使用nilearn里的Dictlearning函数实现fMRI图像激活区域显示

使用nilearn里的Dictlearning函数实现fMRI图像激活区域显示

说明：Dictlearning提取的信号比ICA更干净，所以要注意控制步骤二中alpha参数的大小

一、加载数据

import nilearn
from nilearn import datasets

func_filenames = nilearn.image.load_img("data/4D/Ontario_sub94652_rest.nii")
print(func_filenames.shape)

二、调用Dictlearning

from nilearn.decomposition import DictLearning

dict_learning = DictLearning(n_components=20,
                             memory="nilearn_cache",
                             memory_level=2,
                             verbose=12,
                             random_state=0,
                             n_epochs=1,
                             alpha=3,
                             mask_strategy='template')

print('[Example] Fitting dicitonary learning model')

dict_learning.fit(func_filenames)

三、存储提取激活区域后的图像

print('[Example] Saving results')
dictlearning_components_img = dict_learning.components_img_
dictlearning_components_img.to_filename('dictionary_learning_resting_state.nii.gz')

四、显示字典学习的组成分显示

from nilearn import plotting
from nilearn.image import iter_img
from nilearn.plotting import plot_stat_map, show

plotting.plot_prob_atlas(dictlearning_components_img,
                title='All DictLearning components')

print(dictlearning_components_img.shape)
print(dictlearning_components_img)

五、按切片显示激活成分

for i, cur_img in enumerate(iter_img(dictlearning_components_img)):
    plot_stat_map(cur_img, display_mode="z", title="Comp %d" % i,
                  cut_coords=1, colorbar=False)
show()