Projects:InterleavedSegmentationAndRegistration

Interleaved Segmentation and Registration

Back to NA-MIC_Collaborations, MIT Algorithms

Objectives

To improve segmentation of brain structures.

Progress

We have combined registration of an atlas with MRI images using the Expectation-Maximization algorithm which simultaneously estimates image inhomogeneities, anatomical label maps, and a mapping from the atlas to the image space. The software is being ported to ITK.

References

• K.M. Pohl, J. Fisher, J.J. Levitt, M.E. Shenton, R. Kikinis, W.E.L. Grimson, and W.M. Wells, “ A Unifying Approach to Registration, Segmentation, and Intensity Correction, ” In Proc. MICCAI 2005: Eigth International Conference on Medical Image Computing and Computer Assisted Intervention, Palm Springs, CA, USA, Springer-Verlag, Part I, vol. 3749 of Lecture Notes in Computer Science, pp. 310-318, 2005

Key Investigators

• BWH: Sylvain Bouix, Motoaki Nakamura, Min-Seong Koo, Martha Shenton.
• MIT: Kilian Pohl, Sandy Wells, Eric Grimson
• Kitware: Luis Ibanez, Karthik Krishnan

Links

• DBP:Harvard:Collaboration:MIT
• Progress_Report:Shape_Based_Segmentation_And_Registration