A comparison of the horizontal and vertical bitewing images in detecting approximal caries and interdental bone loss in posterior teeth: A diagnostic accuracy randomized cross over clinical trial

Automatic caries detection in bitewing radiographs-Part II: experimental comparison

OBJECTIVE

The objective of this study was to compare the detection of caries in bitewing radiographs by multiple dentists with an automatic method and to evaluate the detection performance in the absence of a reliable ground truth.

MATERIALS AND METHODS

Four experts and three novices marked caries using bounding boxes in 100 bitewing radiographs. The same dataset was processed by an automatic object detection deep learning method. All annotators were compared in terms of the number of errors and intersection over union (IoU) using pairwise comparisons, with respect to the consensus standard, and with respect to the annotator of the training dataset of the automatic method.

RESULTS

The number of lesions marked by experts in 100 images varied between 241 and 425. Pairwise comparisons showed that the automatic method outperformed all dentists except the original annotator in the mean number of errors, while being among the best in terms of IoU. With respect to a consensus standard, the performance of the automatic method was best in terms of the number of errors and slightly below average in terms of IoU. Compared with the original annotator, the automatic method had the highest IoU and only one expert made fewer errors.

CONCLUSIONS

The automatic method consistently outperformed novices and performed as well as highly experienced dentists.

CLINICAL SIGNIFICANCE

The consensus in caries detection between experts is low. An automatic method based on deep learning can improve both the accuracy and repeatability of caries detection, providing a useful second opinion even for very experienced dentists.

Performance of Oral Cavity Sensors: A Systematic Review

Technological advancements are enabling new applications within biomedical engineering. As a connection point between the outer environment and the human system, the oral cavity offers unique opportunities for sensing technologies. This paper systematically reviews the performance of measurement systems tested in the human oral cavity. Performance was defined by metrics related to accuracy and agreement estimation. A comprehensive search identifying human studies that reported on the accuracy or agreement of intraoral sensors found 85 research papers. Most of the literature (62%) was in dentistry, followed by neurology (21%), and physical medicine and rehabilitation (12%). The remaining papers were on internal medicine, obstetrics, and aerospace medicine. Most of the studies applied force or pressure sensors (32%), while optical and image sensors were applied most widely across fields. The main challenges for future adoption include the lack of large human trials, the maturity of emerging technologies (e.g., biochemical sensors), and the absence of standardization of evaluation in specific fields. New research should aim to employ robust performance metrics to evaluate their systems and incorporate real-world evidence as part of the evaluation process. Oral cavity sensors offer the potential for applications in healthcare and wellbeing, but for many technologies, more research is needed.