Home / Current Issue / Paper 1710590
AI-Enhanced CBCT Interpretation for Lesion Classification
Subject area: Biological & Medical Sciences · Area of research: Dental Imaging and Artificial Intelligence
DOI: https://doi.org/10.64388/IREV5I11-1710590-1475
Abstract
Given its ability to generate high-resolution 3D images of anatomical structures, Cone-Beam Computed Tomography (CBCT) has been pegged as one of major imaging modalities in dentistry and maxillofacial diagnostics. Nevertheless, manual lesion classification through CBCT tests is modernly described as time-demanding, prone to inter-observer bias, and requiring junior and senior clinical expertise. Recently, advances in AI, with deep learning models at the forefront, have begun to enhance the interpretation and efficacy of CBCTs. This paper discusses the use of AI in lesion classification through CBCT imaging and underscores its abilities to increase diagnostic accuracy and reduce diagnostic errors to effectively aid clinicians during treatment planning. It further touches upon ongoing trends and challenges as well as perspectives of integrating AI-based tools into day-to-day clinical workflows. Essentially, with the aid of machine learning and computer vision algorithms, AI-aided CBCT interpretation is regarded as the salient step toward more standardized and reliable diagnostic outcomes in dental and maxillofacial practice.
Keywords
Artificial Intelligence; Cone-Beam Computed Tomography; Deep Learning; Lesion Classification; Computer Vision; Diagnostic Imaging; Dental Radiology
How to cite this paper
@article{1710590,
author = {Viktor Dimitrov, Mette S?rensen, Jonas Keller},
title = {AI-Enhanced CBCT Interpretation for Lesion Classification},
journal = {Iconic Research And Engineering Journals},
year = {2022},
volume = {5},
number = {11},
pages = {442-449},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1710590.pdf},
abstract = {Given its ability to generate high-resolution 3D images of anatomical structures, Cone-Beam Computed Tomography (CBCT) has been pegged as one of major imaging modalities in dentistry and maxillofacial diagnostics. Nevertheless, manual lesion classification through CBCT tests is modernly described as time-demanding, prone to inter-observer bias, and requiring junior and senior clinical expertise. Recently, advances in AI, with deep learning models at the forefront, have begun to enhance the interpretation and efficacy of CBCTs. This paper discusses the use of AI in lesion classification through CBCT imaging and underscores its abilities to increase diagnostic accuracy and reduce diagnostic errors to effectively aid clinicians during treatment planning. It further touches upon ongoing trends and challenges as well as perspectives of integrating AI-based tools into day-to-day clinical workflows. Essentially, with the aid of machine learning and computer vision algorithms, AI-aided CBCT interpretation is regarded as the salient step toward more standardized and reliable diagnostic outcomes in dental and maxillofacial practice.},
keywords = {Artificial Intelligence; Cone-Beam Computed Tomography; Deep Learning; Lesion Classification; Computer Vision; Diagnostic Imaging; Dental Radiology},
month = {May},
doi = {https://doi.org/10.64388/IREV5I11-1710590-1475}
}