A hierarchical approach to deep learning and its application to tomographic reconstruction

12/16/2019
by   Lin Fu, et al.
21

Deep learning (DL) has shown unprecedented performance for many image analysis and image enhancement tasks. Yet, solving large-scale inverse problems like tomographic reconstruction remains challenging for DL. These problems involve non-local and space-variant integral transforms between the input and output domains, for which no efficient neural network models have been found. A prior attempt to solve such problems with supervised learning relied on a brute-force fully connected network and applied it to reconstruction for a 128^4 system matrix size. This cannot practically scale to realistic data sizes such as 512^4 and 512^6 for three-dimensional data sets. Here we present a novel framework to solve such problems with deep learning by casting the original problem as a continuum of intermediate representations between the input and output data. The original problem is broken down into a sequence of simpler transformations that can be well mapped onto an efficient hierarchical network architecture, with exponentially fewer parameters than a generic network would need. We applied the approach to computed tomography (CT) image reconstruction for a 512^4 system matrix size. To our knowledge, this enabled the first data-driven DL solver for full-size CT reconstruction without relying on the structure of direct (analytical) or iterative (numerical) inversion techniques. The proposed approach is applicable to other imaging problems such as emission and magnetic resonance reconstruction. More broadly, hierarchical DL opens the door to a new class of solvers for general inverse problems, which could potentially lead to improved signal-to-noise ratio, spatial resolution and computational efficiency in various areas.

READ FULL TEXT

page 5

page 6

page 7

page 8

page 9

research
01/10/2020

A Two-step-training Deep Learning Framework for Real-time Computational Imaging without Physics Priors

Deep learning (DL) is a powerful tool in computational imaging for many ...
research
01/05/2020

The troublesome kernel: why deep learning for inverse problems is typically unstable

There is overwhelming empirical evidence that Deep Learning (DL) leads t...
research
09/21/2022

Artificial Intelligence-Based Image Reconstruction in Cardiac Magnetic Resonance

Artificial intelligence (AI) and Machine Learning (ML) have shown great ...
research
09/12/2022

Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography

In the present work, we propose a Self-supervised COordinate Projection ...
research
09/18/2023

vSHARP: variable Splitting Half-quadratic ADMM algorithm for Reconstruction of inverse-Problems

Medical Imaging (MI) tasks, such as accelerated Parallel Magnetic Resona...
research
08/19/2019

Direct Neural Network 3D Image Reconstruction of Radon Encoded Data

Neural network image reconstruction directly from measurement data is a ...
research
11/14/2018

Deep Bayesian Inversion

Characterizing statistical properties of solutions of inverse problems i...

Please sign up or login with your details

Forgot password? Click here to reset