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.

A dual composite resin injection molding technique with 3D-printed flexible indices for biomimetic replacement of a missing mandibular lateral incisor.

PATIENTS: This case report presents a minimally invasive approach to replace a missing mandibular lateral incisor using a dual-injection molding technique with flowable composite resins. Integrated with a comprehensive digital workflow, this method achieves a structurally and esthetically biomimetic, bi-layered prosthetic solution. A 34-year-old woman with congenital absence of a mandibular lateral incisor was successfully rehabilitated using a direct composite resin-bonded fixed partial denture (RBFPD). DISCUSSION: Two specialized three-dimensional (3D)-printed flexible indices stabilized by a custom-designed 3D-printed rigid holder were employed to ensure the meticulous injection molding of flowable composite resins formulated to emulate the inherent chromatic gradations between dentin and enamel. The inherent flexibility of the indices, combined with the holder, facilitated accurate and seamless adaptation to the complex morphological features of the dental arch, thereby mitigating the challenges commonly associated with rigid 3D-printed resin indices. CONCLUSIONS: The bilayered direct composite RBFPD using 3D printed flexible indices prepared with a full digital workflow has several advantages over other dental prosthetic solutions, including noninvasiveness, cost-effectiveness, biomimetic esthetics, repairability, and shortened treatment times. Although the initial results are promising, further longitudinal studies with larger patient cohorts are required to confirm the long-term efficacy of this approach.