Objectives Facial canal dehiscence (FCD), typically found in the tympanic segment, is a risk factor for facial nerve injury. An imaging scoring method was proposed to identify FCD based on ultra-high-resolution CT. Methods Forty patients (21 females and 19 males, mean age 44.3 +/- 17.4 years), whose tympanic facial canal (FC) was examined during otological surgery, were divided into the FCD group (n = 29) and the control group (n = 11) based on surgical findings. Imaging appearance of tympanic FC was scored 0-3: 0 = no evident bony covering, 1 = discontinuous bony covering with linear deficiency, 2 = discontinuous bony covering with dotted deficiency, and 3 = continuous bony covering. Both lateral and inferior walls were assigned a score as L-FCD and I-FCD, respectively. An FCD score was calculated as L-FCD + I-FCD. The diagnostic value of the FCD score was tested using the ROC curve. Results The inter-observer agreement was moderate for the lateral wall (Cohen's kappa coefficient 0.416, 95% CI 0.193-0.639), and good for the inferior wall (Cohen's kappa coefficient 0.702, 95% CI 0.516-0.888). In the FCD group, the most common appearance for both walls was discontinuous bony covering with linear deficiency (L-FCD = 1, 22/29, 75.9%; I-FCD = 1, 15/29, 51.7%). An FCD score of less than 4 was associated with high sensitivity (0.82) and specificity (0.93) for identifying FCD, with an AUC of 0.928. Conclusions Using the proposed scoring method, FCD score < 4 could identify FCD of the tympanic segment with high concordance with surgical findings.