Python SimpleITK.BSplineTransformInitializer方法代碼示例

# 需要導入模塊: import SimpleITK [as 別名]
# 或者: from SimpleITK import BSplineTransformInitializer [as 別名]
def produceRandomlyDeformedImage(image, label, numcontrolpoints, stdDef):
    sitkImage=sitk.GetImageFromArray(image, isVector=False)
    sitklabel=sitk.GetImageFromArray(label, isVector=False)

    transfromDomainMeshSize=[numcontrolpoints]*sitkImage.GetDimension()

    tx = sitk.BSplineTransformInitializer(sitkImage,transfromDomainMeshSize)


    params = tx.GetParameters()

    paramsNp=np.asarray(params,dtype=float)
    paramsNp = paramsNp + np.random.randn(paramsNp.shape[0])*stdDef

    paramsNp[0:int(len(params)/3)]=0 #remove z deformations! The resolution in z is too bad

    params=tuple(paramsNp)
    tx.SetParameters(params)

    resampler = sitk.ResampleImageFilter()
    resampler.SetReferenceImage(sitkImage)
    resampler.SetInterpolator(sitk.sitkLinear)
    resampler.SetDefaultPixelValue(0)
    resampler.SetTransform(tx)

    resampler.SetDefaultPixelValue(0)
    outimgsitk = resampler.Execute(sitkImage)
    outlabsitk = resampler.Execute(sitklabel)

    outimg = sitk.GetArrayFromImage(outimgsitk)
    outimg = outimg.astype(dtype=np.float32)

    outlbl = sitk.GetArrayFromImage(outlabsitk)
    outlbl = (outlbl>0.5).astype(dtype=np.float32)

    return outimg,outlbl 

# 需要導入模塊: import SimpleITK [as 別名]
# 或者: from SimpleITK import BSplineTransformInitializer [as 別名]
def get_bspline_transform(
            image: sitk.Image,
            num_control_points: Tuple[int, int, int],
            coarse_field: np.ndarray,
            ) -> sitk.BSplineTransformInitializer:
        mesh_shape = [n - SPLINE_ORDER for n in num_control_points]
        bspline_transform = sitk.BSplineTransformInitializer(image, mesh_shape)
        parameters = coarse_field.flatten(order='F').tolist()
        bspline_transform.SetParameters(parameters)
        return bspline_transform 

# 需要導入模塊: import SimpleITK [as 別名]
# 或者: from SimpleITK import BSplineTransformInitializer [as 別名]
def gen_warp_field(shape, sigma=0.1, grid_size=3):
    '''Generate an spline warp field'''
    import SimpleITK as sitk
    # Initialize bspline transform
    args = shape+(sitk.sitkFloat32,)
    ref_image = sitk.Image(*args)
    tx = sitk.BSplineTransformInitializer(ref_image, [grid_size, grid_size])

    # Initialize shift in control points:
    # mesh size = number of control points - spline order
    p = sigma * np.random.randn(grid_size+3, grid_size+3, 2)

    # Anchor the edges of the image
    p[:, 0, :] = 0
    p[:, -1:, :] = 0
    p[0, :, :] = 0
    p[-1:, :, :] = 0

    # Set bspline transform parameters to the above shifts
    tx.SetParameters(p.flatten())

    # Compute deformation field
    displacement_filter = sitk.TransformToDisplacementFieldFilter()
    displacement_filter.SetReferenceImage(ref_image)
    displacement_field = displacement_filter.Execute(tx)

    return displacement_field 

# 需要導入模塊: import SimpleITK [as 別名]
# 或者: from SimpleITK import BSplineTransformInitializer [as 別名]
def produceRandomlyDeformedImage(image, label, numcontrolpoints, stdDef, seed=1):
        '''
        This function comes from V-net，deform a image by B-spine interpolation
        :param image: images ，numpy array
        :param label: labels，numpy array
        :param numcontrolpoints: control point，B-spine interpolation parameters，take 2 for default
        :param stdDef: Deviation，B-spine interpolation parameters，take 15 for default
        :return: Deformed images and GT in numpy array
        '''
        sitkImage = sitk.GetImageFromArray(image, isVector=False)
        sitklabel = sitk.GetImageFromArray(label, isVector=False)

        transfromDomainMeshSize = [numcontrolpoints] * sitkImage.GetDimension()

        tx = sitk.BSplineTransformInitializer(
            sitkImage, transfromDomainMeshSize)

        params = tx.GetParameters()

        paramsNp = np.asarray(params, dtype=float)
        # 設置種子值，確保多通道時兩個通道變換程度一樣
        np.random.seed(seed)
        paramsNp = paramsNp + np.random.randn(paramsNp.shape[0]) * stdDef

        # remove z deformations! The resolution in z is too bad
        paramsNp[0:int(len(params) / 3)] = 0

        params = tuple(paramsNp)
        tx.SetParameters(params)

        resampler = sitk.ResampleImageFilter()
        resampler.SetReferenceImage(sitkImage)
        resampler.SetInterpolator(sitk.sitkLinear)
        resampler.SetDefaultPixelValue(0)
        resampler.SetTransform(tx)

        resampler.SetDefaultPixelValue(0)
        outimgsitk = resampler.Execute(sitkImage)
        outlabsitk = resampler.Execute(sitklabel)

        outimg = sitk.GetArrayFromImage(outimgsitk)
        outimg = outimg.astype(dtype=np.float32)

        outlbl = sitk.GetArrayFromImage(outlabsitk)
        # outlbl = (outlbl > 0.5).astype(dtype=np.float32)

        return outimg, outlbl 

# 需要導入模塊: import SimpleITK [as 別名]
# 或者: from SimpleITK import BSplineTransformInitializer [as 別名]
def produceRandomlyDeformedImage(image, label, numcontrolpoints=2, stdDef=15):
    sitkImage=sitk.GetImageFromArray(image, isVector=False)
    sitklabel=sitk.GetImageFromArray(label, isVector=False)

    transfromDomainMeshSize=[numcontrolpoints]*sitkImage.GetDimension()

    tx = sitk.BSplineTransformInitializer(sitkImage,transfromDomainMeshSize)


    params = tx.GetParameters()

    paramsNp=np.asarray(params,dtype=float)
    paramsNp = paramsNp + np.random.randn(paramsNp.shape[0])*stdDef
    #remove z deformations! The resolution in z is too bad in case of 3D or its channels in 2D
    paramsNp[0:int(len(params)/3)]=0 #remove z deformations! The resolution in z is too bad in case of 3D or its channels

    params=tuple(paramsNp)
    tx.SetParameters(params)
    # print (sitkImage.GetSize(), sitklabel.GetSize(), transfromDomainMeshSize, paramsNp.shape)

    resampler = sitk.ResampleImageFilter()
    resampler.SetReferenceImage(sitkImage)
    resampler.SetInterpolator(sitk.sitkLinear)
    resampler.SetDefaultPixelValue(0)
    resampler.SetTransform(tx)

    outimgsitk = resampler.Execute(sitkImage)

    # For Label use nearest neighbour
    resampler.SetReferenceImage(sitklabel)
    resampler.SetInterpolator(sitk.sitkLabelGaussian)
    resampler.SetDefaultPixelValue(0)
    outlabsitk = resampler.Execute(sitklabel)

    outimg = sitk.GetArrayFromImage(outimgsitk)
    outimg = outimg.astype(dtype=np.float32)

    outlbl = sitk.GetArrayFromImage(outlabsitk)
    outlbl = (outlbl).astype(dtype=np.uint8)
    return outimg, outlbl

# ********************************Augmentation Transforms**************************#