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.


Labeling quality improvement.Change of labeling quality as the number of example subjects increases from one to eleven.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0133337.g011: Labeling quality improvement.Change of labeling quality as the number of example subjects increases from one to eleven.

Mentions: To demonstrate the benefit of our multi-atlas approach, we measured the performance by adding an example subject incrementally. Specifically, we performed our method to label tracts in one randomly chosen subject while increasing the number of example subjects from one to eleven. The labeling performance was measured as the average of sensitivity and precision for every bundle. The SKLD threshold value was set to 50,000, and the threshold value for the maximum number of votes was set to majority of the number of example subjects. Fig 11 shows the results: The performance was improved by 6.4% (LH: 4.1%, RH: 8.6%) when the number of example subjects was increased from one to eleven.


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)

Labeling quality improvement.Change of labeling quality as the number of example subjects increases from one to eleven.
© Copyright Policy
Related In: Results  -  Collection

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

pone.0133337.g011: Labeling quality improvement.Change of labeling quality as the number of example subjects increases from one to eleven.
Mentions: To demonstrate the benefit of our multi-atlas approach, we measured the performance by adding an example subject incrementally. Specifically, we performed our method to label tracts in one randomly chosen subject while increasing the number of example subjects from one to eleven. The labeling performance was measured as the average of sensitivity and precision for every bundle. The SKLD threshold value was set to 50,000, and the threshold value for the maximum number of votes was set to majority of the number of example subjects. Fig 11 shows the results: The performance was improved by 6.4% (LH: 4.1%, RH: 8.6%) when the number of example subjects was increased from one to eleven.

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.