In planning a mandibular posterior dental implant, identifying the exact location of the alveolar bone (AB) and mandibular canal (MC) is essential to determine the height and width of the available bone. Cone beam computed tomography (CBCT) is a 3D imaging modality widely used for dental implant planning, which requires a lower radiation dose compared to medical CT and can provide cross-sectional image quality to visualize AB and MC. The radiologist carried out the AB and MC detection processes manually on each section of the CBCT image until the appropriate area was determined for bone measurement. This process is time consuming, and the measurement accuracy depends on the ability and experience of the radiologist. This study proposes an automatic and simultaneous detection system for AB and MC based on 2D grayscale CBCT images, that can simplify and expedite dental implant planning. We introduce Dental-YOLO, an efficient version of YOLOv4 specifically developed to detect AB and MC, with two-scale feature maps at low and high scales. The height and width of the available bone in the implant area were estimated by using the detected bounding box attributes. The AB and MC detection performances using Dental-YOLO reached a mean average precision of 99.46%. The two-way analysis of variance (ANOVA) test showed no difference in the bone height and width measurements produced by the proposed approach and manual measurement by radiologists. Our results suggest that the Dental-YOLO detection system could be helpful for dental implant surgery and presurgical treatment planning.INDEX TERMS Alveolar bone, CBCT, bone measurement, dental implant planning, mandibular canal, object detection, YOLO.
Fruits classification from image is a very challenging task, particularly for Indonesian indigenous fruits, due to some similarities occurred in several types of the fruits. This study proposes a method to classify Indonesian fruits from image using MPEG-7 color and texture descriptors. The descriptors were directly extracted from the image without pre-processing and segmentation steps. Principle component analysis was then applied to reduce the dimension of the descriptors. Four simple classifiers, decision tree, naïve Bayesian, linear discriminant analysis, and k-nearest neighbor were used to classify the fruit image based on extracted descriptors. An ensemble of simple classifiers trained with some combination of MPEG-7 descriptors has been constructed to increase the classification accuracy of single simple classifier. To validate the proposed method, an Indonesian fruit images data set consisted of 15 classes was developed in this study. The experiment result showed that the ensemble of simple classifiers achieved the best accuracy of 97.80% by employing linear discriminant analysis, and k-nearest neighbor as base classifiers trained using CSD, SCD, and the combination of CLD and EHD. Therefore, the proposed method achieved a good classification accuracy and can be applied in vision-based classification system in industry.
Practical ApplicationsThis study proposes a method to classify Indonesian fruits from image using MPEG-7 descriptors and the ensemble of simple classifiers. The proposed method can be applied in vision-based fruit sorting system in fruit industry as well as vision-based fruit pricing system in supermarket.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.