本文档旨在指导用户如何将自定义的fMRI NIfTI文件加载到现有的Python代码中，该代码使用了monai库进行图像处理。我们将重点介绍如何利用nilearn库加载NIfTI文件，并将其集成到现有的数据处理流程中，以便进行后续的分析和处理。同时，我们也简单提及了多进程处理的建议，以便加速数据处理流程。
nilearn 是一个专门用于神经影像数据分析的 Python 库，它提供了方便的函数来加载和处理 NIfTI 文件。相比于从头开始解析文件，使用 nilearn 可以大大简化代码并提高效率。
首先，确保你已经安装了 nilearn 库。如果没有安装，可以使用 pip 进行安装：
pip install nilearn
安装完成后，就可以使用 nilearn.image.load_img 函数加载 NIfTI 文件了。
from nilearn.image import load_img
# 指定 NIfTI 文件的路径
nifti_file_path = "F:\New folder\cn_processed data\Sub1\S1.nii"
# 加载 NIfTI 文件
try:
nifti_image = load_img(nifti_file_path)
print(f"Successfully loaded NIfTI image from: {nifti_file_path}")
except FileNotFoundError:
print(f"Error: NIfTI file not found at: {nifti_file_path}")
exit()
except Exception as e:
print(f"An error occurred while loading the NIfTI image: {e}")
exit()
# 获取图像数据，返回一个 NumPy 数组
data = nifti_image.get_fdata()
# 打印数据的形状，以确认加载成功
print("Data shape:", data.shape)代码解释：
现在，我们需要将使用 nilearn 加载 NIfTI 文件的代码集成到你提供的原始代码中。修改 read_data 函数，使用 nilearn 加载数据，并移除 monai 的 LoadImage：
from nilearn.image import load_img
import torch
import os
import time
from multiprocessing import Process, Queue
import numpy as np # 导入 NumPy
def read_data(filename, load_root, save_root, subj_name, count, queue=None, scaling_method=None, fill_zeroback=False):
print("processing: " + filename, flush=True)
path = os.path.join(load_root, filename)
try:
# 使用 nilearn 加载 NIfTI 文件
nifti_image = load_img(path)
data = nifti_image.get_fdata()
except FileNotFoundError:
print(f"Error: NIfTI file not found at: {path}")
return None
except Exception as e:
print(f"An error occurred while loading the NIfTI image: {e}")
return None
#change this line according to your file names
save_dir = os.path.join(save_root,subj_name)
isExist = os.path.exists(save_dir)
if not isExist:
os.makedirs(save_dir)
# change this line according to your dataset
data = data[:, 14:-7, :, :]
# width, height, depth, time
# Inspect the fMRI file first using your visualization tool.
# Limit the ranges of width, height, and depth to be under 96. Crop the background, not the brain regions.
# Each dimension of fMRI registered to MNI space (2mm) is expected to be around 100.
# You can do this when you load each volume at the Dataset class, including padding backgrounds to fill dimensions under 96.
background = data==0
if scaling_method == 'z-norm':
global_mean = data[~background].mean()
global_std = data[~background].std()
data_temp = (data - global_mean) / global_std
elif scaling_method == 'minmax':
data_temp = (data - data[~background].min()) / (data[~background].max() - data[~background].min())
data_global = torch.empty(data.shape)
data_global[background] = data_temp[~background].min() if not fill_zeroback else 0
# data_temp[~background].min() is expected to be 0 for scaling_method == 'minmax', and minimum z-value for scaling_method == 'z-norm'
data_global[~background] = data_temp[~background]
# save volumes one-by-one in fp16 format.
data_global = torch.tensor(data_global) #Convert numpy array to tensor
data_global = data_global.type(torch.float16)
data_global_split = torch.split(data_global, 1, 3)
for i, TR in enumerate(data_global_split):
torch.save(TR.clone(), os.path.join(save_dir,"frame_"+str(i)+".pt"))
def main():
# change two lines below according to your dataset
dataset_name = 'ABCD'
load_root = 'F:\New folder\cn_processed data' # This folder should have fMRI files in nifti format with subject names. Ex) sub-01.nii.gz
save_root = f'/storage/7.{dataset_name}_MNI_to_TRs_minmax'
scaling_method = 'z-norm' # choose either 'z-norm'(default) or 'minmax'.
# make result folders
filenames = os.listdir(load_root)
os.makedirs(os.path.join(save_root,'img'), exist_ok = True)
os.makedirs(os.path.join(save_root,'metadata'), exist_ok = True) # locate your metadata file at this folder
save_root = os.path.join(save_root,'img')
finished_samples = os.listdir(save_root)
queue = Queue()
count = 0
for filename in sorted(filenames):
# Assuming filename is like "Sub1.nii"
subj_name = filename[:-4] # extract subject name from nifti file. [:-4] rules out '.nii'
# we recommend you use subj_name that aligns with the subject key in a metadata file.
expected_seq_length = 1000 # Specify the expected sequence length of fMRI for the case your preprocessing stopped unexpectedly and you try to resume the preprocessing.
# change the line below according to your folder structure
if (subj_name not in finished_samples) or (len(os.listdir(os.path.join(save_root,subj_name))) < expected_seq_length): # preprocess if the subject folder does not exist, or the number of pth files is lower than expected sequence length.
try:
count+=1
p = Process(target=read_data, args=(filename,load_root,save_root,subj_name,count,queue,scaling_method))
p.start()
if count % 32 == 0: # requires more than 32 cpu cores for parallel processing
p.join()
except Exception:
print('encountered problem with'+filename)
print(Exception)
if __name__=='__main__':
start_time = time.time()
main()
end_time = time.time()
print('
Total', round((end_time - start_time) / 60), 'minutes elapsed.')关键修改：
注意事项：
joblib 库提供了一种更简洁的方式来进行多进程处理，它可以更方便地并行处理多个任务。
from joblib import Parallel, delayed
import os
from nilearn.image import load_img
import numpy as np
import torch
def read_data(filename, load_root, save_root, subj_name, scaling_method=None, fill_zeroback=False):
path = os.path.join(load_root, filename)
try:
nifti_image = load_img(path)
data = nifti_image.get_fdata()
except FileNotFoundError:
print(f"Error: NIfTI file not found at: {path}")
return None
except Exception as e:
print(f"An error occurred while loading the NIfTI image: {e}")
return None
save_dir = os.path.join(save_root, subj_name)
os.makedirs(save_dir, exist_ok=True)
data = data[:, 14:-7, :, :]
background = data == 0
if scaling_method == 'z-norm':
global_mean = data[~background].mean()
global_std = data[~background].std()
data_temp = (data - global_mean) / global_std
elif scaling_method == 'minmax':
data_temp = (data - data[~background].min()) / (data[~background].max() - data[~background].min())
data_global = torch.empty(data.shape)
data_global[background] = data_temp[~background].min() if not fill_zeroback else 0
data_global[~background] = data_temp[~background]
data_global = torch.tensor(data_global) #Convert numpy array to tensor
data_global = data_global.type(torch.float16)
data_global_split = torch.split(data_global, 1, 3)
for i, TR in enumerate(data_global_split):
torch.save(TR.clone(), os.path.join(save_dir, "frame_" + str(i) + ".pt"))
def main():
dataset_name = 'ABCD'
load_root = 'F:\New folder\cn_processed data'
save_root = f'/storage/7.{dataset_name}_MNI_to_TRs_minmax'
scaling_method = 'z-norm'
filenames = os.listdir(load_root)
os.makedirs(os.path.join(save_root, 'img'), exist_ok=True)
os.makedirs(os.path.join(save_root, 'metadata'), exist_ok=True)
save_root = os.path.join(save_root, 'img')
# Use joblib for parallel processing
Parallel(n_jobs=os.cpu_count())( # Use all available CPU cores
delayed(read_data)(
filename,
load_root,
save_root,
filename[:-4], # Extract subj_name
scaling_method
) for filename in sorted(filenames)
)
if __name__ == '__main__':
start_time = time.time()
main()
end_time = time.time()
print('
Total', round((end_time - start_time) / 60), 'minutes elapsed.')代码解释：
总结：
通过使用 nilearn 库，可以方便地加载 NIfTI 文件，并将其集成到现有的代码中。同时，利用 joblib 库可以更有效地进行多进程处理，从而加速数据处理流程。请根据你的实际情况调整代码，并确保数据路径和文件名正确。
以上就是加载自定义fMRI NIfTI文件到现有代码的教程的详细内容，更多请关注php中文网其它相关文章！
每个人都需要一台速度更快、更稳定的 PC。随着时间的推移，垃圾文件、旧注册表数据和不必要的后台进程会占用资源并降低性能。幸运的是，许多工具可以让 Windows 保持平稳运行。
Copyright 2014-2025 https://www.php.cn/ All Rights Reserved | php.cn | 湘ICP备2023035733号
408
收藏
