M
Matthew Toews
Researcher at École de technologie supérieure
Publications - 98
Citations - 1544
Matthew Toews is an academic researcher from École de technologie supérieure. The author has contributed to research in topics: Feature (computer vision) & Image registration. The author has an hindex of 20, co-authored 87 publications receiving 1300 citations. Previous affiliations of Matthew Toews include Brigham and Women's Hospital & Harvard University.
Papers
More filters
Journal ArticleDOI
Detection, Localization, and Sex Classification of Faces from Arbitrary Viewpoints and under Occlusion
Matthew Toews,Tal Arbel +1 more
TL;DR: A comparison with the geometry-free bag-of-words model shows that geometrical information provided by the framework improves classification, and a comparison with support vector machines demonstrates that Bayesian classification results in superior performance.
Journal ArticleDOI
Feature-based morphometry: discovering group-related anatomical patterns.
TL;DR: In this article, feature-based morphometry (FBM) is proposed to identify distinctive anatomical patterns that may only be present in subsets of subjects, due to disease or anatomical variability.
Journal ArticleDOI
Efficient and robust model-to-image alignment using 3D scale-invariant features
TL;DR: Feature-Based Alignment (FBA) as mentioned in this paperBA is a general method for efficient and robust model-to-image alignment, where features are incorporated as a latent random variable and marginalized out in computing a maximum a posteriori alignment solution.
Journal ArticleDOI
Novel Radiomic Features Based on Joint Intensity Matrices for Predicting Glioblastoma Patient Survival Time
TL;DR: This study demonstrated the usefulness of modeling the joint intensity characteristics of CE-T1 and FLAIR images for predicting the prognosis of patients with GBM, with significantly higher AUC values than those based on standard GLCMs and gene expression.
Journal ArticleDOI
Classifications of Multispectral Colorectal Cancer Tissues Using Convolution Neural Network.
Hawraa Haj-Hassan,Ahmad Chaddad,Youssef Harkouss,Christian Desrosiers,Matthew Toews,Camel Tanougast +5 more
TL;DR: Experimental results demonstrate the effectiveness of CNN for the classification of CRC tissue types, in particular when using presegmented regions of interest.