import nibabel as nib怎么安装

你可以使用pip来安装nibabel模块，具体步骤如下：

1. 打开命令行窗口（Windows用户可以按下Win+R键，在弹出的窗口中输入cmd并回车）。

2. 输入以下命令并回车：

pip install nibabel

3. 等待安装完成即可。

如果你使用的是Anaconda环境，则可以使用conda命令来安装：

conda install -c conda-forge nibabel

希望这个回答能够帮到你！

相关问题

替换掉此代码里的import cv2模块，import os import numpy as np import nibabel as nib import imageio import cv2 def read_niifile(niifilepath): # 读取niifile文件 img = nib.load(niifilepath) # 提取niifile文件 img_fdata = img.get_fdata(dtype='float32') return img_fdata def save_fig(niifilepath, savepath, num, name): # 保存为图片 name = name.split('-')[1] filepath_seg = niifilepath + "segmentation\" + "segmentation-" + name filepath_vol = niifilepath + "volume\" + "volume-" +name savepath_seg = savepath + "segmentation\" savepath_vol = savepath + "volume\" if not os.path.exists(savepath_seg): os.makedirs(savepath_seg) if not os.path.exists(savepath_vol): os.makedirs(savepath_vol) fdata_vol = read_niifile(filepath_vol) fdata_seg = read_niifile(filepath_seg) (x, y, z) = fdata_seg.shape total = x * y for k in range(z): silce_seg = fdata_seg[:, :, k] # 三个位置表示三个不同角度的切片 if silce_seg.max() == 0: continue else: silce_seg = (silce_seg-silce_seg.min())/(silce_seg.max() - silce_seg.min())*255 silce_seg = cv2.threshold(silce_seg, 1, 255, cv2.THRESH_BINARY)[1] if (np.sum(silce_seg == 255) / total) > 0.015: silce_vol = fdata_vol[:, :, k] silce_vol = (silce_vol - silce_vol.min()) / (silce_vol.max() - silce_vol.min()) * 255 imageio.imwrite(os.path.join(savepath_seg, '{}.png'.format(num)), silce_seg) imageio.imwrite(os.path.join(savepath_vol, '{}.png'.format(num)), silce_vol) num += 1 # 将切片信息保存为png格式 return num if name == 'main': path= 'E:\dataset\LiTS17\' savepath = 'E:\dataset\LiTS17\2d\' filenames = os.listdir(path + "segmentation") num = 0 for filename in filenames: num = save_fig(path, savepath, num, filename)

将import cv2替换为from PIL import Image即可，函数中用到了cv2.threshold函数，可以使用PIL中的ImageOps.autocontrast()函数代替。修改后的代码如下：

import os 
import numpy as np 
import nibabel as nib 
import imageio 
from PIL import Image, ImageOps

def read_niifile(niifilepath):  # 读取niifile文件     
    img = nib.load(niifilepath)  # 提取niifile文件     
    img_fdata = img.get_fdata(dtype='float32')     
    return img_fdata 

def save_fig(niifilepath, savepath, num, name):  # 保存为图片     
    name = name.split('-')[1]     
    filepath_seg = niifilepath + "segmentation\\" + "segmentation-" + name     
    filepath_vol = niifilepath + "volume\\" + "volume-" +name     
    savepath_seg = savepath + "segmentation\\"     
    savepath_vol = savepath + "volume\\"       

    if not os.path.exists(savepath_seg):         
        os.makedirs(savepath_seg)     
    if not os.path.exists(savepath_vol):         
        os.makedirs(savepath_vol)       

    fdata_vol = read_niifile(filepath_vol)     
    fdata_seg = read_niifile(filepath_seg)     
    (x, y, z) = fdata_seg.shape     
    total = x * y       

    for k in range(z):         
        silce_seg = fdata_seg[:, :, k]  # 三个位置表示三个不同角度的切片         
        if silce_seg.max() == 0:             
            continue         
        else:             
            silce_seg = (silce_seg-silce_seg.min())/(silce_seg.max() - silce_seg.min())*255             
            silce_seg  = Image.fromarray(silce_seg.astype(np.uint8)) 
            silce_seg = ImageOps.autocontrast(silce_seg,1) 
            silce_seg = np.array(silce_seg)             

        if  (np.sum(silce_seg == 255) / total) > 0.015:             
            silce_vol = fdata_vol[:, :, k]             
            silce_vol = (silce_vol - silce_vol.min()) / (silce_vol.max() - silce_vol.min()) * 255               
            imageio.imwrite(os.path.join(savepath_seg, '{}.png'.format(num)), silce_seg)             
            imageio.imwrite(os.path.join(savepath_vol, '{}.png'.format(num)), silce_vol)             
            num += 1         
            # 将切片信息保存为png格式     
    return num 

if __name__ == '__main__':       
    path= 'E:\\dataset\\LiTS17\\'     
    savepath = 'E:\\dataset\\LiTS17\\2d\\'     
    filenames = os.listdir(path + "segmentation")     
    num = 0     
    for filename in filenames:         
        num = save_fig(path, savepath, num, filename)

将代码中的import cv2模块替换掉，import os import numpy as np import nibabel as nib import imageio import cv2 def read_niifile(niifilepath): # 读取niifile文件 img = nib.load(niifilepath) # 提取niifile文件 img_fdata = img.get_fdata(dtype='float32') return img_fdata def save_fig(niifilepath, savepath, num, name): # 保存为图片 name = name.split('-')[1] filepath_seg = niifilepath + "segmentation\\" + "segmentation-" + name filepath_vol = niifilepath + "volume\\" + "volume-" +name savepath_seg = savepath + "segmentation\\" savepath_vol = savepath + "volume\\" if not os.path.exists(savepath_seg): os.makedirs(savepath_seg) if not os.path.exists(savepath_vol): os.makedirs(savepath_vol) fdata_vol = read_niifile(filepath_vol) fdata_seg = read_niifile(filepath_seg) (x, y, z) = fdata_seg.shape total = x * y for k in range(z): silce_seg = fdata_seg[:, :, k] # 三个位置表示三个不同角度的切片 if silce_seg.max() == 0: continue else: silce_seg = (silce_seg-silce_seg.min())/(silce_seg.max() - silce_seg.min())*255 silce_seg = cv2.threshold(silce_seg, 1, 255, cv2.THRESH_BINARY)[1] if (np.sum(silce_seg == 255) / total) > 0.015: silce_vol = fdata_vol[:, :, k] silce_vol = (silce_vol - silce_vol.min()) / (silce_vol.max() - silce_vol.min()) * 255 imageio.imwrite(os.path.join(savepath_seg, '{}.png'.format(num)), silce_seg) imageio.imwrite(os.path.join(savepath_vol, '{}.png'.format(num)), silce_vol) num += 1 # 将切片信息保存为png格式 return num if __name__ == '__main__': path= 'E:\\dataset\\LiTS17\\' savepath = 'E:\\dataset\\LiTS17\\2d\\' filenames = os.listdir(path + "segmentation") num = 0 for filename in filenames: num = save_fig(path, savepath, num, filename)

替后的代码如下：

import os
import numpy as np
import nibabel as nib
import imageio

def read_niifile(niifilepath):  # 读取niifile文件
    img = nib.load(niifilepath)  # 提取niifile文件
    img_fdata = img.get_fdata(dtype='float32')
    return img_fdata

def save_fig(niifilepath, savepath, num, name):  # 保存为图片
    name = name.split('-')[1]
    filepath_seg = niifilepath + "segmentation\\" + "segmentation-" + name
    filepath_vol = niifilepath + "volume\\" + "volume-" +name
    savepath_seg = savepath + "segmentation\\"
    savepath_vol = savepath + "volume\\"
    
    if not os.path.exists(savepath_seg):
        os.makedirs(savepath_seg)
    if not os.path.exists(savepath_vol):
        os.makedirs(savepath_vol)
        
    fdata_vol = read_niifile(filepath_vol)
    fdata_seg = read_niifile(filepath_seg)
    (x, y, z) = fdata_seg.shape
    total = x * y
    
    for k in range(z):
        silce_seg = fdata_seg[:, :, k]  # 三个位置表示三个不同角度的切片
        if silce_seg.max() == 0:
            continue
        else:
            silce_seg = (silce_seg-silce_seg.min())/(silce_seg.max() - silce_seg.min())*255
            silce_seg  = cv2.threshold(silce_seg, 1, 255, cv2.THRESH_BINARY)[1]
            
            if  (np.sum(silce_seg == 255) / total) > 0.015:
                silce_vol = fdata_vol[:, :, k]
                silce_vol = (silce_vol - silce_vol.min()) / (silce_vol.max() - silce_vol.min()) * 255
                
                imageio.imwrite(os.path.join(savepath_seg, '{}.png'.format(num)), silce_seg)
                imageio.imwrite(os.path.join(savepath_vol, '{}.png'.format(num)), silce_vol)
                num += 1
    
    # 将切片信息保存为png格式
    return num

if __name__ == '__main__':
    path= 'E:\\dataset\\LiTS17\\'
    savepath = 'E:\\dataset\\LiTS17\\2d\\'
    filenames = os.listdir(path + "segmentation")
    num = 0
    
    for filename in filenames:
        num = save_fig(path, savepath, num, filename)