DeepAI AI Chat
Log In Sign Up

A Deep Learning Approach for Reconstruction Filter Kernel Discretization

by   Christopher Syben, et al.

In this paper, we present substantial evidence that a deep neural network will intrinsically learn the appropriate way to discretize the ideal continuous reconstruction filter. Currently, the Ram-Lak filter or heuristic filters which impose different noise assumptions are used for filtered back-projection. All of these, however, inhibit a fully data-driven reconstruction deep learning approach. In addition, the heuristic filters are not chosen in an optimal sense. To tackle this issue, we propose a formulation to directly learn the reconstruction filter. The filter is initialized with the ideal Ramp filter as a strong pre-training and learned in frequency domain. We compare the learned filter with the Ram-Lak and the Ramp filter on a numerical phantom as well as on a real CT dataset. The results show that the network properly discretizes the continuous Ramp filter and converges towards the Ram-Lak solution. In our view these observations are interesting to gain a better understanding of deep learning techniques and traditional analytic techniques such as Wiener filtering and discretization theory. Furthermore, this will allow fully trainable data-driven reconstruction deep learning approaches.


Deep Generative Fixed-filter Active Noise Control

Due to the slow convergence and poor tracking ability, conventional LMS-...

k-Space Deep Learning for Accelerated MRI

The annihilating filter-based low-rank Hanel matrix approach (ALOHA) is ...

A Continuous Convolutional Trainable Filter for Modelling Unstructured Data

Convolutional Neural Network (CNN) is one of the most important architec...

Continuous Conversion of CT Kernel using Switchable CycleGAN with AdaIN

In X-ray computed tomography (CT) reconstruction, different filter kerne...

Learned Experts' Assessment-based Reconstruction Network ("LEARN") for Sparse-data CT

Compressive sensing (CS) has proved effective for tomographic reconstruc...

DNN-Based Topology Optimisation: Spatial Invariance and Neural Tangent Kernel

We study the SIMP method with a density field generated by a fully-conne...