A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis

  title={A Tetrahedron-Based Heat Flux Signature for Cortical Thickness Morphometry Analysis},
  author={Yonghui Fan and G. Wang and Natasha Lepore and Yalin Wang},
  journal={Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention},
  • Yonghui Fan, G. Wang, Yalin Wang
  • Published 16 September 2018
  • Biology
  • Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
Cortical thickness analysis of brain magnetic resonance images is an important technique in neuroimaging research. There are two main computational paradigms, namely voxel-based and surface-based methods. Recently, a tetrahedron-based volumetric morphometry (TBVM) approach involving proper discretization methods was proposed. The multi-scale and physics-based geometric features generated through such methods may yield stronger statistical power. However, several challenges, such as the lack of… 
Morphometric Gaussian process for landmarking on grey matter tetrahedral models
A morphometric Gaussian process (M-GP) is proposed as a novel Bayesian model on the gray matter tetrahedral meshes and an M-GP regression landmarking algorithm is implemented as a manifold learning method for non-linear dimensionality reduction.
Fast Polynomial Approximation of Heat Kernel Convolution on Manifolds and Its Application to Brain Sulcal and Gyral Graph Pattern Analysis
A new fast and accurate numerical scheme to solve heat diffusion on surface meshes by approximating the heat kernel convolution using high degree orthogonal polynomials in the spectral domain by derived the closed-form expression of the spectral decomposition of the Laplace-Beltrami operator.
Convolutional Bayesian Models for Anatomical Landmarking on Multi-dimensional Shapes
A convolutional Bayesian model for anatomical landmarking on multi-dimensional shapes is proposed that is flexible and efficient in extracting arbitrary numbers of landmarks and the posterior inference is geometrically meaningful without entangling with extra features.
Predicting Future Cognitive Decline with Hyperbolic Stochastic Coding
Multi-task Dictionary Learning Based on Convolutional Neural Networks for Longitudinal Clinical Score Predictions in Alzheimer's Disease
A novel computer-aided AD diagnosis system CNN-Multitask Stochastic Coordinate Coding (MSCC) which integrates CNN with transfer learning strategy, a novel MSCC algorithm and effective AD-related biomarkers-multivariate morphometry statistics (MMS) is proposed.


Three‐dimensional mapping of cortical thickness using Laplace's Equation
A novel, computerized method of examining cerebral cortical thickness is presented, which presents graphical results that map cortical thickness everywhere in a normal brain, and shows global variations in cortical thickness consistent with known neuroanatomy.
Voxel-Based Morphometry—The Methods
At its simplest, voxel-based morphometry (VBM) involves a voxel-wise comparison of the local concentration of gray matter between two groups of subjects. The procedure is relatively straightforward
Measuring the thickness of the human cerebral cortex from magnetic resonance images.
  • B. Fischl, A. Dale
  • Biology, Psychology
    Proceedings of the National Academy of Sciences of the United States of America
  • 2000
An automated method for accurately measuring the thickness of the cerebral cortex across the entire brain and for generating cross-subject statistics in a coordinate system based on cortical anatomy is presented.
In Vivo Mapping of Gray Matter Loss with Voxel-Based Morphometry in Mild Alzheimer's Disease
This study has mapped gray matter density by means of voxel-based morphometry on T1-weighted MRI volume sets in 19 patients with mild AD and 16 healthy subjects of similar age and gender ratio and report highly significant clusters of gray matter loss with almost symmetrical distribution.
Volumetric Harmonic Map
It is suggested that 3D harmonic mapping of volume can provide a canonical coordinate system for feature identification and registration for computer animation and medical imaging.