caries Detection

Cost-effectiveness of Artificial Intelligence for Proximal Caries Detection

Kariesdiagnostik mittels künstlicher Intelligenz: Zukunftsmusik oder Realität?

Cost-effectiveness of Artificial Intelligence as a Decision-Support System Applied to the Detection and Grading of Melanoma, Dental Caries, and Diabetic Retinopathy

Contact Info

Product

Resources

About