Method and apparatus for generating a derived image using images of different types

摘要

Disclosed herein are techniques for translating a first image of a first type to a derived image of a second type. For example, a plurality of similarity indicators can be computed as between a plurality of patches of first image and a plurality of patches of a first atlas image, the first atlas image being of the first type. Weight factors can then be computed based on the computed similarity indicators. These weight factors can be applied to a plurality of data points of a second atlas image to compute a plurality of data points for the derived image such that each of at least a plurality of the data points for the derived image is a function of a plurality of the data points of the second atlas image. Such a technique can be used for pseudo-CT generation from an MR image.

主权项

1. A method of converting a first image of a first modality type to a second image of a second modality type based on a first reference image of the first modality type and a second reference image of the second modality type, wherein the first modality type and the second modality type are different, the method comprising:
selecting a first set of image data points in the first image, wherein the first set of image data points is associated with a first image data point of the first image; selecting a plurality of sets of image data points in the first reference image, wherein each set of the selected image data points in the first reference image is associated with a reference image data point of the first reference image, and wherein each set of the selected image data points in the first reference image is associated with a different reference image data point of the first reference image; comparing the first set of image data points selected in the first image and each of the plurality of sets of selected image data points in the first reference image to generate a plurality of similarity indicators respectively indicative of similarities between the first image data point and corresponding reference image data points; computing a plurality of weight factors associated with a plurality of reference image data points in the second reference image based on the similarity indicators; computing a second image data point corresponding to the first image data point as a weighted combination of the plurality of reference image data points in the second reference image that are associated with the computed weight factors, the weighted combination being in accordance with the computed weight factors; and generating the second image including a plurality of second image data points by repeatedly computing individual second image data points of the second image based on a plurality of different first image data points in the first image.