Spherical Brain Mapping

The Spherical Brain Mapping (SBM) is a feature extraction and visualization framework intended to map the internal structures and features of the brain onto a 2D image that summarizes all this information.

The Spherical Brain Mapping (SBM) is a framework intended to map the internal structures and features of the brain onto a 2D image that summarizes all this information, as described in [1] and previously presented in [2] and [3]. 3D brain imaging, such as MRI or PET produces a huge amount of data that is currently analysed using uni or multivariate approaches.

A new structural parametrization of MRI images has been added, using a modified hidden markov model to trace routes that follow minimal intensity change paths inside the brain, instead of the rectilinear paths used in typical SBM [4]. This file, currently only working in MATLAB, is contained in the file hmmPaths.m.

This method was published in:

  1. F.J. Martinez-Murcia et al. A Spherical Brain Mapping of MR images for the detection of Alzheimer’s Disease. Current Alzheimer Research 13(5):575-88. 2016.
  2. F.J. Martinez-Murcia et al. Projecting MRI Brain images for the detection of Alzheimer’s Disease. Stud Health Technol Inform 207, 225-33. 2014.
  3. F.J. Martínez-Murcia et al. A Volumetric Radial LBP Projection of MRI Brain Images for the Diagnosis of Alzheimer’s Disease. Lecture Notes in Computer Science 9107, 19-28. 2015.
  4. F.J. Martinez-Murcia et al. A Structural Parametrization of the Brain Using Hidden Markov Models-Based Paths in Alzheimer’s Disease. International Journal of Neural Systems 26(6) 1650024. 2016.

Project the Brain.

Example of the Projections
Example of the Projections for White and Grey Matter

Spherical Brain Mapping uses an algorithm to perform a projection of the different tissues of the brain to a single plane that can be visually analysed.

 

Locate the most signifcant areas.

Projected Atlas of the AAL regions
Projected Atlas of the AAL regions

It is possible to superimpose a projected brain atlas onto a resulting significance map (e.g., a t-map). Thereby it is easy to identify the sources of the changes in a two-dimensional map.

 

Write your own Extensions.

Spherical Brain Mapping is written in Matlab, totally compatible with Octave, and ported to Python, so that you can write your own statistical properties to project the brain. The more specific these statistical are, the more significant will be your results.

Publicado por fjmartinezmurcia

Ingeniero de Telecomunicación y Doctor en Tecnologías de la Información y las Comunicaciones por la Universidad de Granada. Investigador Juan de la Cierva en la Universidad de Málaga, especializado en procesamiento y análisis de señales e imágenes médicas cerebrales. Finalista en Famelab 2018 y ganador de 3-Minute Thesis granada 2017. Músico y friki sin remedio.