PubMed · 4024675
The source did not provide an abstract. Follow the original record for more information.
Explore connections, maps & timelines
G Redlow, R Zuhrt. 1985. [Truth is all].. https://pubmed.ncbi.nlm.nih.gov/4024675/
Cite the original work for its findings. Save a collection to share your selection of sources.
KEEP EXPLORING
Artificial intelligence (AI) has been proposed as a tool to improve dental caries detection across imaging modalities; however, its clinical value remains uncertain. This umbrella review aimed to synthesize and critically appraise systematic reviews evaluating AI for caries detection and diagnosis. An umbrella review was conducted following PRIOR guidance (PROSPERO CRD420261340728). Searches were performed in MEDLINE, Embase, Scopus, Web of Science, and Google Scholar up to 15 March 2026. Methodological quality was assessed using AMSTAR 2, and overlap of primary studies was quantified using the corrected covered area (CCA). Seventeen systematic reviews were included, of which five reported diagnostic test accuracy meta-analyses using bivariate or HSROC models. Across these meta-analyses, pooled sensitivity ranged from 0.76 to 0.94 and specificity from 0.85 to 0.91. Most systems were based on deep learning models applied to bitewing radiographs and intraoral photographs. However, substantial heterogeneity was observed in imaging modalities, lesion thresholds, analytical tasks, and evaluation metrics. In addition, a high degree of overlap across reviews and recurrent methodological limitations, including reliance on retrospective datasets, limited external validation, and inconsistent reporting, substantially weaken the reliability of the evidence. Although AI models demonstrate high diagnostic performance under experimental conditions, current evidence does not support their use as stand-alone diagnostic tools. Their clinical applicability remains limited, and implementation should be restricted to decision-support contexts until robust prospective validation demonstrates meaningful impact on clinical decision-making and patient outcomes.
Image compression may reduce storage needs whether in the lossless (reversible) or lossy (irreversible) form. The aims of the study were to evaluate (1) storage needs, (2) subjective image quality, and (3) accuracy of caries detection in digital radiographs compressed to various levels by a lossy compression method. The material consisted of 116 extracted human premolars and molars. The teeth were mounted three in a line and radiographed by the Digora system (Sorodex Medical Systems, Helsinki, Finland). The images were exported in tagged image file format and compressed with the Lempel-Ziv-Welch reversible and the Joint Photographic Experts Group irreversible compression algorithm on four levels. The total of 580 images were assessed by five observers on a 5-rank confidence scale for caries diagnosis. The observers subjectively judged image quality on an 11-point rank scale. With the reversible compression, images could be compressed to less than 50% of the original storage needs whereas the four irreversible compression factors compressed to 20%, 8%, 5%, and 3%, respectively. For occlusal surfaces, when receiver operating characteristic curve areas were increasingly smaller and the compression rate was higher. The difference between the original and the most compressed images was 14% (p = 0.1). The median quality score was above middle on the 11-point rank scale for all except the most compressed images (median score = 1). In conclusion, for caries diagnosis, compression ratio rates of 1:12 can be justified before accuracy and image quality is significantly affected.