Theme: Segmentation

Segmentation is typically the first step in extracting useful information from medical images, where we determine the underlying anatomy. Tissue segmentation, which partitions brain magnetic resonance (MR) images into gray matter (GM), white matter (WM), and  erebrospinal fluid (CSF), is a crucial step for subsequent volumetric and cortical surface analysis.  effective segmentation of neonatal brain images still remains a great challenge in many emerging neonatal studies, which have the potential of revealing interesting brain developmental patterns and also neurodevelopmental disorders.We develop segmentation schemes for healthy adults, neonatal (newborn) infants, and adults.

Surface rendering of tissue segmentation result of one subject. (a) Gray matter surface and (b) white matter surface.

Publications:

• F. Shi, D. Shen, P.-T. Yap, Y. Fan, J.-Z. Cheng, H. An, L.L. Wald, G. Gerig, J.H. Gilmore, W. Lin. “CENTS: Cortical Enhanced Neonatal Tissue Segmentation,” In Human Brain Mapping HBM, Vol. 32, No. 3, Note: ePub 5 Aug 2010, pp. 382--396. March, 2011.  DOI: 10.1002/hbm.21023  PubMed ID: 20690143
• A.R.C. Paiva, T. Tasdizen. “Fast Semi-Supervised Image Segmentation by Novelty Selection,” In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing, Dallas, Texas, pp. (to appear). March, 2010.

Quick Links

Research Projects

• Autism Centers of Excellence

• Early brain development in infants at risk for mental illness

• CAMID Neurobiological and Behavioral Consequences of Cocaine Use in Mother-Infant Dyads

• National Center for Biomedical Computing NA-MIC

• Image Analysis of Pathological changes

• Brain Lesion Modeling and Segmentation

• 4D Analysis of White Matter Diffusion
• 4D Modeling of Image Appearance Changes

PIs

• Guido Gerig
• Marcel Prastawa