M
Mert R. Sabuncu
Researcher at Cornell University
Publications - 129
Citations - 10846
Mert R. Sabuncu is an academic researcher from Cornell University. The author has contributed to research in topics: Image registration & Image segmentation. The author has an hindex of 44, co-authored 129 publications receiving 9291 citations. Previous affiliations of Mert R. Sabuncu include Siemens & Princeton University.
Papers
More filters
Book ChapterDOI
Spherical Demons: Fast Surface Registration
TL;DR: The Spherical Demons algorithm for registering two spherical images is presented, which is diffeomorphic and fast - registration of two cortical mesh models with more than 100k nodes takes less than 5 minutes, comparable to the fastest surface registration algorithms.
Journal ArticleDOI
The Relevance Voxel Machine (RVoxM): A Self-Tuning Bayesian Model for Informative Image-Based Prediction
Mert R. Sabuncu,K. Van Leemput +1 more
TL;DR: The results indicate that RVoxM yields biologically meaningful models, while providing state-of-the-art predictive accuracy, in contrast to the generic machine learning algorithms used for this purpose.
Entropy-based Image Registration
TL;DR: This thesis focuses on the entropy estimation problem for image registration and provides theoretical and experimental comparisons of two important entropy estimators: the plug-in estimator and minimal entropic graphs, and develops an image registration framework based on the graph-theoretic estimator.
Journal ArticleDOI
Improved inference in Bayesian segmentation using Monte Carlo sampling: application to hippocampal subfield volumetry.
TL;DR: This work approximate the required marginalization over model parameters using computationally efficient Markov chain Monte Carlo techniques and illustrates the proposed approach using a recently developed Bayesian method for the segmentation of hippocampal subfields in brain MRI scans, showing a significant improvement in an Alzheimer's disease classification task.
Journal ArticleDOI
Morphometricity as a measure of the neuroanatomical signature of a trait.
Mert R. Sabuncu,Mert R. Sabuncu,Tian Ge,Tian Ge,Avram J. Holmes,Avram J. Holmes,Jordan W. Smoller,Jordan W. Smoller,Randy L. Buckner,Bruce Fischl,Bruce Fischl +10 more
TL;DR: The results demonstrate that morphometricity can provide novel insights about the neuroanatomical correlates of a diverse set of traits, revealing associations that might not be detectable through traditional statistical techniques.