The aim was to compare digital and conventional panoramic imaging techniques for identifying high-risk radiographic markers associated with mandibular nerve (MN) injury after mandibular third molar (M3) removal. The study used a retrospective cohort model. The predictor variable was the presence or absence of radiographic signs associated with MN exposure during M3 removal. The outcome variable was MN exposure. Intraexaminer variability was estimated using a kappa statistic. Logistic regression modeling was used to measure the association between radiographic signs and MN exposure and determine if imaging technique modified that association. The level of statistical significance was set at P < .05. The sample was composed of 571 patients having 1,017 mandibular M3s removed. The MN was visualized in 66 extraction sites (6.5%). In the adjusted logistic model, radiographic signs were statistically associated with MN exposure (P < .001) and imaging technique was a statistically insignificant effect modifying variable (P = .4). The results of this study suggest that imaging technique does not modify the relationship between high-risk panoramic radiographic signs and MN exposure.