镜像自地址
https://github.com/xming521/CTAI.git
已同步 2025-12-06 06:36:49 +00:00
upload train code
这个提交包含在：
xming521
0
CTAI_model/cv/__init__.py
普通文件
0
CTAI_model/cv/__init__.py
普通文件
114
CTAI_model/cv/get_ROI-all.py
普通文件
114
CTAI_model/cv/get_ROI-all.py
普通文件
@@ -0,0 +1,114 @@
|
||||
import SimpleITK as sitk
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
from data_set.make import get_train_files
|
||||
|
||||
# 跑train不加第二个train
|
||||
train_data_path = '../data/train/train/'
|
||||
|
||||
|
||||
# train_data_path = '../data/CT/'
|
||||
|
||||
|
||||
def get_roi(path):
|
||||
global w
|
||||
file_name = path.split('/')[-3] + '-' + path.split('/')[-1].replace('.dcm', '')
|
||||
image = sitk.ReadImage(path)
|
||||
image = sitk.GetArrayFromImage(image)[0, :, :]
|
||||
image[image < -300] = 0
|
||||
image[image > 300] = 0
|
||||
img_o = image.copy()
|
||||
ROI = np.zeros(image.shape, np.uint8)
|
||||
slices = [image]
|
||||
img = slices[int(len(slices) / 2)].copy()
|
||||
img = np.uint8(img)
|
||||
# kernel = np.ones((3, 3), np.uint8)
|
||||
# kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (1, 1))
|
||||
# img = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)
|
||||
# img = cv2.dilate(img, kernel, iterations=1)
|
||||
|
||||
kernel = np.ones((4, 4), np.uint8)
|
||||
img = cv2.dilate(img, kernel, iterations=1)
|
||||
|
||||
# 对图像进行阈值分割
|
||||
ret, img = cv2.threshold(img, 150, 255, cv2.THRESH_BINARY_INV)
|
||||
# 提取分割结果中的轮廓，并填充孔洞
|
||||
im2, contours, x = cv2.findContours(img.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
|
||||
area = []
|
||||
for c in contours:
|
||||
area.append(cv2.contourArea(c))
|
||||
cparea = area.copy()
|
||||
|
||||
area.sort(reverse=True)
|
||||
ROI_tmp = np.zeros(img.shape, np.uint8)
|
||||
# for i in range(1, 10):
|
||||
# # 选择最有可能的一个区域
|
||||
# ROI_tmp = np.zeros(img.shape, np.uint8)
|
||||
# max_idx = cparea.index(area[i])
|
||||
#
|
||||
# # 强度匹配 因为直接映射到dcm上不用转uint8
|
||||
# cv2.drawContours(ROI_tmp, contours, max_idx, (255, 255, 255), -1)
|
||||
#
|
||||
# index = np.nonzero(ROI_tmp)
|
||||
# mean = np.mean(img_o[index])
|
||||
# std = np.std(img_o[index])
|
||||
# # if mean > 90 or mean < 10 or std > 70 or std < 15:
|
||||
# # continue
|
||||
#
|
||||
# s = pd.Series(img_o[index])
|
||||
# piandu = s.skew()
|
||||
# fengdu = s.kurt()
|
||||
# # if piandu > 1 or fengdu < -5 or fengdu > 20:
|
||||
# # continue
|
||||
#
|
||||
# # 生成矩
|
||||
# M = cv2.moments(contours[max_idx])
|
||||
#
|
||||
# # 面积周长
|
||||
# perimeter = cv2.arcLength(contours[max_idx], True)
|
||||
# # if area[i] > 2000 or area[i] < 500 or perimeter > 250 or perimeter < 80:
|
||||
# # continue
|
||||
# if area[i] > 2000 or perimeter > 400 :
|
||||
# continue
|
||||
#
|
||||
# # if area[i] > 4000 or area[i] < 500 or perimeter > 400 :
|
||||
# # continue
|
||||
# #
|
||||
# # 椭圆拟合
|
||||
# # try:
|
||||
# # (x, y), (MA, ma), angle = cv2.fitEllipse(contours[max_idx])
|
||||
# # if ma - MA > 25:
|
||||
# # continue
|
||||
# # # ellipse.append(ma-MA)
|
||||
# # except:
|
||||
# # continue
|
||||
#
|
||||
#
|
||||
# # img_o[]
|
||||
#
|
||||
# # 加矩形框
|
||||
# x, y, w, h = cv2.boundingRect(contours[max_idx])
|
||||
# ROI = cv2.rectangle(ROI, (x, y), (x + w + 10, y + h + 10), (255, 255, 255), -1)
|
||||
#
|
||||
# # 填充
|
||||
# # cv2.drawContours(ROI, contours, max_idx, (255, 255, 255), -1)
|
||||
|
||||
ROI_tmp[270:430, 200:300] = image[270:430, 200:300]
|
||||
|
||||
cv2.imshow("Image", image)
|
||||
cv2.imshow("Image", ROI_tmp)
|
||||
cv2.waitKey(0)
|
||||
print(f"{train_data_path}ROI-{file_name}.png")
|
||||
# cv2.imwrite(f"{train_data_path}ROI-{file_name}.png", ROI, [int(cv2.IMWRITE_PNG_COMPRESSION), 0])
|
||||
|
||||
|
||||
def main():
|
||||
global w
|
||||
dcm_files, _ = get_train_files(train_data_path, file_type='dcm', all=False)
|
||||
for i in dcm_files:
|
||||
get_roi(i)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
68
CTAI_model/cv/get_ROI-one.py
普通文件
68
CTAI_model/cv/get_ROI-one.py
普通文件
@@ -0,0 +1,68 @@
|
||||
import SimpleITK as sitk
|
||||
import cv2
|
||||
import numpy as np
|
||||
|
||||
image = sitk.ReadImage('../data/train/train/10087.dcm')
|
||||
image = sitk.GetArrayFromImage(image)[0, :, :]
|
||||
|
||||
image[image < -300] = 0
|
||||
image[image > 300] = 0
|
||||
|
||||
ROI = np.zeros(image.shape, np.uint8)
|
||||
# 获取图像中的像素数据
|
||||
slices = [image]
|
||||
|
||||
# 复制Dicom图像中的像素数据
|
||||
img = slices[int(len(slices) / 2)].copy()
|
||||
img = np.uint8(img)
|
||||
|
||||
kernel = np.ones((4, 4), np.uint8)
|
||||
img = cv2.dilate(img, kernel, iterations=1)
|
||||
|
||||
# 对图像进行阈值分割
|
||||
ret, img = cv2.threshold(img, 150, 255, cv2.THRESH_BINARY_INV)
|
||||
|
||||
xxx = img
|
||||
# 提取分割结果中的轮廓，并填充孔洞
|
||||
im2, contours, x = cv2.findContours(img.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
|
||||
# 需要反色处理一下 现在找的是白色的 应该是黑色的
|
||||
|
||||
# mask = np.zeros(img.shape, np.uint8)
|
||||
# for contour in contours:
|
||||
# cv2.fillPoly(mask, [contour], 255)
|
||||
# img[(mask > 0)] = 255
|
||||
|
||||
|
||||
area = []
|
||||
for c in contours:
|
||||
area.append(cv2.contourArea(c))
|
||||
cparea = area.copy()
|
||||
|
||||
area.sort(reverse=True)
|
||||
|
||||
for i in range(3, 8):
|
||||
max_idx = cparea.index(area[i])
|
||||
perimeter = cv2.arcLength(contours[max_idx], True)
|
||||
if area[i] > 5000 or perimeter > 500:
|
||||
continue
|
||||
print('周长', perimeter)
|
||||
|
||||
cv2.drawContours(ROI, contours, max_idx, (220, 20, 60), -1)
|
||||
|
||||
# max_idx = cparea.index(area[3])
|
||||
# cv2.drawContours(ROI, contours, max_idx, (220, 20, 60), -1)
|
||||
# cv2.drawContours(ROI, contours, max_idx, (220, 20, 60), -1)
|
||||
|
||||
|
||||
# 对分割结果进行形态学的开操作
|
||||
# kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (2, 2))
|
||||
# img = cv2.morphologyEx(img, cv2.MORPH_OPEN, kernel)
|
||||
|
||||
# plt.figure(figsize=(10, 7))
|
||||
# plt.imshow(img, 'gray')
|
||||
# plt.title('Mask')
|
||||
# plt.show()
|
||||
|
||||
|
||||
cv2.imshow("Image", ROI)
|
||||
cv2.waitKey(0)
|
||||
232
CTAI_model/cv/get_all_feature.py
普通文件
232
CTAI_model/cv/get_all_feature.py
普通文件
@@ -0,0 +1,232 @@
|
||||
import sys
|
||||
|
||||
sys.path.append("..")
|
||||
from data_set.make import get_person_files
|
||||
import cv2
|
||||
import numpy as np
|
||||
import SimpleITK as sitk
|
||||
import pandas as pd
|
||||
from numba import jit
|
||||
import inspect
|
||||
import csv
|
||||
|
||||
np.set_printoptions(suppress=True) # 输出时禁止科学表示法，直接输出小数值
|
||||
|
||||
mask_data_path = '../data/all/d2/'
|
||||
|
||||
# ID为第一个字段名会会让xlsx报错
|
||||
# dict用表头
|
||||
column_all = ['ID', '性别', '年龄', '阴性/阳性', 'area', 'perimeter', 'focus_x', 'focus_y', 'ellipse', 'mean', 'std', 'piandu',
|
||||
'fengdu',
|
||||
'small_grads_dominance',
|
||||
'big_grads_dominance', 'gray_asymmetry', 'grads_asymmetry', 'energy', 'gray_mean', 'grads_mean',
|
||||
'gray_variance', 'grads_variance', 'corelation', 'gray_entropy', 'grads_entropy', 'entropy', 'inertia',
|
||||
'differ_moment']
|
||||
# 实际表头
|
||||
column_all_c = ['ID', '性别', '年龄', '阴性/阳性', '面积', '周长', '重心x', '重心y', '近圆度', '灰度均值', '灰度方差', '灰度偏度',
|
||||
'灰度峰态', '小梯度优势', '大梯度优势', '灰度分布不均匀性', '梯度分布不均匀性', '能量', '灰度平均', '梯度平均',
|
||||
'灰度均方差', '梯度均方差', '相关', '灰度熵', '梯度熵', '混合熵', '惯性', '逆差矩']
|
||||
|
||||
features_list = ['area', 'perimeter', 'focus_x', 'focus_y', 'ellipse', 'mean', 'std', 'piandu', 'fengdu',
|
||||
'small_grads_dominance',
|
||||
'big_grads_dominance', 'gray_asymmetry', 'grads_asymmetry', 'energy', 'gray_mean', 'grads_mean',
|
||||
'gray_variance', 'grads_variance', 'corelation', 'gray_entropy', 'grads_entropy', 'entropy', 'inertia',
|
||||
'differ_moment']
|
||||
|
||||
|
||||
# 最后俩偏度 峰度
|
||||
|
||||
|
||||
# 获取变量的名
|
||||
def get_variable_name(variable):
|
||||
callers_local_vars = inspect.currentframe().f_back.f_locals.items()
|
||||
return [var_name for var_name, var_val in callers_local_vars if var_val is variable]
|
||||
|
||||
|
||||
def glcm(img_gray, ngrad=16, ngray=16):
|
||||
'''Gray Level-Gradient Co-occurrence Matrix,取归一化后的灰度值、梯度值分别为16、16'''
|
||||
# 利用sobel算子分别计算x-y方向上的梯度值
|
||||
gsx = cv2.Sobel(img_gray, cv2.CV_64F, 1, 0, ksize=3)
|
||||
gsy = cv2.Sobel(img_gray, cv2.CV_64F, 0, 1, ksize=3)
|
||||
height, width = img_gray.shape
|
||||
grad = (gsx ** 2 + gsy ** 2) ** 0.5 # 计算梯度值
|
||||
grad = np.asarray(1.0 * grad * (ngrad - 1) / grad.max(), dtype=np.int16)
|
||||
gray = np.asarray(1.0 * img_gray * (ngray - 1) / img_gray.max(), dtype=np.int16) # 0-255变换为0-15
|
||||
gray_grad = np.zeros([ngray, ngrad]) # 灰度梯度共生矩阵
|
||||
for i in range(height):
|
||||
for j in range(width):
|
||||
gray_value = gray[i][j]
|
||||
grad_value = grad[i][j]
|
||||
gray_grad[gray_value][grad_value] += 1
|
||||
gray_grad = 1.0 * gray_grad / (height * width) # 归一化灰度梯度矩阵，减少计算量
|
||||
get_glcm_features(gray_grad)
|
||||
|
||||
|
||||
@jit
|
||||
def get_gray_feature():
|
||||
# 灰度特征提取算法
|
||||
hist = cv2.calcHist([image_ROI_uint8[index]], [0], None, [256], [0, 256])
|
||||
|
||||
c_features['mean'].append(np.mean(image_ROI[index]))
|
||||
c_features['std'].append(np.std(image_ROI[index]))
|
||||
|
||||
s = pd.Series(image_ROI[index])
|
||||
c_features['piandu'].append(s.skew())
|
||||
c_features['fengdu'].append(s.kurt())
|
||||
|
||||
|
||||
def get_glcm_features(mat):
|
||||
'''根据灰度梯度共生矩阵计算纹理特征量，包括小梯度优势，大梯度优势，灰度分布不均匀性，梯度分布不均匀性，能量，灰度平均，梯度平均，
|
||||
灰度方差，梯度方差，相关，灰度熵，梯度熵，混合熵，惯性，逆差矩'''
|
||||
sum_mat = mat.sum()
|
||||
small_grads_dominance = big_grads_dominance = gray_asymmetry = grads_asymmetry = energy = gray_mean = grads_mean = 0
|
||||
gray_variance = grads_variance = corelation = gray_entropy = grads_entropy = entropy = inertia = differ_moment = 0
|
||||
for i in range(mat.shape[0]):
|
||||
gray_variance_temp = 0
|
||||
for j in range(mat.shape[1]):
|
||||
small_grads_dominance += mat[i][j] / ((j + 1) ** 2)
|
||||
big_grads_dominance += mat[i][j] * j ** 2
|
||||
energy += mat[i][j] ** 2
|
||||
if mat[i].sum() != 0:
|
||||
gray_entropy -= mat[i][j] * np.log(mat[i].sum())
|
||||
if mat[:, j].sum() != 0:
|
||||
grads_entropy -= mat[i][j] * np.log(mat[:, j].sum())
|
||||
if mat[i][j] != 0:
|
||||
entropy -= mat[i][j] * np.log(mat[i][j])
|
||||
inertia += (i - j) ** 2 * np.log(mat[i][j])
|
||||
differ_moment += mat[i][j] / (1 + (i - j) ** 2)
|
||||
gray_variance_temp += mat[i][j] ** 0.5
|
||||
|
||||
gray_asymmetry += mat[i].sum() ** 2
|
||||
gray_mean += i * mat[i].sum() ** 2
|
||||
gray_variance += (i - gray_mean) ** 2 * gray_variance_temp
|
||||
for j in range(mat.shape[1]):
|
||||
grads_variance_temp = 0
|
||||
for i in range(mat.shape[0]):
|
||||
grads_variance_temp += mat[i][j] ** 0.5
|
||||
grads_asymmetry += mat[:, j].sum() ** 2
|
||||
grads_mean += j * mat[:, j].sum() ** 2
|
||||
grads_variance += (j - grads_mean) ** 2 * grads_variance_temp
|
||||
small_grads_dominance /= sum_mat
|
||||
big_grads_dominance /= sum_mat
|
||||
gray_asymmetry /= sum_mat
|
||||
grads_asymmetry /= sum_mat
|
||||
gray_variance = gray_variance ** 0.5
|
||||
grads_variance = grads_variance ** 0.5
|
||||
for i in range(mat.shape[0]):
|
||||
for j in range(mat.shape[1]):
|
||||
corelation += (i - gray_mean) * (j - grads_mean) * mat[i][j]
|
||||
glgcm_features = [small_grads_dominance, big_grads_dominance, gray_asymmetry, grads_asymmetry, energy, gray_mean,
|
||||
grads_mean,
|
||||
gray_variance, grads_variance, corelation, gray_entropy, grads_entropy, entropy, inertia,
|
||||
differ_moment]
|
||||
for i in range(len(glgcm_features)):
|
||||
t = get_variable_name(glgcm_features[i])[0]
|
||||
c_features[t].append(np.round(glgcm_features[i], 4))
|
||||
|
||||
|
||||
def get_geometry_feature():
|
||||
# 形态特征 分割mask获得一些特征
|
||||
im2, contours, x = cv2.findContours(mask_array.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
|
||||
tarea = []
|
||||
tperimeter = []
|
||||
for c in contours:
|
||||
# 生成矩
|
||||
try:
|
||||
M = cv2.moments(c)
|
||||
cx = int(M['m10'] / M['m00'])
|
||||
cy = int(M['m01'] / M['m00'])
|
||||
c_features['focus_x'].append(cx)
|
||||
c_features['focus_y'].append(cy)
|
||||
except:
|
||||
print('error')
|
||||
|
||||
# 椭圆拟合
|
||||
try:
|
||||
(x, y), (MA, ma), angle = cv2.fitEllipse(c)
|
||||
c_features['ellipse'].append((ma - MA))
|
||||
except:
|
||||
continue
|
||||
# 面积周长
|
||||
tarea.append(cv2.contourArea(c))
|
||||
tperimeter.append(cv2.arcLength(c, True))
|
||||
|
||||
# 将mask里的最大值追加 有黑洞
|
||||
try:
|
||||
c_features['area'].append(max(tarea))
|
||||
c_features['perimeter'].append(round(max(tperimeter), 4))
|
||||
except:
|
||||
print('area error')
|
||||
|
||||
|
||||
# 提取肿瘤特征
|
||||
def get_feature(image, mask):
|
||||
global w
|
||||
global image_ROI_uint8, index, image_ROI_mini, image_ROI, mask_array
|
||||
|
||||
mask_array = cv2.imread(mask, 0)
|
||||
image = sitk.ReadImage(image)
|
||||
image_arrary = sitk.GetArrayFromImage(image)[0, :, :]
|
||||
# 映射到CT获得特征
|
||||
image_ROI = np.zeros(shape=image_arrary.shape)
|
||||
index = np.nonzero(mask_array)
|
||||
if not index[0].any():
|
||||
# c_features['no'] = True
|
||||
return None
|
||||
image_ROI[index] = image_arrary[index]
|
||||
image_ROI_uint8 = np.uint8(image_ROI)
|
||||
# 获得只有肿瘤的图片
|
||||
x, y, w, h = cv2.boundingRect(mask_array)
|
||||
image_ROI_mini = np.uint8(image_arrary[y:y + h, x:x + w])
|
||||
w = image_ROI_mini
|
||||
|
||||
get_geometry_feature()
|
||||
|
||||
get_gray_feature()
|
||||
|
||||
glcm(image_ROI_mini, 15, 15)
|
||||
|
||||
return c_features
|
||||
|
||||
|
||||
def main():
|
||||
global w
|
||||
# 注意下面文件路径 格式
|
||||
csv_file = open('../data/all/res.csv', 'w', encoding='gbk', newline='')
|
||||
writer1 = csv.writer(csv_file)
|
||||
writer1.writerow(column_all_c)
|
||||
writer2 = csv.DictWriter(csv_file, column_all)
|
||||
|
||||
df = pd.read_csv('../data/all/临床数据.csv', encoding='gbk')
|
||||
|
||||
image = get_person_files('../data/all/d2/')
|
||||
mask = get_person_files('../data/out/')
|
||||
# image1 mask2
|
||||
|
||||
for i in range(len(image)):
|
||||
person_id = image[i][0]
|
||||
global c_features
|
||||
c_features = {}
|
||||
for k in features_list:
|
||||
c_features[k] = []
|
||||
if len(image[i][1]) != len(mask[i][2]):
|
||||
print('文件有错')
|
||||
for j in range(len(image[i][1])):
|
||||
get_feature(image[i][1][j], mask[i][2][j])
|
||||
|
||||
for j in c_features:
|
||||
if j == 'id':
|
||||
continue
|
||||
c_features[j] = np.round(np.mean(c_features[j]), 4)
|
||||
|
||||
person_info = df[df['ID'].isin([person_id])].to_dict('index').values()
|
||||
person_info = list(person_info)[0]
|
||||
person_info.update(c_features)
|
||||
writer2.writerow(person_info)
|
||||
print(person_info)
|
||||
|
||||
csv_file.close()
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
main()
|
||||
在新工单中引用
屏蔽一个用户