def reg(fix_path,fix_label_path,move_path,move_label_path,type='SyN'):
#读取数据，格式为： ants.core.ants_image.ANTsImage
fix_img = ants.image_read(fix_path)
fix_label_img = ants.image_read(fix_label_path)
move_img = ants.image_read(move_path)
move_label_img = ants.image_read(move_label_path)
g1 = ants.iMath_grad( fix_img )
g2 = ants.iMath_grad( move_img )
demonsMetric = ['demons', g1, g2, 1, 1]
ccMetric = ['CC', fix_img, move_img, 2, 4 ]
metrics = list( )
metrics.append( demonsMetric )
#配准
# outs = ants.registration(fix_img,move_img,type_of_transforme = 'Affine')
# outs = ants.registration( fix_img, move_img, 'ElasticSyN', multivariate_extras = metrics )
outs = ants.registration( fix_img, move_img, type)
#获取配准后的数据，并保存
reg_img = outs['warpedmovout']
save_path = './warp_image.nii.gz'
ants.image_write(reg_img,save_path)
#获取move到fix的转换矩阵；将其应用到 move_label上；插值方式选取 最近邻插值; 这个时候也对应的将label变换到 配准后的move图像上
reg_label_img = ants.apply_transforms(fix_img ,move_label_img,transformlist= outs['fwdtransforms'],interpolator = 'nearestNeighbor')
save_label_path = './warp_label.nii.gz'
ants.image_write(reg_label_img,save_label_path)
return dice_compute(reg_label_img.numpy().astype(np.int32),fix_label_img.numpy().astype(np.int32),indexes=[5])
def reg(fix_path, fix_label_path, move_path, move_label_path, type='SyN'):
#读取数据，格式为： ants.core.ants_image.ANTsImage
fix_img = ants.image_read(fix_path)
fix_label_img = ants.image_read(fix_label_path)
move_img = ants.image_read(move_path)
move_label_img = ants.image_read(move_label_path)
g1 = ants.iMath_grad(fix_img)
g2 = ants.iMath_grad(move_img)
demonsMetric = ['demons', g1, g2, 1, 1]
ccMetric = ['CC', fix_img, move_img, 2, 4]
metrics = list()
metrics.append(demonsMetric)
#配准
# outs = ants.registration(fix_img,move_img,type_of_transforme = 'Affine')
# outs = ants.registration( fix_img, move_img, 'ElasticSyN', multivariate_extras = metrics )
# outs = ants.registration( fix_img, move_img, type,verbose=True)
outs = ants.registration(fix_img,
move_img,
type,
reg_iterations=(10, 10, 20))
outs = ants.registration(fix_img,
move_img,
type,
syn_metric='mattes',
syn_sampling=5,
reg_iterations=(10, 10, 20))
# outs = ants.registration( fix_img, move_img, type,syn_metric='demons',reg_iterations=(40, 20, 10))
#获取配准后的数据，并保存
# ants.image_write(outs['warpedmovout'] ,'./warp_image.nii.gz')
if len(outs['fwdtransforms']) != 2:
return [0]
#获取move到fix的转换矩阵；将其应用到 move_label上；插值方式选取 最近邻插值; 这个时候也对应的将label变换到 配准后的move图像上
reg_label_img = ants.apply_transforms(fix_img,
move_label_img,
transformlist=outs['fwdtransforms'],
interpolator='nearestNeighbor')
# ants.image_write(reg_label_img,'./warp_label.nii.gz')
# ants.image_write(move_img,'./mv_img.nii.gz')
# ants.image_write(fix_img,'./fix_img.nii.gz')
# ants.image_write(fix_label_img,'./fix_label.nii.gz')
return dice_compute(reg_label_img.numpy().astype(np.int32),
fix_label_img.numpy().astype(np.int32),
indexes=[5])
import ants #https://blog.csdn.net/weixin_43718675/article/details/102606717#2_antspy_92 #获取数据路径 fix_path = 'mr_train_1001_image.nii.gz' move_path = 'ct_train_1013_image.nii.gz' move_label_path = 'ct_train_1013_label.nii.gz' #读取数据，格式为： ants.core.ants_image.ANTsImage fix_img = ants.image_read(fix_path) move_img = ants.image_read(move_path) move_label_img = ants.image_read(move_label_path) g1 = ants.iMath_grad( fix_img ) g2 = ants.iMath_grad( move_img ) demonsMetric = ['demons', g1, g2, 1, 1] ccMetric = ['CC', fix_img, move_img, 2, 4 ] metrics = list( ) metrics.append( demonsMetric ) #配准 # outs = ants.registration(fix_img,move_img,type_of_transforme = 'Affine') outs = ants.registration( fix_img, move_img, 'ElasticSyN', multivariate_extras = metrics ) # outs = ants.registration( fix_img, move_img, 'SyNCC') #获取配准后的数据，并保存 reg_img = outs['warpedmovout'] save_path = './warp_image.nii.gz' ants.image_write(reg_img,save_path)
# -*- coding:utf-8 -*-
import ants
img1 = ants.image_read(
'../mmwhs/CT_test/205_5/ct-image_crop_man_reg_resize/ct_train_1013_image.nii.gz'
)
img2 = ants.image_read(
'../mmwhs/CT_test/205_5/ct-image_crop_man_reg_resize/ct_train_1014_image.nii.gz'
)
print(img2)
print(img1)
g1 = ants.iMath_grad(img1)
g2 = ants.iMath_grad(img2)
reg1 = ants.registration(img1, img2, 'SyNOnly')
demonsMetric = ['demons', g1, g2, 1, 1]
ccMetric = ['CC', img1, img2, 2, 4]
metrics = list()
metrics.append(demonsMetric)
print("start to registration...........")
reg2 = ants.registration(img1, img2, 'SyNOnly', multivariate_extras=metrics)
metrics.append(ccMetric)
reg3 = ants.registration(img1, img2, 'SyNOnly', multivariate_extras=metrics)
print(ants.image_mutual_information(img1, img2))
print(ants.image_mutual_information(img1, reg1['warpedmovout']))
print(ants.image_mutual_information(img1, reg2['warpedmovout']))
print(ants.image_mutual_information(img1, reg3['warpedmovout']))