Rechberger, Albert;
Dymerska, Barbara;
Poljanc, Karin;
Georg, Langs;
Robinson, Simon Daniel;
(2017)
Automatic venous vessel segmentation in high field, multi-echo SWI using Random Forests.
Presented at: ISMRM 25th Annual Meeting, Honolulu, HI, USA.
Preview |
Text
3676.html.pdf - Published Version Download (636kB) | Preview |
Abstract
A method for automatic venous vessel segmentation is presented that uses a Random Forest classifier supplied with a number of appearance and shape features computed separately from magnitude images, phase images and QSMs of a multi-echo T2*-weighted GE scan. The importance of each feature, and thus each echo, is investigated. The approach was tested on whole-brain 7T scans of four subjects, two of which were manually annotated, and was effective in segmenting both internal and surface veins.
Archive Staff Only
 |
View Item |
