Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2015 Aug;10(8):1227-37.
doi: 10.1007/s11548-015-1174-5. Epub 2015 Apr 7.

Stability, structure and scale: improvements in multi-modal vessel extraction for SEEG trajectory planning

Maria A Zuluaga  1 , Roman Rodionov, Mark Nowell, Sufyan Achhala, Gergely Zombori, Alex F Mendelson, M Jorge Cardoso, Anna Miserocchi, Andrew W McEvoy, John S Duncan, Sébastien Ourselin
Affiliations

Stability, structure and scale: improvements in multi-modal vessel extraction for SEEG trajectory planning

Maria A Zuluaga et al. Int J Comput Assist Radiol Surg. 2015 Aug.

Abstract

Purpose: Brain vessels are among the most critical landmarks that need to be assessed for mitigating surgical risks in stereo-electroencephalography (SEEG) implantation. Intracranial haemorrhage is the most common complication associated with implantation, carrying significantly associated morbidity. SEEG planning is done pre-operatively to identify avascular trajectories for the electrodes. In current practice, neurosurgeons have no assistance in the planning of electrode trajectories. There is great interest in developing computer-assisted planning systems that can optimise the safety profile of electrode trajectories, maximising the distance to critical structures. This paper presents a method that integrates the concepts of scale, neighbourhood structure and feature stability with the aim of improving robustness and accuracy of vessel extraction within a SEEG planning system.

Methods: The developed method accounts for scale and vicinity of a voxel by formulating the problem within a multi-scale tensor voting framework. Feature stability is achieved through a similarity measure that evaluates the multi-modal consistency in vesselness responses. The proposed measurement allows the combination of multiple images modalities into a single image that is used within the planning system to visualise critical vessels.

Results: Twelve paired data sets from two image modalities available within the planning system were used for evaluation. The mean Dice similarity coefficient was 0.89 ± 0.04, representing a statistically significantly improvement when compared to a semi-automated single human rater, single-modality segmentation protocol used in clinical practice (0.80 ± 0.03).

Conclusions: Multi-modal vessel extraction is superior to semi-automated single-modality segmentation, indicating the possibility of safer SEEG planning, with reduced patient morbidity.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Vessel extraction diagram. After optimal scale selection, images are converted into tokens through analysis of the Hessian matrix. After voting, the resulting saliency maps are combined using the cosine between the vectors defining orientation. The resulting probability map is then visualised in the planning system
Fig. 2
Fig. 2
Probability maps φ obtained using, from left to right, no preferred orientation, Hessian-based analysis and structure tensor-based initialisation. The response of a vesselness filter [10] was used as initial saliency measurement for the first two cases. The approaches using the response of the vesselness filter are more sensible to fine structures. The structure tensor approach fails to detect small vessels, but has a strong response in large vessels
Fig. 3
Fig. 3
3DPC (first column) and CTA images (second column), superposed vesselness map generated by the proposed method over 3DPC (third column) and consensus for two subjects (fourth column)
Fig. 4
Fig. 4
Boxplots displaying the DSC for the proposed method, the single-modality results (without data fusion) using CTA and 3DPC, and data fusion through min and max operators. The red cross represents an outlier
Fig. 5
Fig. 5
Average execution times of the proposed approach (fast) and our original formulation Zuluaga et al. [20] as a function of the number of scales. Dice score coefficients (DSCs) for both methods are also displayed to show that speedup of the method is not at the cost of accuracy
Fig. 6
Fig. 6
Integration into the computer-assisted planning system. On top, examples of displayed extracted vessels using different colour schemes. On bottom left, display of a segmented vascular tree contrasted with the combined single-modality segmentation, right, from 3DPC (blue) and CTA (gold). The results obtained with the proposed method contain less noise
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Bériault S, Al Subaie F, Collins D, Sadikot A, Pike G. A multi-modal approach to computer-assisted deep brain stimulation trajectory planning. Int J Comput Assist Radiol Surg. 2012;7:687–704. doi: 10.1007/s11548-012-0768-4. - DOI - PubMed
    1. Cossu M, Cardinale F, Castana L, Citterio A, Francione S, Tassi L, Benabid ALM, Lo Russo G. Stereoelectroencephalography in the presurgical evaluation of focal epilepsy: a retrospective analysis of 215 procedures. Neurosurgery. 2005;57(4):706–718. doi: 10.1227/01.NEU.0000176656.33523.1e. - DOI - PubMed
    1. David O, Blauwblomme T, Job AS, C S, Hoffmann D, Minotti L, Kahane P. Imaging the seizure onset zone with stereo-electroencephalography. Brain. 2011;134:2898–2911. doi: 10.1093/brain/awr238. - DOI - PubMed
    1. Du X, Ding H, Zhou W, Zhang G, Wang G. Cerebrovascular segmentation and planning of depth electrode insertion for epilepsy surgery. Int J Comput Assist Radiol Surg. 2013;8:905–916. doi: 10.1007/s11548-013-0843-5. - DOI - PubMed
    1. Essert C, Haegelen C, Lalys F, Abadie A, Jannin P. Automatic computation of electrode trajectories for deep brain stimulation: a hybrid symbolic and numerical approach. Int J Comput Assist Radiol Surg. 2012;7(4):517–532. doi: 10.1007/s11548-011-0651-8. - DOI - PubMed

Publication types