Deep convolutional network is a deep learning approach to optimize image recognition. This study aimed to apply DCNN to the reading of mandibular cortical thinning in digital panoramic radiographs. Digital panoramic radiographs of 1,268 female dental patients (age 45.2 ± 21.1yrs) were used in the reading of the mandibular cortical bone by two maxillofacial radiologists. Among the subjects, 535 normal subject’s panoramic radiographs (age 28.6 ±7.4 yrs) and 533 those of osteoporosis pationts (age 72.1 ± 8.7 yrs) with mandibular cortical thinning were used for training DCNN. In the testing of mandibular cortical thinning, 100 panoramic radiographs of normal subjects (age 26.6 ± 4.5 yrs) and 100 mandibular cortical thinning (age 72.5 ± 7.2 yrs) were used. The sensitive area of DCNN to mandibular cortical thinning was investigated by occluding analysis. The readings of DCNN were compared by two maxillofacial radiologists. DCNN showed 97.5% accuracy, 96% sensitivity, and 99% specificity in reading mandibular cortical thinning. DCNN was sensitively responded on the cancellous and cortical bone of the mandibular inferior area. DCNN was effective in diagnosing mandibular cortical thinning.

Railroad ballast materials tend to degrade due to the increase of ballast abrasion and fracture that results in decreasing the capability of shock absorption, interlocking friction, and the resistance to track irregularity. Therefore, it is necessary to establish a methodology to improve or maintain the structural condition of ballast materials which is in the middle of fouling. This study aimed to investigate the effect of reinforcement on the fouled ballast using ballast stabilizer. Field experimental program was conducted to compare the lateral ballast resistance in case of before and after application of ballast stabilizer. A series of laboratory repetitive load triaxial compression test was then performed to compare the accumulated plastic strain in case of before and after application of ballast stabilizer to the ballast materials having a different level of Fouling Index(FI). In the event of application of ballast stabilizer, the accumulated plastic strain decreased by 41.8 and 28.8 percent, respectively, when the FI was 14 and 21, which appears to indicate the ballast stabilizer is effective for the moderate level fouled ballast materials.