nimare.parcellate.mamp
.MAMP¶
-
class
MAMP
(dataset, ids)[source]¶ Meta-analytic activation modeling-based parcellation (MAMP) [Re636c01f812e-1].
Parameters: Notes
MAMP works similarly to CBP, but skips the step of performing a MACM for each voxel. Here are the steps:
- Create an MA map for each study in the dataset.
- Concatenate MA maps across studies to create a 4D dataset.
- Extract values across studies for voxels in mask, resulting in n_voxels X n_studies array.
- Correlate “study series” between voxels to generate n_voxels X n_voxels correlation matrix.
- Convert correlation coefficients to correlation distance (1 -r) values.
- Perform clustering on correlation distance matrix.
Warning
This method is not yet implemented.
References
[Re636c01f812e-1] Yang, Yong, et al. “Identifying functional subdivisions in the human brain using meta-analytic activation modeling-based parcellation.” Neuroimage 124 (2016): 300-309. https://doi.org/10.1016/j.neuroimage.2015.08.027 Methods
fit
(self, target_mask[, n_parcels, …])Run MAMP parcellation. get_params
(self[, deep])Get parameters for this estimator. load
(filename[, compressed])Load a pickled class instance from file. save
(self, filename[, compress])Pickle the class instance to the provided file. set_params
(self, \*\*params)Set the parameters of this estimator. -
fit
(self, target_mask, n_parcels=2, kernel_estimator=<class 'nimare.meta.cbma.kernel.ALEKernel'>, **kwargs)[source]¶ Run MAMP parcellation.
Parameters: - target_mask (img_like) – Image with binary mask for region of interest to be parcellated.
- n_parcels (
int
or array_like ofint
, optional) – Number of parcels to generate for ROI. If array_like, each parcel number will be evaluated and results for all will be returned. Default is 2. - n_iters (
int
, optional) – Number of iterations to run for each parcel number. Default is 10000. - n_cores (
int
, optional) – Number of cores to use for model fitting.
Returns: Return type: results
-
get_params
(self, deep=True)[source]¶ Get parameters for this estimator.
Parameters: deep (boolean, optional) – If True, will return the parameters for this estimator and contained subobjects that are estimators. Returns: params – Parameter names mapped to their values. Return type: mapping of string to any
-
classmethod
load
(filename, compressed=True)[source]¶ Load a pickled class instance from file.
Parameters: Returns: obj – Loaded class object.
Return type: class object
-
save
(self, filename, compress=True)[source]¶ Pickle the class instance to the provided file.
Parameters:
-
set_params
(self, **params)[source]¶ Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects (such as pipelines). The latter have parameters of the form
<component>__<parameter>
so that it’s possible to update each component of a nested object.Returns: Return type: self