Limits...
An Example-Based Multi-Atlas Approach to Automatic Labeling of White Matter Tracts.

Yoo SW, Guevara P, Jeong Y, Yoo K, Shin JS, Mangin JF, Seong JK - PLoS ONE (2015)

Bottom Line: To further enhance the computational efficiency, we implemented our approach on the graphics processing unit (GPU).Through nested cross-validation we demonstrated that our approach yielded high classification performance.The average sensitivities for bundles in the left and right hemispheres were 89.5% and 91.0%, respectively, and their average false discovery rates were 14.9% and 14.2%, respectively.

View Article: PubMed Central - PubMed

Affiliation: Department of Biomedical Engineering, Korea University, Seoul, Republic of Korea; Department of Computer Science, KAIST, Daejeon, Republic of Korea.

ABSTRACT
We present an example-based multi-atlas approach for classifying white matter (WM) tracts into anatomic bundles. Our approach exploits expert-provided example data to automatically classify the WM tracts of a subject. Multiple atlases are constructed to model the example data from multiple subjects in order to reflect the individual variability of bundle shapes and trajectories over subjects. For each example subject, an atlas is maintained to allow the example data of a subject to be added or deleted flexibly. A voting scheme is proposed to facilitate the multi-atlas exploitation of example data. For conceptual simplicity, we adopt the same metrics in both example data construction and WM tract labeling. Due to the huge number of WM tracts in a subject, it is time-consuming to label each WM tract individually. Thus, the WM tracts are grouped according to their shape similarity, and WM tracts within each group are labeled simultaneously. To further enhance the computational efficiency, we implemented our approach on the graphics processing unit (GPU). Through nested cross-validation we demonstrated that our approach yielded high classification performance. The average sensitivities for bundles in the left and right hemispheres were 89.5% and 91.0%, respectively, and their average false discovery rates were 14.9% and 14.2%, respectively.

No MeSH data available.


Skeleton of nested cross-validation.The skeleton of the nested cross-validation for measuring the performance of the proposed method.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4520495&req=5

pone.0133337.g005: Skeleton of nested cross-validation.The skeleton of the nested cross-validation for measuring the performance of the proposed method.

Mentions: The performance of the proposed approach for automatic classification was assessed through nested cross-validation. The nested cross-validation was used to avoid duplicate use of the same data for parameter tuning and testing. Fig 5 shows the skeleton of the nested cross-validation. The inner loop is used to determine the parameter set, while the outer loop is for testing each example subject data using the determined parameter set. The parameter set consists of distance threshold and vote number threshold. SKLD distance is used for the tract group labeling approach, while Mahalanobis distance was used for the direct tract labeling approach. We uniformly sampled between 40,000 and 60,000 for the SKLD distance threshold, and between 200 and 400 for the Mahalanobis distance threshold. The vote number threshold was uniformly sampled between 5 and 7.


An Example-Based Multi-Atlas Approach to Automatic Labeling of White Matter Tracts.

Yoo SW, Guevara P, Jeong Y, Yoo K, Shin JS, Mangin JF, Seong JK - PLoS ONE (2015)

Skeleton of nested cross-validation.The skeleton of the nested cross-validation for measuring the performance of the proposed method.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4520495&req=5

pone.0133337.g005: Skeleton of nested cross-validation.The skeleton of the nested cross-validation for measuring the performance of the proposed method.
Mentions: The performance of the proposed approach for automatic classification was assessed through nested cross-validation. The nested cross-validation was used to avoid duplicate use of the same data for parameter tuning and testing. Fig 5 shows the skeleton of the nested cross-validation. The inner loop is used to determine the parameter set, while the outer loop is for testing each example subject data using the determined parameter set. The parameter set consists of distance threshold and vote number threshold. SKLD distance is used for the tract group labeling approach, while Mahalanobis distance was used for the direct tract labeling approach. We uniformly sampled between 40,000 and 60,000 for the SKLD distance threshold, and between 200 and 400 for the Mahalanobis distance threshold. The vote number threshold was uniformly sampled between 5 and 7.

Bottom Line: To further enhance the computational efficiency, we implemented our approach on the graphics processing unit (GPU).Through nested cross-validation we demonstrated that our approach yielded high classification performance.The average sensitivities for bundles in the left and right hemispheres were 89.5% and 91.0%, respectively, and their average false discovery rates were 14.9% and 14.2%, respectively.

View Article: PubMed Central - PubMed

Affiliation: Department of Biomedical Engineering, Korea University, Seoul, Republic of Korea; Department of Computer Science, KAIST, Daejeon, Republic of Korea.

ABSTRACT
We present an example-based multi-atlas approach for classifying white matter (WM) tracts into anatomic bundles. Our approach exploits expert-provided example data to automatically classify the WM tracts of a subject. Multiple atlases are constructed to model the example data from multiple subjects in order to reflect the individual variability of bundle shapes and trajectories over subjects. For each example subject, an atlas is maintained to allow the example data of a subject to be added or deleted flexibly. A voting scheme is proposed to facilitate the multi-atlas exploitation of example data. For conceptual simplicity, we adopt the same metrics in both example data construction and WM tract labeling. Due to the huge number of WM tracts in a subject, it is time-consuming to label each WM tract individually. Thus, the WM tracts are grouped according to their shape similarity, and WM tracts within each group are labeled simultaneously. To further enhance the computational efficiency, we implemented our approach on the graphics processing unit (GPU). Through nested cross-validation we demonstrated that our approach yielded high classification performance. The average sensitivities for bundles in the left and right hemispheres were 89.5% and 91.0%, respectively, and their average false discovery rates were 14.9% and 14.2%, respectively.

No MeSH data available.