DOES RADIOGRAPHIC FEATURE RECOGNITION CONTRIBUTE TO DENTISTS DIAGNOSIS OF PATHOLOGY

Objectives. To measure the degree to which dentists can accurately ide ntify radiographic features and use their findings in the diagnosis of three lesions. Methods. Fourteen radiographic examples were used in t his study and five features derived from the literature: border sharpn ess, border radiopacity, lesion shape, lesion radiopacity and root con tact. A 'silver standard' for the presence of the features in the radi ographic images of the lesions was established by expert observers; an d a diagnostic 'gold standard' based on the histopathology of the lesi ons was available. Dentists scored each image according to these featu res and gave their diagnosis. Results. When dentists made different su bjective diagnoses for a case, significant differences were found in t he extent to which features were reported to be present. The degrees o f presence of border sharpness (21%) and border radiopacity (46%) meas ured using the 'silver standard' were significantly related to the dia gnosis of osteosarcoma. Conclusions. Radiographic information is not u sed to its full extent and improvement in the recognition of features and the cognitive use of this radiographic information in the diagnost ic process could improve diagnostic accuracy.