Prediction of low bone mass using a combinational approach of cortical and trabecular bone measures from dental panoramic radiographs

The aim of this study is to extract cortical and trabecular features of the mandible and to develop a novel combinational model of mandibular cortical thickness, trabecular bone area and age in order to predict low bone mineral density or osteoporosis from a dental panoramic radiograph. The study involved 64 south Indian women (age = 52.5 +/- 12.7 years) categorised into two groups (normal and low bone mineral density) based on total femur bone mineral density. The dental panoramic radiographs were obtained by a digital scanner, and measurement of total bone mineral density at the right femur was performed by a dual-energy X-ray absorptiometry scanner. The mandibular cortical thickness and panoramic mandibular index were measured bilaterally, and the mean values were considered. The region of interest of 128 x 128 pixels around the mental foramen region was manually cropped and subjected to pre-processing, normalisation and average threshold-based segmentation to determine trabecular bone area. Multiple linear regression analyses of cortical and trabecular measures along with age were performed to develop a combinational model to classify subjects as normal and low bone mineral density. The proposed approach demonstrated strong correlation (r = 0.76; p < 0.01) against the total bone mineral density and resulted in accuracy, sensitivity and positive predictive values of 0.84, 0.92 and 0.85, respectively; the receiver operating characteristic outcomes disclosed that the area under the curve was 0.89.Our results suggest that the proposed combinational model could be useful to diagnose subjects with low bone mineral density.