Advanced search
1 file | 1.99 MB

The effect of morphometric atlas selection on multi-atlas-based automatic brachial plexus segmentation

Joris Van de Velde (UGent) , Johan Wouters (UGent) , Tom Vercauteren (UGent) , Werner De Gersem (UGent) , Eric Achten (UGent) , Wilfried De Neve (UGent) and Tom Van Hoof (UGent)
Author
Organization
Abstract
Purpose: The present study aimed to measure the effect of a morphometric atlas selection strategy on the accuracy of multi-atlas-based BP autosegmentation using the commercially available software package ADMIRE (R) and to determine the optimal number of selected atlases to use. Autosegmentation accuracy was measured by comparing all generated automatic BP segmentations with anatomically validated gold standard segmentations that were developed using cadavers. Materials and methods: Twelve cadaver computed tomography (CT) atlases were included in the study. One atlas was selected as a patient in ADMIRE (R), and multi-atlas-based BP autosegmentation was first performed with a group of morphometrically preselected atlases. In this group, the atlases were selected on the basis of similarity in the shoulder protraction position with the patient. The number of selected atlases used started at two and increased up to eight. Subsequently, a group of randomly chosen, non-selected atlases were taken. In this second group, every possible combination of 2 to 8 random atlases was used for multi-atlas-based BP autosegmentation. For both groups, the average Dice similarity coefficient (DSC), Jaccard index (JI) and Inclusion index (INI) were calculated, measuring the similarity of the generated automatic BP segmentations and the gold standard segmentation. Similarity indices of both groups were compared using an independent sample t-test, and the optimal number of selected atlases was investigated using an equivalence trial. Results: For each number of atlases, average similarity indices of the morphometrically selected atlas group were significantly higher than the random group (p<0,05). In this study, the highest similarity indices were achieved using multi-atlas autosegmentation with 6 selected atlases (average DSC = 0,598; average JI = 0,434; average INI = 0,733). Conclusions: Morphometric atlas selection on the basis of the protraction position of the patient significantly improves multi-atlas-based BP autosegmentation accuracy. In this study, the optimal number of selected atlases used was six, but for definitive conclusions about the optimal number of atlases and to improve the autosegmentation accuracy for clinical use, more atlases need to be included.
Keywords
Cadavers, ACCURACY, Brachial plexus, Morphometric atlas selection, Autosegmentation, Multi-atlas-based

Downloads

  • The effect of morphometric atlas selection.pdf
    • full text
    • |
    • open access
    • |
    • PDF
    • |
    • 1.99 MB

Citation

Please use this url to cite or link to this publication:

Chicago
Van de Velde, Joris, Johan Wouters, Tom Vercauteren, Werner De Gersem, Eric Achten, Wilfried De Neve, and Tom Van Hoof. 2015. “The Effect of Morphometric Atlas Selection on Multi-atlas-based Automatic Brachial Plexus Segmentation.” Radiation Oncology 10.
APA
Van de Velde, Joris, Wouters, J., Vercauteren, T., De Gersem, W., Achten, E., De Neve, W., & Van Hoof, T. (2015). The effect of morphometric atlas selection on multi-atlas-based automatic brachial plexus segmentation. RADIATION ONCOLOGY, 10.
Vancouver
1.
Van de Velde J, Wouters J, Vercauteren T, De Gersem W, Achten E, De Neve W, et al. The effect of morphometric atlas selection on multi-atlas-based automatic brachial plexus segmentation. RADIATION ONCOLOGY. 2015;10.
MLA
Van de Velde, Joris, Johan Wouters, Tom Vercauteren, et al. “The Effect of Morphometric Atlas Selection on Multi-atlas-based Automatic Brachial Plexus Segmentation.” RADIATION ONCOLOGY 10 (2015): n. pag. Print.
@article{7124585,
  abstract     = {Purpose: The present study aimed to measure the effect of a morphometric atlas selection strategy on the accuracy of multi-atlas-based BP autosegmentation using the commercially available software package ADMIRE (R) and to determine the optimal number of selected atlases to use. Autosegmentation accuracy was measured by comparing all generated automatic BP segmentations with anatomically validated gold standard segmentations that were developed using cadavers. 
Materials and methods: Twelve cadaver computed tomography (CT) atlases were included in the study. One atlas was selected as a patient in ADMIRE (R), and multi-atlas-based BP autosegmentation was first performed with a group of morphometrically preselected atlases. In this group, the atlases were selected on the basis of similarity in the shoulder protraction position with the patient. The number of selected atlases used started at two and increased up to eight. Subsequently, a group of randomly chosen, non-selected atlases were taken. In this second group, every possible combination of 2 to 8 random atlases was used for multi-atlas-based BP autosegmentation. For both groups, the average Dice similarity coefficient (DSC), Jaccard index (JI) and Inclusion index (INI) were calculated, measuring the similarity of the generated automatic BP segmentations and the gold standard segmentation. Similarity indices of both groups were compared using an independent sample t-test, and the optimal number of selected atlases was investigated using an equivalence trial. 
Results: For each number of atlases, average similarity indices of the morphometrically selected atlas group were significantly higher than the random group (p{\textlangle}0,05). In this study, the highest similarity indices were achieved using multi-atlas autosegmentation with 6 selected atlases (average DSC = 0,598; average JI = 0,434; average INI = 0,733). 
Conclusions: Morphometric atlas selection on the basis of the protraction position of the patient significantly improves multi-atlas-based BP autosegmentation accuracy. In this study, the optimal number of selected atlases used was six, but for definitive conclusions about the optimal number of atlases and to improve the autosegmentation accuracy for clinical use, more atlases need to be included.},
  articleno    = {260},
  author       = {Van de Velde, Joris and Wouters, Johan and Vercauteren, Tom and De Gersem, Werner and Achten, Eric and De Neve, Wilfried and Van Hoof, Tom},
  issn         = {1748-717X},
  journal      = {RADIATION ONCOLOGY},
  keyword      = {Cadavers,ACCURACY,Brachial plexus,Morphometric atlas selection,Autosegmentation,Multi-atlas-based},
  language     = {eng},
  pages        = {8},
  title        = {The effect of morphometric atlas selection on multi-atlas-based automatic brachial plexus segmentation},
  url          = {http://dx.doi.org/10.1186/s13014-015-0570-x},
  volume       = {10},
  year         = {2015},
}

Altmetric
View in Altmetric
Web of Science
Times cited: