Abstract
Abstract
This phantom study aimed to determine whether a novel non-artificial intelligence image-sharpening approach improves the visibility of reference points on low-dose lateral cephalometric radiographs. Lateral cephalometric radiographs were obtained using an adult human bone phantom at 100% of the routine dose. Low-dose imaging was performed using 60%, 40%, and 20% of the routine dose. Each low-dose image underwent a 2-level image-sharpening process using the Medical Image Enhancer software. Six reviewers evaluated the visibility of the 5 reference points in the first and second sets of sharpened and 100% radiation-dose images. Using Scheffé’s method of paired comparisons, odds ratios (ORs) were reported as relative values for a standard cephalometric radiograph (100% radiation dose) to compare the visibility of reference points among imaging conditions. For the first set of mildly sharpened 60%-dose images, the ORs for the 4 reference points were >1.0, Point A (OR 1.12, P = .83), Nasion (OR 2.26, P = .11), posterior nasal spine (OR 2.35, P = .1), and incisal edge of the maxillary central incisor (OR 1.35, P = .53), indicating visibility comparable to or better than the 100%-dose images. For the second set of markedly sharpened images, rated visibility was significantly higher for all reference points at 60% and 40% doses and for several reference points at 20% dose. Image-sharpening algorithms improved the visibility of reference points on low-dose phantom radiographs, suggesting their technical feasibility as a post-acquisition approach for dose-reduced cephalometric imaging.