Non-AI image sharpening made landmark visibility on 60%-dose lateral cephalometric radiographs comparable to routine 100% dose, and markedly sharpened images were significantly superior at 60% and 40% dose
This phantom study acquired lateral cephalometric radiographs of an adult dry human skull phantom at the routine dose (80 kVp, 200 mA, 100 ms; DAP 270 mGy cm2) and at 60%, 40%, 20%, and 10% of that dose, applied two levels of non-artificial-intelligence sharpening with the Medical Image Enhancer software (mild: sharpening strength 55%, contrast ratio 20%; marked: 70%/70%), and had six reviewers rate the visibility of five reference points and soft tissue using Scheffe's method of paired comparisons with ordinal logistic regression odds ratios relative to the 100%-dose image; mildly sharpened 60%-dose images gave ORs above 1.