Main Content

Preprocessing and Augmentation

3-D registration and denoising, random intensity augmentation

Image preprocessing and image augmentation prepare data for advanced medical image analysis workflows. Use image preprocessing to reduce image acquisition artifacts and format data for the target workflow. For example, you can remove noise, normalize intensity values, resize image voxels, or align images using registration. Use image augmentation to increase the amount and variability of training data for deep learning workflows. For example, you can randomly adjust image contrast or apply random rotations or scaling to simulate variations in image acquisition and patient anatomy. To get started, see Get Started with Image Preprocessing and Augmentation for Deep Learning.

Functions

expand all

specklefiltFilter image using speckle-reducing anisotropic diffusion (Since R2022b)
imfilterN-D filtering of multidimensional images
medfilt22-D median filtering
medfilt33-D median filtering
imgaussfilt2-D Gaussian filtering of images
imgaussfilt33-D Gaussian filtering of 3-D images
fspecialCreate predefined 2-D filter
fspecial3Create predefined 3-D filter

Fast Registration

imregmomentFast registration of grayscale images or intensity volumes using moment of mass method (Since R2022b)

Optimization-Based Registration

imregisterIntensity-based image registration
imregtformEstimate geometric transformation that aligns two 2-D or 3-D images
imregconfigConfigurations for intensity-based registration
MattesMutualInformationMattes mutual information metric configuration
MeanSquaresMean square error metric configuration
RegularStepGradientDescentRegular step gradient descent optimizer configuration
OnePlusOneEvolutionaryOne-plus-one evolutionary optimizer configuration

Deformable Registration

imregdeformDeformable registration of grayscale images or intensity volumes using total variation method (Since R2022b)
imregdemonsEstimate displacement field that aligns two 2-D or 3-D images

Control Point Registration

fitgeotform3dFit 3-D geometric transformation to control point pairs (Since R2024a)

Groupwise Registration

imreggroupwiseGroupwise deformable registration (Since R2022b)

Correlation-Based Registration

imregcorrEstimate geometric transformation that aligns two 2-D images using phase correlation
normxcorr2Normalized 2-D cross-correlation

Surface Registration

imregicpSurface registration using iterative closest point algorithm (Since R2022b)

Apply Transformation

imwarpApply geometric transformation to image
resampleResample medical image volume in different patient coordinate system (Since R2022b)
jitterIntensityRandomly augment intensity of grayscale image or intensity volume (Since R2022b)
randomWindow2dRandomly select rectangular region in image (Since R2021a)
randomCropWindow3dCreate randomized cuboidal cropping window (Since R2019b)
centerCropWindow2dCreate rectangular center cropping window (Since R2019b)
centerCropWindow3dCreate cuboidal center cropping window (Since R2019b)
RectangleSpatial extents of 2-D rectangular region (Since R2019b)
CuboidSpatial extents of 3-D cuboidal region (Since R2019b)
randomAffine2dCreate randomized 2-D affine transformation (Since R2019b)
randomAffine3dCreate randomized 3-D affine transformation (Since R2019b)
affineOutputViewCreate output view for warping images (Since R2019b)
imeraseRemove image pixels within rectangular region of interest (Since R2021a)

Topics

Related Information