Recent advances in 3D-CSC based MR brain image segmentation

Frank Schmitt; Lutz Priese

doi:10.1117/12.768505

Translator Disclaimer

11 March 2008 Recent advances in 3D-CSC based MR brain image segmentation

Frank Schmitt, Lutz Priese

Author Affiliations +

Proceedings Volume 6914, Medical Imaging 2008: Image Processing; 691438 (2008) https://doi.org/10.1117/12.768505
Event: Medical Imaging, 2008, San Diego, California, United States

Abstract

The 3D-CSC is a general segmentation method for voxel images. One of its possible applications is the segmentation of MR images of the human head. We here propose a self-contained method consisting of preprocessing steps which remove common artifacts from the input image, a 3D-CSC segmentation which partitions the input image into gray value similar, spatially connected regions and a final classification of CSC segments into white matter, gray matter and non-brain. We evaluate our method using the brainweb dataset for which a ground truth is available.

Citation Download Citation

Frank Schmitt and Lutz Priese "Recent advances in 3D-CSC based MR brain image segmentation", Proc. SPIE 6914, Medical Imaging 2008: Image Processing, 691438 (11 March 2008); https://doi.org/10.1117/12.768505

ACCESS THE FULL ARTICLE