Dental-YOLO: Alveolar Bone and Mandibular Canal Detection on Cone Beam Computed Tomography Images for Dental Implant Planning

Abstract

In planning a mandibular posterior dental implant, identifying the exact location of the \nalveolar bone (AB) and mandibular canal (MC) is essential to determine the height and width of the \navailable bone. Cone beam computed tomography (CBCT) is a 3D imaging modality widely used for dental \nimplant planning, which requires a lower radiation dose compared to medical CT and can provide crosssectional image quality to visualize AB and MC. The radiologist carried out the AB and MC detection \nprocesses manually on each section of the CBCT image until the appropriate area was determined for bone \nmeasurement. This process is time consuming, and the measurement accuracy depends on the ability and \nexperience of the radiologist. This study proposes an automatic and simultaneous detection system for AB \nand MC based on 2D grayscale CBCT images, that can simplify and expedite dental implant planning. \nWe introduce Dental-YOLO, an efficient version of YOLOv4 specifically developed to detect AB and \nMC, with two-scale feature maps at low and high scales. The height and width of the available bone in \nthe implant area were estimated by using the detected bounding box attributes. The AB and MC detection \nperformances using Dental-YOLO reached a mean average precision of 99.46%. The two-way analysis of \nvariance (ANOVA) test showed no difference in the bone height and width measurements produced by the \nproposed approach and manual measurement by radiologists. Our results suggest that the Dental-YOLO \ndetection system could be helpful for dental implant surgery and presurgical treatment planning.