EE Seminar: Presurgical brain white matter tractography using multiple MRI sequences
Speaker: Ilya Nelkenbaum
M.Sc. student under the supervision of Prof. Nahum Kiryati and Dr. Arnaldo Mayer
Wednesday, December 25th, 2019 at 15:30
Room 011, Kitot Bldg., Faculty of Engineering
Presurgical brain white matter tractography using multiple MRI sequences
Abstract
White matter (WM) tractography mapping is a must in neuro-surgical planning and navigation to minimize risks of iatrogenic damages. Clinical tractography pipelines still require time consuming manual operations and significant neuro-anatomical expertise, to accurately seed the tracts and remove tractography outliers.
One of the optional solutions might be automatic seeds segmentation for further tractography. Although it saves the time consuming manual delineation by neuro-anatomy experts, it still requires heavy computations required by standard tractography algorithms as well as manual tractography outliers removal.
A better solution for clinical purposes would be automatic segmentation of white matter tracts using deep neural networks, which will make the whole process fully automatic. However, most of the works in this area use a single brain MRI sequence, whereas neuro-radiologists rely on 2 or more MRI sequences, e.g. T1w and the principal direction of diffusion (PDD), for pre-surgical WM mapping.
In this work, we propose a novel neural architecture for the automatic segmentation of white matter tracts by fusing multiple MRI sequences. The proposed method is demonstrated and validated on joint T1w and PDD input sequences. It is shown to compare favorably against state-of-the art methods (Vnet, TractSeg) on the Human Connectome Project (HCP) brain scans dataset for clinically important WM tracts.
