Z
Zahra Karimaghaloo
Researcher at McGill University
Publications - 17
Citations - 402
Zahra Karimaghaloo is an academic researcher from McGill University. The author has contributed to research in topics: Imaging phantom & Image registration. The author has an hindex of 9, co-authored 17 publications receiving 361 citations. Previous affiliations of Zahra Karimaghaloo include Montreal Neurological Institute and Hospital & Queen's University.
Papers
More filters
Journal ArticleDOI
Self-similarity weighted mutual information: a new nonrigid image registration metric.
TL;DR: This work proposes a self-similarity weighted graph-based implementation of α-mutual information (α-MI) for nonrigid image registration and shows that SeSaMI produces a robust and smooth cost function and outperforms the state of the art statistical based similarity metrics in simulation and using data from image-guided neurosurgery.
Journal ArticleDOI
Evaluation of state-of-the-art segmentation algorithms for left ventricle infarct from late Gadolinium enhancement MR images
Rashed Karim,Pranav Bhagirath,Piet Claus,R. James Housden,Zhong Chen,Zahra Karimaghaloo,Hyon-Mok Sohn,Laura Lara Rodríguez,Sergio Vera,Xènia Albà,Anja Hennemuth,Heinz-Otto Peitgen,Tal Arbel,Miguel Ángel González Ballester,Alejandro F. Frangi,Marco J.W. Götte,Reza Razavi,Tobias Schaeffter,Kawal Rhode +18 more
TL;DR: The benchmarking evaluation framework can be used to test and benchmark future algorithms that detect and quantify infarct in LGE CMR images of the LV, with the exception of the Full-Width-at-Half-Maximum (FWHM) fixed-thresholding method.
Journal ArticleDOI
Nonrigid Registration of Ultrasound and MRI Using Contextual Conditioned Mutual Information
TL;DR: This work uses CoCoMI as the similarity measure in a regularized cost function with a B-spline deformation field and efficiently optimize the cost function using a stochastic gradient descent method.
Journal ArticleDOI
Automatic Detection of Gadolinium-Enhancing Multiple Sclerosis Lesions in Brain MRI Using Conditional Random Fields
TL;DR: An automatic, probabilistic framework for segmentation of gadolinium-enhancing lesions in MS using conditional random fields is presented and superior performance of the proposed algorithm is demonstrated at successfully detecting all of the gadolinia-enhanced lesions while maintaining a low false positive lesion count.
Patent
Marker localization using intensity-based registration of imaging modalities
TL;DR: In this paper, the authors presented methods and systems for registering image data from two imaging modalities, to produce an image having features from both imaging technologies, in particular, the methods and system relate to intensity-based registration of the image data.