Assessment of efficacy and accuracy of segmentation methods in Dentomaxillofacial imaging- A systematic review

Background and aim: Radiographic image segmentation aims to differentiate the voxels and pixelsof a specific area of interest from the image background, which is an essential stage in supportingclinical diagnosis, treatment planning, intervention, and follow-up in dentistry and medicineThis paper aims to provide an assessment on the efficacy and accuracy of segmentation methodsin dentomaxillofacial imaging by systematically outlining, analyzing, and categorizing the relevantpublications in this field to date, highlighting the current state, and making recommendationsfor future research in the area.Methods and material: The keywords used for the search were combinations of the followingterms for each database: Artificial intelligence, Segmentation, Image interpretation, Deep Learning,Convolutional neural networks, and Head and neck imaging. After the initial search, eligiblestudies were selected based on the inclusion criteria, and a quality assessment was conducted byQUADAS-۲.Results: Primary electronic database searches resulted in ۲۷۶۳ articles. Finally, a total of ۵۲ recordswere considered suitable for this systematic review. Twenty-three (۴۴%) used CBCT as abaseline imaging modality, ۱۱ used MDCT (۲۱%),۶ used panoramic (۲۱%), ۴ used micro-CT, ۳used periapical(۱.۵%), and ۲ used ultrasonography(۳%). Segmentation through automatic algorithmswas used in the majority of the studies.Conclusion: The systematic review of the current segmentation methods in dentomaxillofacialradiology shows interesting trends, with the rising popularity of deep learning methods over time.However, continued efforts will be necessary to improve algorithms.

کلیدواژه ها:

Artificial intelligence ، Segmentation ، Image interpretation ، Deep learning ، Convolutional neural networks ، Head and neck imaging