Biomedical Engineering Reference
In-Depth Information
In some of the patients, MIP images tended to induce misinterpretation of
the overlapping vessels leading to wrong estimates of the neck size. Therefore,
particularly in these cases, aneurysm quantification from 3D models may help in
a more accurate determination of coil dimensions for the surgical intervention.
5.6
Conclusion
We have presented a method for three dimensional quantification of brain
aneurysms for the purpose of surgical planning and the corresponding eval-
uation study. This study demonstrates the feasibility of using implicit de-
formable models combined with non-parametric statistical information to quan-
tify aneurysm morphology and to obtain clinically relevant parameters. In sum-
mary, the technique presented in this work will contribute to the computerized
surgical planning of coiling procedures by allowing more accurate and truly 3D
quantification of brain aneurysms.
Acknowledgments
The authors would like to acknowledge Dr. R. Barrena and Dr. G. Hern andez
from the Aragon Institute of Health Sciences (Zaragoza, Spain) for providing the
data, measurements and clinical background. We also would like to acknowledge
F. M emoli for interesting conversations during this work. MHG is supported by
the grant AP2001-1678 from the Spanish Ministry of Education, Culture and
Sport. AFF is supported by a Ramon y Cajal Research Fellowship from the
Spanish Ministry of Science and Technology (MCyT). GS is supported by
ONI28NSF. This research was partially supported by the grants TIC2002-04495-
C02 and TIC2000-1635-C04-01 from the MCyT, and G03/185 from ISCIII.
Questions
1.
Why are normalized the feature vectors? In the normalization of the sam-
ple feature vectors, the mean and standard deviation extracted from the
training set are used. Explain why.
