Cerebrovascular segmentation in 4D ASL MRA images

Fast and accurate automatic cerebrovascular segmentation is important for clinicians and researchers to analyze the vessels of the brain, determine criteria of normality, and identify and study cerebrovascular diseases. Nevertheless, automatic segmentation is challenging due to the complex shape, inhomogeneous intensity, and inter-person variability of normal and malformed vessels. The aim of this project is to develop automatic segmentation methods of the vessels of the brain in time-of-flight magnetic resonance angiography (TOF MRA) images.

cerebrovascular

Publications

Renzo Phellan, Thomas Lindner, Michael Helle, Alexandre X. Falcão, Clarissa L. Yasuda, Magdalena Sokolska, Rolf H. Jäger, Nils D. Forkert: Segmentation-based blood flow parameter refinement in cerebrovascular structures using 4D arterial spin labeling MRA. IEEE Transactions on Biomedical Engineering, 67(7), 1936-1946, 2020.

Renzo Phellan, Thomas Lindner, Michael Helle, Alexandre X. Falcão, Thomas Okell, Nils D. Forkert: A methodology for generating four-dimensional arterial spin labeling MR angiography virtual phantoms. Medical Image Analysis, 56, 184-192, 2019.

Renzo Phellan, Thomas Lindner, Michael Helle, Alexandre X. Falcão, Nils D. Forkert: The effect of labeling duration and temporal resolution on arterial transit time estimation accuracy in 4D ASL MRA datasets - a flow phantom study. In: Liao H. et al. (eds) Machine Learning and Medical Engineering for Cardiovascular Health and Intravascular Imaging and Computer Assisted Stenting. MLMECH 2019, CVII-STENT 2019. Lecture Notes in Computer Science, Vol 11794, 141-148, 2019.
 

Team members

  • Renzo Phellan

  • Nils D. Forkert