SPAM recognition, local registration

The SPAM sulci recognition is a newer alternative to the older recognition process. Several variants of it are available under the SPAM recognition process. This one is the "local registration" method, which should take place after a "global registration".

Description

SPAM recognition is based on a probabilistic model which provides for any 3D position the probability of presence of every sulcus. Several variants and additions may also be taken into account (conjoint registration, additional prior contstraints, mix with the older neural network-based recognition, etc.) in a bayesian probabilistic framework.

The current version is a second step, and must take place after a global registration step. It performs "Local registration", and optimizes both the sulci labelings and a set of rigid registrations between the cortical data of the current subject and the SPAM maps. A local registration is performed for each sulcus, at each step of the iterative labeling process.

Other methods can be accessed via the general process SPAM recognition.

For a more precise description of the method, see:

• M. Perrot, D. Rivière, and J.-F. Mangin. Cortical sulci recognition and spatial normalization. Medical Image Analysis, 15(4):529-550, 2011.
• M. Perrot, D. Rivière, A. Tucholka, and J.-F. Mangin. Joint Bayesian Cortical Sulci Recognition and Spatial Normalization. In Proc. 21th IPMI, LNCS-5636, Williamsburg, VA, pages 176-187, July 2009..

Warning: additional model data are required:

The process uses learned SPAM models, which are a little too big to be distributed with the main BrainVISA package. They are distributed as separate packages which should be installed on the BrainVISA distribution. They can be very easily installed using the process SPAM install models.

Parameters

data_graph: Cortical folds graph ( input )

output_graph: Labelled Cortical folds graph ( output )

model: Sulci Segments Model ( input )

posterior_probabilities: Sulci Labels Segmentwise Posterior Probabilities ( output )

labels_translation_map: Label translation ( input )

labels_priors: Sulci Labels Priors ( input )

local_referentials: Sulci Local referentials ( input )

direction_priors: Sulci Direction Transformation Priors ( input )

angle_priors: Sulci Angle Transformation Priors ( input )

translation_priors: Sulci Translation Transformation Priors ( input )

output_local_transformations: Sulci Local SPAM transformations Directory ( optional, output )

initial_transformation: Transformation matrix ( optional, input )

global_transformation: Sulci Talairach to Global SPAM transformation ( optional, input )

Technical information

Toolbox : Morphologist

User level : 2

Identifier : spam_recognitionlocal

File name : brainvisa/toolboxes/morphologist/processes/Sulci/Recognition/spam_recognitionlocal.py

Supported file formats :

data_graph :

Graph and data

output_graph :

Graph and data

model :

Text Data Table

posterior_probabilities :

CSV file

labels_translation_map :

Label Translation, DEF Label Translation

labels_priors :

Text Data Table

local_referentials :

Text Data Table

direction_priors :

Text Data Table

angle_priors :

Text Data Table

translation_priors :

Text Data Table

output_local_transformations :

Directory

initial_transformation :

Transformation matrix

global_transformation :

Transformation matrix