Stabilizing Deep Tomographic Reconstruction

Tomographic Image Reconstruction

Binary tomographic reconstruction

The binary tomographic reconstruction problem consists of finding a binary image from (very) few projections (line sum of pixels) along given directions [1]. An efficient heuristic algorithm is introduced [2]. The first (initialization) step is similar to the traditional “filtered backprojection” algorithm used for standard tomographic reconstructions, but based on a non-linear transform, s = ...

Tomographic reconstruction from limited data

Introduction At present, image reconstruction in micro-CT imaging is typically performed using the FDK algorithm. This algorithm, which is similar to the Filtered Backprojection algorithm for singleslice tomography, is capable of computing accurate reconstructions in a relatively short time, provided that the acquired dataset satisfies certain requirements: (i) a large number of projection imag...

Parallelisation of Tomographic Reconstruction Methods

In medicine, there is a still growing interest in non-invasive examination techniques which can depict anatomical structures. Amongst these methods are Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET) and Computerised Tomography (CT). These are all based on the same principle: under a number of angles, a set of line integrals in a plane is measured resulting in a set of proo...

Variational Approach to Tomographic Reconstruction

We formulate the tomographic reconstruction problem in a variational setting. The object to be reconstructed is considered as a continuous density function, unlike in the pixel-based approaches. The measurements are modeled as linear operators (Radon transform), integrating the density function along the ray path. The criterion that we minimize consists of a data term and a regularization term....