Related Experiment Video
Updated: Apr 7, 2026

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
Automatic correction of dental artifacts in PET/MRI
Claes N Ladefoged1, Flemming L Andersen1, Sune H Keller1
1University of Copenhagen , Department of Clinical Physiology, Nuclear Medicine and PET, Rigshospitalet, Blegdamsvej 9, Copenhagen 2100, Denmark.
Dental fillings in PET/MRI scans create artificial air regions, impacting attenuation correction. This study introduces a novel method using active contours and machine learning to accurately correct these artifacts, improving image quality.
Area of Science:
- Medical Imaging
- Image Processing
- Radiological Physics
Background:
- Magnetic resonance (MR)-based attenuation correction in positron emission tomography/MR imaging (PET/MRI) is crucial for accurate quantitative analysis.
- Signal voids in MRIs due to dental fillings are erroneously segmented as air, leading to significant artifacts in the attenuation map.
- These artifacts compromise the accuracy of PET quantification in the head and neck region.
Purpose of the Study:
- To develop and validate a novel method for correcting artificial air regions caused by dental fillings in PET/MRI attenuation maps.
- To improve the accuracy of attenuation correction in PET/MRI by differentiating between true air cavities and artifactual regions.
Main Methods:
- An extension to an active contour algorithm was developed to delineate artifact contours using non-attenuation corrected PET and the original attenuation map.
- A combined approach using artifact region templates, active shape models, and k-nearest-neighbors was employed to differentiate artifacts from anatomical air.
- The method was evaluated on 25 [Formula: see text]-fluorodeoxyglucose PET/MR patient datasets.
Main Results:
- The proposed method successfully delineated the outer contour of artifacts connected to the background.
- The combined artifact differentiation approach effectively distinguished between dental filling artifacts and anatomical air regions.
- An average of [Formula: see text] of artifact areas were corrected, demonstrating significant improvement.
Conclusions:
- The developed method provides an effective solution for correcting dental filling-induced artifacts in PET/MRI attenuation correction.
- Accurate attenuation correction is vital for reliable quantitative PET imaging, especially in the presence of metallic implants.
- This technique has the potential to enhance diagnostic accuracy and reduce quantification errors in PET/MRI studies involving patients with dental work.
More Related Videos
06:53Management of Respiratory Motion Artefacts in 18F-fluorodeoxyglucose Positron Emission Tomography using an Amplitude-Based Optimal Respiratory Gating Algorithm
Published on: July 23, 2020
07:13Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
Published on: October 27, 2023