A Generative Model for Image Segmentation Based on Label Fusion

• Published in: IEEE transactions on medical imaging Vol. 29; no. 10; pp. 1714 - 1729
• Main Authors: Sabuncu, Mert R, Yeo, B T Thomas, Van Leemput, K, Fischl, Bruce, Golland, Polina
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2010; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Aging; Algorithms; Biomedical imaging; Brain; Brain - anatomy & histology; Cerebral cortex; Computer Simulation; Fusion power generation; Humans; Image Enhancement - methods; Image generation; Image Interpretation, Computer-Assisted - methods; Image parcellation; image registration; Image segmentation; Inference algorithms; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Models, Anatomic; Models, Neurological; Pattern Recognition, Automated - methods; Reproducibility of Results; Robustness; Sensitivity and Specificity; Studies; Subtraction Technique; Testing

We propose a nonparametric, probabilistic model for the automatic segmentation of medical images, given a training set of images and corresponding label maps. The resulting inference algorithms rely on pairwise registrations between the test image and individual training images. The training labels...