Medical Image Registration

Medical image registration is the process of aligning multiple medical images, volumes, or surfaces to a common coordinate system. In medical imaging, you may need to compare scans of multiple patients or scans of the same patient taken in different sessions under different conditions. Use medical image registration as a preprocessing step to align the medical images to a common coordinate system before you analyze them.

Scenarios for Medical Image Registration

Classification by Type of Misalignment

• Translation registration - Required when the two images, volumes, or surfaces differ by a global shift common to all pixels, voxels, or points.

  

• Rigid registration - Required when the two images, volumes, or surfaces differ by a global shift and a global rotation common to all pixels, voxels, or points.

  

• Similarity registration - Required when the two images, volumes, or surfaces differ by a global shift, a global rotation, and a global scale factor common to all pixels, voxels, or points.

  

• Affine registration - Required when the two images, volumes, or surfaces differ by a global shift, a global rotation, a global scale factor, and a global shear factor common to all pixels, voxels, or points.

  

• Deformable registration (also known as non-rigid registration) - Required when the images, volumes, or surfaces differ by local transformations specific to certain pixels, voxels, or points.

  

Classification by Type of Input

• Image registration - Aligns 2-D grayscale images.

• Volume registration - Aligns 3-D intensity volumes.

• Surface registration - Aligns surfaces extracted from 3-D intensity volumes.

• Groupwise registration - Aligns slices in a series of 2-D medical images, such as a timeseries, to reduce sliding motion between the slices.

Interactive Registration Using Apps

The Medical Registration Estimator app (since R2024b) enables you to interactively register 3-D medical image volumes. You can manually translate, rotate, and scale the volumes to align them, or apply automated rigid and deformable registration techniques. You can compare different techniques, tune settings, and visualize the registered volumes as 2-D slice planes and 3-D volumes. The app provides a quantitative measure of registration accuracy, and you can export the registered volume and the transformation matrix. The app can also generate code with your selected registration technique to apply to other volumes outside of the app. To learn more, see Get Started with Medical Registration Estimator.

To register 2-D images, use the Registration Estimator app.

Functions for Medical Image Registration

Medical Imaging Toolbox™ provides various functions for medical image registration.

Function	Type of Misalignment	Type of Input	Function Details	Method
imregmoment	Translation Rigid Similarity	2-D grayscale images 3-D intensity volumes	Returns registered image and transform.	Fast registration technique. Uses moment of mass method, with the option to also use the median threshold bitmap (MTB) method. Suitable for monomodal and multimodal images and volumes.
imregister	Translation Rigid Similarity Affine	2-D grayscale images 3-D intensity volumes	Specify configuration using imregconfig. Returns registered image. Get transform by using imregtform.	Optimization-based technique. Regular step gradient descent optimizer with mean squares metric for monomodal configuration. One-plus-one evolutionary optimizer with Mattes mutual information metric for multimodal configuration.
imregcorr	Translation Rigid Similarity	2-D grayscale, binary, and RGB images	Returns transform. Get the registered image by using imwarp.	FFT-based technique. Uses the phase correlation method.
imregmtb	Translation	2-D grayscale and RGB images	Returns registered images and displacement vector.	Fast registration technique. Uses median threshold bitmap (MTB) method. Suitable for monomodal and multimodal images.
imregicp	Translation Rigid	Surfaces	Returns registered surface and transform.	Optimization-based technique. Uses the iterative closest point (ICP) algorithm.
imregdemons	Deformable	2-D grayscale images 3-D intensity volumes	Returns registered image and displacement field.	Deformable registration technique. Uses a diffusion-based Demons algorithm.
imregdeform	Deformable	2-D grayscale images 3-D intensity volumes	Returns registered image and displacement field.	Deformable registration technique. Uses the isotropic total variation regularization method.
imreggroupwise	Deformable	3-D image series consisting of 2-D slices	Returns registered image and displacement field. Requires only one input image.	Groupwise registration technique. Uses the isotropic total variation regularization method.
fitgeotform2d	Similarity Reflective Similarity Affine	2-D control point pairs	Returns transform. Get the registered image by using imwarp.	Performs 2-D point mapping between pairs of control points.
fitgeotform3d	Translation Rigid Affine	3-D control point pairs	Returns transform. Get the registered image by using imwarp.	Performs 3-D point mapping between pairs of control points.