Sparse-Coding-Based Computed Tomography Image Reconstruction

Abstract EN

Computed tomography (CT) is a popular type of medical imaging that generatesimages of the internal structure of an object based on projection scans of the objectfrom several angles.

There are numerous methods to reconstruct the original shapeof the target object from scans, but they are still dependent on the number of anglesand iterations.

To overcome the drawbacks of iterative reconstruction approacheslike the algebraic reconstruction technique (ART), while the recovery is slightlyimpacted from a random noise (small amount of ℓ2 norm error) and projection scans(small amount of ℓ1 norm error) as well, we propose a medical image reconstructionmethodology using the properties of sparse coding.

It is a very powerful matrixfactorization method which each pixel point is represented as a linear combinationof a small number of basis vectors.