Influence of exposure protocol, voxel size, and artifact removal algorithm on the trueness of segmentation utilizing an artificial-intelligence-based system.

Safa AlrashedVinicius Dutra Tien Min Gabriel Chu Chao-Chieh Yang Wei-Shao Lin

Published in: Journal of prosthodontics : official journal of the American College of Prosthodontists (2024)

This study informs optimal exposure protocol and voxel size choices in CBCT imaging for true AI-based automatic segmentation with minimal radiation. The artifact removal algorithm did not influence the trueness of AI segmentation. When using an ultra-low exposure protocol to minimize patient radiation exposure in AI segmentations, a voxel size of 0.15 mm is recommended, while a voxel size of 0.45 mm should be avoided.

Keyphrases

artificial intelligence
deep learning
machine learning
convolutional neural network
big data
randomized controlled trial
high resolution
image quality
case report
magnetic resonance imaging
radiation induced