Related Experiment Video
Updated: Jul 11, 2026
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Isointense Infant Brain Segmentation by Stacked Kernel Canonical Correlation Analysis
Li Wang1, Feng Shi1, Yaozong Gao2
1IDEA Lab, Department of Radiology and BRIC, University of North Carolina at Chapel Hill, NC, USA.
Patch-Based Techniques in Medical Imaging : First International Workshop, Patch-Mi 2015, Held in Conjunction with MICCAI 2015, Munich, Germany, October 9, 2015, Revised Selected Papers. Patch-Mi (Workshop) (1St : 2015 : Munich, Germany)
|April 11, 2017
Summary
This study introduces a new method for segmenting infant brain MR images, overcoming low contrast issues around 6 months old. The technique uses 12-month-old brain scans to guide the segmentation of younger brains, improving accuracy.
Area of Science:
- Medical Imaging
- Neuroscience
- Computer Vision
Background:
- Infant brain MRI segmentation is difficult due to rapid maturation and myelination.
- Isointense tissue contrast (white and gray matter) around 6 months poses significant challenges for automated segmentation.
Purpose of the Study:
- To develop a novel method for segmenting isointense infant brain MR images.
- To address the challenge of extremely low tissue contrast in 6-month-old infant brains.
Main Methods:
- Proposed a segmentation method based on stacked kernel canonical correlation analysis (KCCA).
- Utilized 12-month-old brain images with high contrast to guide segmentation of 6-month-old images.
- Employed stacked KCCA for optimized common feature representation and sparse patch-based multi-atlas labeling.
Main Results:
- The novel KCCA-based method demonstrated significantly improved performance compared to state-of-the-art techniques.
- Evaluated on 20 isointense brain images using leave-one-out cross-validation.
Conclusions:
- Stacked kernel canonical correlation analysis offers a robust solution for segmenting challenging isointense infant brain MR images.
- The method effectively leverages longitudinal data (12-month-old scans) to enhance segmentation accuracy in younger subjects.
