Detection of caries around restorations on bitewings using deep learning.

OBJECTIVE: Secondary caries lesions adjacent to restorations, a leading cause of restoration failure, require accurate diagnostic methods to ensure an optimal treatment outcome. Traditional diagnostic strategies rely on visual inspection complemented by radiographs. Recent advancements in artificial intelligence (AI), particularly deep learning, provide potential improvements in caries detection. This study aimed to develop a convolutional neural network (CNN)-based algorithm for detecting primary caries and secondary caries around restorations using bitewings. METHODS: Clinical data from 7 general dental practices in the Netherlands, comprising 425 bitewings of 383 patients, were utilized. The study used the Mask-RCNN architecture, for instance, segmentation, supported by the Swin Transformer backbone. After data augmentation, model training was performed through a ten-fold cross-validation. The diagnostic accuracy of the algorithm was evaluated by calculating the area under the Free-Response Receiver Operating Characteristics curve, sensitivity, precision, and F1 scores. RESULTS: The model achieved areas under FROC curves of 0.806 and 0.804, and F1-scores of 0.689 and 0.719 for primary and secondary caries detection, respectively. CONCLUSION: An accurate CNN-based automated system was developed to detect primary and secondary caries lesions on bitewings, highlighting a significant advancement in automated caries diagnostics. CLINICAL SIGNIFICANCE: An accurate algorithm that integrates the detection of both primary and secondary caries will permit the development of automated systems to aid clinicians in their daily clinical practice.

Comparative Study of Electrochemical Sensors Based on Enzyme Immobilized into Polyelectrolyte Microcapsules and into Chitosan Gel.

The characteristics of an electrochemical biosensor based on a Prussian-blue screen-printed electrode containing glucose oxidase incorporated into polyelectrolyte microcapsules (PMC) are considered. PMC with the embedded enzyme were formed using sodium polystyrene sulfonate and poly(allylamine hydrochloride). The characteristics were compared with those of the enzyme immobilized in chitosan gel. We assessed the dependences of biosensor signals on the composition of the buffer solution, on the glucose concentration; the operational and long-term stabilities. The enzyme immobilized in PMC proved to be more sensitive to buffer molarity at a maximum within 35 - 40 mM. The apparent Michaelis constants were 1.5 and 4.1 mM at the immobilization in, respectively, chitosan and PMC. The developed biosensors were used to assay commercial juices. The biosensors' data on the glucose contents were shown to have a high correlation with the standard spectrophotometric assay (0.92 - 0.95%), which implies a possible application of the fabricated biosensors in foodstuff analysis.

[40 years of silicone breast implants]. / Silikonbrystimplantater gjennom 40 år.

BACKGROUND: It is estimated that approximately 50,000 Norwegian women have silicone breast implants following breast augmentation or breast reconstruction. Their numbers are growing and doctors will more often be confronted with the health problems related to these implants. MATERIAL AND METHODS: This review is based on information retrieved from Medline and our clinical experience. RESULTS AND INTERPRETATION: The modern silicone breast implant is the product of four decades of development. The ongoing debate on health problems associated with the implants has been a vibrant stimulator for research, but a causal relationship between implants and the development of breast cancer and autoimmune defects has not been found. The implants are not, however, without complications; more research is required in order to improve the implants and for quality assurance of treatment and follow up.