Welcome back to deep learning! So today, we want to look into the applications of known operator learning and a particular one that I want to show today is CT reconstruction.
CT Reconstruction is just matrix multiplication with really large, sparse matrices. Image under CC BY 4.0 from the Deep Learning Lecture.
So here, you see the formal solution to the CT reconstruction problem. This is the so-called filtered back-projection or Radon inverse. This is exactly the equation that I referred to earlier that has already been solved in 1917. But as you may know, CT scanners have only been realized in 1971. So actually, Radon who found this very nice solution has never seen it put to practice. So, how did he solve the CT reconstruction problem? Well, CT reconstruction is a projection process. It’s essentially a linear system of equations that can be solved. The solution is essentially described by a convolution and a sum. So, it’s a convolution along the detector direction s and then a back-projection over the rotation angle θ. During the whole process, we suppress negative values. So, we kind of also get a non-linearity into the system. This all can also be expressed in matrix notation. So, we know that the projection operations can simply be described as a matrix A that describes how the rays intersect with the volume. With this matrix, you can simply take the volume x multiplied with A and this gives you the projections p that you observe in the scanner. Now, getting the reconstruction is you take the projections p and you essentially need some kind of inverse or pseudo-inverse of A in order to compute this. We can see that there is a solution that is very similar to what we’ve seen in the above continuous equation. So, we have essentially a pseudo-inverse here and that is A transpose times A A transpose inverted times p. Now, you could argue that the inverse that you see here in a is actually the filter. So, for this particular problem, we know that the inverse of A A transpose will form a convolution.
#fau-lecture-notes #machine-learning #data-science #artificial-intelligence #deep-learning #deep learning
