An objective method to optimize the MR sequence set for plaque classification in carotid vessel wall images using
Ronald van 't Klooster1, Andrew J Patterson, Victoria E Young
1Division of Image Processing, Department of Radiology, Leiden University Medical Center, Leiden, The Netherlands.
Plos One
|November 7, 2013
Summary
Optimizing magnetic resonance imaging (MRI) protocols for carotid artery atherosclerosis can significantly reduce scan times. A new automated method achieved 60% shorter scans with comparable plaque segmentation performance.
Area of Science:
- Medical Imaging
- Cardiovascular Research
- Artificial Intelligence in Medicine
Background:
- Carotid artery atherosclerosis assessment relies on Magnetic Resonance (MR) imaging protocols.
- Balancing scan duration with image quality is crucial for disease evaluation.
- Automated image segmentation aids in classifying soft plaque within vessel walls.
Purpose of the Study:
- To develop an objective method for optimizing MR imaging sequence sets for carotid artery plaque classification.
- To evaluate the trade-off between scan duration and automated segmentation performance.
- To enable shorter scanning times without compromising diagnostic accuracy.
Main Methods:
- Developed an automated method using statistical pattern recognition for soft plaque classification.
- Utilized extensive MR contrast weightings and manual segmentations validated by histology.
- Evaluated segmentation performance across nine different contrast weightings.
Main Results:
- The optimal set for segmentation included five contrast weightings.
- A reduced set of three contrast weightings achieved similar performance.
- This reduction led to over 60% decrease in scan time.
Conclusions:
- An objective approach effectively optimizes MR imaging protocols for carotid artery atherosclerosis.
- Selecting three contrast weightings significantly reduces scan time while maintaining segmentation accuracy.
- This method can improve image interpretation and be applied to other research areas.
