Fiber tracking is a standard approach for the visualization of the results of Diffusion Tensor Imaging (DTI). Individual fibers are reconstructed from the tensor information by tracing streamlines. Usually fibers are defined by manually setting seed points. In this case, the result is biased by the user and therefore not easily reproducible. Some methods propose to seed through the whole volume to avoid manual seeding. However, white matter is a complex structure and the image gets easily cluttered. This makes it difficult to see meaningful structures. Fibers form anatomically entities called bundles. Several authors have proposed to use clustering techniques for fibers, such that the enormous amount of individual fibers is reduced to a limited number of logical fiber clusters that are more manageable and understandable. Clustering might also be used to explore and obtain quantitative comparisons by unbiased measurements in anatomically structures. Different clustering algorithms and different options within a clustering algorithm (e.g., similarity measure between fibers) can be chosen. Furthermore, clustering algorithms have parameters to tune such as the amount of clusters to obtain. It is not clear which method or distance measure produces the best results. Many combinations exist and therefore it is also not viable that physicians evaluate all possible combinations. We present the results of the evaluation of different similarity measures and clustering techniques using the framework presented by Moberts et al

title = "Evaluation of white matter fiber clustering methods for diffusion tensor imaging",

abstract = "Fiber tracking is a standard approach for the visualization of the results of Diffusion Tensor Imaging (DTI). Individual fibers are reconstructed from the tensor information by tracing streamlines. Usually fibers are defined by manually setting seed points. In this case, the result is biased by the user and therefore not easily reproducible. Some methods propose to seed through the whole volume to avoid manual seeding. However, white matter is a complex structure and the image gets easily cluttered. This makes it difficult to see meaningful structures. Fibers form anatomically entities called bundles. Several authors have proposed to use clustering techniques for fibers, such that the enormous amount of individual fibers is reduced to a limited number of logical fiber clusters that are more manageable and understandable. Clustering might also be used to explore and obtain quantitative comparisons by unbiased measurements in anatomically structures. Different clustering algorithms and different options within a clustering algorithm (e.g., similarity measure between fibers) can be chosen. Furthermore, clustering algorithms have parameters to tune such as the amount of clusters to obtain. It is not clear which method or distance measure produces the best results. Many combinations exist and therefore it is also not viable that physicians evaluate all possible combinations. We present the results of the evaluation of different similarity measures and clustering techniques using the framework presented by Moberts et al",

author = "Anna Vilanova and B. Moberts and Wijk, {Jarke J. van} and {Op denBuijs}, J. and F.G. Roos and Pul, {C. van}",

T1 - Evaluation of white matter fiber clustering methods for diffusion tensor imaging

AU - Vilanova, Anna

AU - Moberts, B.

AU - Wijk, Jarke J. van

AU - Op denBuijs, J.

AU - Roos, F.G.

AU - Pul, C. van

PY - 2006

Y1 - 2006

N2 - Fiber tracking is a standard approach for the visualization of the results of Diffusion Tensor Imaging (DTI). Individual fibers are reconstructed from the tensor information by tracing streamlines. Usually fibers are defined by manually setting seed points. In this case, the result is biased by the user and therefore not easily reproducible. Some methods propose to seed through the whole volume to avoid manual seeding. However, white matter is a complex structure and the image gets easily cluttered. This makes it difficult to see meaningful structures. Fibers form anatomically entities called bundles. Several authors have proposed to use clustering techniques for fibers, such that the enormous amount of individual fibers is reduced to a limited number of logical fiber clusters that are more manageable and understandable. Clustering might also be used to explore and obtain quantitative comparisons by unbiased measurements in anatomically structures. Different clustering algorithms and different options within a clustering algorithm (e.g., similarity measure between fibers) can be chosen. Furthermore, clustering algorithms have parameters to tune such as the amount of clusters to obtain. It is not clear which method or distance measure produces the best results. Many combinations exist and therefore it is also not viable that physicians evaluate all possible combinations. We present the results of the evaluation of different similarity measures and clustering techniques using the framework presented by Moberts et al

AB - Fiber tracking is a standard approach for the visualization of the results of Diffusion Tensor Imaging (DTI). Individual fibers are reconstructed from the tensor information by tracing streamlines. Usually fibers are defined by manually setting seed points. In this case, the result is biased by the user and therefore not easily reproducible. Some methods propose to seed through the whole volume to avoid manual seeding. However, white matter is a complex structure and the image gets easily cluttered. This makes it difficult to see meaningful structures. Fibers form anatomically entities called bundles. Several authors have proposed to use clustering techniques for fibers, such that the enormous amount of individual fibers is reduced to a limited number of logical fiber clusters that are more manageable and understandable. Clustering might also be used to explore and obtain quantitative comparisons by unbiased measurements in anatomically structures. Different clustering algorithms and different options within a clustering algorithm (e.g., similarity measure between fibers) can be chosen. Furthermore, clustering algorithms have parameters to tune such as the amount of clusters to obtain. It is not clear which method or distance measure produces the best results. Many combinations exist and therefore it is also not viable that physicians evaluate all possible combinations. We present the results of the evaluation of different similarity measures and clustering techniques using the framework presented by Moberts et al