WSI Image Segmentation

0. Introduction:

(Whole Slide Image, WSI) images are very large and cumbersome to process. Most pathological slice images in deep learning are at 100,000 x 100,000 resolution, which cannot be read with ordinary image processing libraries. Openslide provides a Very good interface, here is a python library (OpenSlide) that can be used to process large pathological slide images.

1. Openslide installation:

pip install openslide-python  #终端输入

OpenSlide official website download 

Configuration path: Open the lowlevel.py file under Lib\site-packages, and paste the bin file path in the decompressed openslide-win64-20221217 file to the following

At this point, enter the python console, enter import openslide, and there is no abnormal prompt, indicating that opensldie is installed!

If this method does not work, you need to import the relevant path before importing openslide! (simple and rude)

The path is the bin file path in the openslide-win64-20221217 file 

import os
os.add_dll_directory('D:\\CNN\\openslide-win64-20221217\\openslide-win64-20221217\\bin')
import openslide

2. Cut the picture

# 注意这里只能切割单张图片，不支持文件夹
import openslide
import numpy as np
import imageio  #用于保存图片

slide = openslide.OpenSlide("D:\Visio_relatation\\111\\") #原始图片文件夹
dst_path = 'D:\Visio_relatation\\222\\' #保存图片文件夹

[m, n] = slide.dimensions   # 得出高倍下的（宽，高）
print(m, n)
N = 1024
ml = N * m//N
nl = N * n//N

for i in range(0, ml, N):   # 这里由于只是想实现剪切功能，暂时忽略边缘不足N*N的部分
    for j in range(0, nl, N):
        im = np.array(slide.read_region((i, j), 0, (N, N)))
                imageio.imwrite(dst_path + '1' + 'a' + str(i) + 'a' + str(j) + '.png', im)  # patch命名为‘x-y’

slide.close()   # 关闭文件

# 这里可以循环遍历文件夹中的所有图片
import os
import openslide
import numpy as np
import imageio  # 用于保存图片

dst_path = 'D:\Visio_relatation\\222\\' #切割后保存地址
img_floder = r'D:\Visio_relatation\\111' #原tif图片文件夹
img_list = os.listdir(img_floder)
print(img_list)

for img_name in img_list:
    name = img_name[:-4]
    slide = openslide.OpenSlide(img_floder + "\\" + img_name)

    [m, n] = slide.dimensions   # 得出高倍级别下的（宽，高）
    print(m, n)
    N = 1024
    ml = N * m//N
    nl = N * n//N

    for i in range(0, ml, N):   # 这里由于只是想实现剪切功能，暂时忽略边缘不足N*N的部分
        for j in range(0, nl, N):
            im = np.array(slide.read_region((i, j), 0, (N, N)))
            imageio.imwrite(dst_path + name + '_' + str(i) + '_' + str(j) + '.png', im)  # patch命名为‘x-y’

    slide.close()   # 关闭文件

Note: The image cut out by Openslide is 4-channel (RGBA), if you want to get a 3-channel (RGB) image, please use the following method~~

import os
import numpy as np
import cv2 as cv
import PIL.Image as Image
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
Image.MAX_IMAGE_PIXELS = None


clip_img_path = 'D:/CNN/GHHE/zhimi/'  # 切割后保存地址
img_floder = r'D:/CNN/GHHE/zhimi_tif/large'  # 原tif图片文件夹
img_list = os.listdir(img_floder)
print(img_list)


def pixel_equal(image, x, y):
    # 取图片像素点
    piex = image.load()[x, y]
    threshold1 = 250
    threshold2 = 30
    # 比较每个像素点的RGB值是否大于阈值
    if piex[0] > threshold1 and piex[1] > threshold1 and piex[2] > threshold1:
        return 1
    elif piex[0] < threshold2 and piex[1] < threshold2 and piex[2] < threshold2:
        return 2
    else:
        return 3


img_size = 1024
l = 0
right_num1 = 0  # 记录白色像素点个数
right_num2 = 0  # 记录黑色像素点个数
for img_name in img_list:
    name = img_name[:-4]
    # print(img_floder + '/' + img_name)
    img0 = Image.open(img_floder + '/' + img_name) #PIL的形式可以显示size
    img = np.array(Image.open(img_floder + '/' + img_name)) #array的形式才能显示shape
    print(img0.size)

    w, h = img0.size[0], img0.size[1]
    # print(h, w)

    for i in range(0, h, img_size):
        for j in range(0, w, img_size):
            end_i, end_j = i + img_size, j + img_size
            cropped = img[i:end_i, j:end_j]
            # img_orig = Image.fromarray(cv.cvtColor(cropped, cv.COLOR_BGR2RGB)) # bgr 转 rgb
            img_orig = Image.fromarray(cropped)  # 实现array到image的转换
            to_image = Image.new('RGB', (img_size, img_size))  # 创建1024大小图片

            to_image.paste(img_orig, (0, 0))
            # print(to_image.size)
            # to_image.save(clip_img_path + name + '_' + str(m) + '_' + str(n) + ".jpg")


            for m in range(0, to_image.size[0]): 
                for n in range(0, to_image.size[1]):
                    if pixel_equal(to_image, m, n) == 1:
                        right_num1 += 1
                    elif pixel_equal(to_image, m, n) == 2:
                        right_num2 += 1
                    else:
                        continue
            # print(right_num1, right_num2)
            
            # 剔除不符合要求的图片
            if right_num1 / (1024 * 1024) < 0.4 and right_num2 / (1024 * 1024) < 0.05:
                to_image.save(clip_img_path + name + '_' + str(l) + ".jpg")
                right_num1 = 0
                right_num2 = 0
            else:
                right_num1 = 0
                right_num2 = 0
            l += 1
    l = 0