The present study aims to evaluate the relation between chronological age and the ratio of pulp volume (PV) to enamel volume (EV) of impacted mandibular third molars (IMTMs) by using cone-beam computed tomography (CBCT) images and an improved 3D image segmentation technique. A sample of CBCT images of IMTM was collected from 414 northern Chinese subjects (214 male and 200 female clinical patients) ranging in age from 20 to 65 years. The GrowCut effect image segmentation (GCEIS) module algorithm was used to calculate the PV and EV from CBCT images. The total sample was divided into a training group and validation group in a ratio of 7 to 3. The PV/EV ratio (PEr) in the training sample was used to develop a mathematical formula for age estimation as follows: age = - 5.817-21.726 × Ln PEr (p < 0.0001) (Ln, natural logarithm). The mean absolute error (MAE) and root mean square error (RMSE) were used to determine the precision and accuracy of the mathematical formula in the validation group and all samples. The MAEs in the male, female, and pooled gender samples were 9.223, 7.722, and 8.41, respectively, and the RMSEs in the male, female, and pooled gender samples were 10.76, 9.58, and 9.986, respectively. The precise and accurate results indicate that the PEr of IMTM in CBCT images is a potential index for dental age estimation and is possible to be used in forensic medicine.