Patient-specific hyperparameter learning for optimization-based CT image reconstruction

Jingyan Xu

doi:10.1088/1361-6560/ac0f9a

Patient-specific hyperparameter learning for optimization-based CT image reconstruction

2021-09-20

6

OA

AI

DOI：10.1088/1361-6560/ac0f9a

Original

Original request for help

Save

Abstract

En 中文

We propose a hyperparameter learning framework that learns patient-specific hyperparameters for optimization-based image reconstruction problems for x-ray CT applications. The framework consists of two functional modules: (1) a hyperparameter learning module parameterized by a convolutional neural network, (2) an image reconstruction module that takes as inputs both the noisy sinogram and the hyperparameters from (1) and generates the reconstructed images. As a proof-of-concept study, in this work we focus on a subclass of optimization-based image reconstruction problems with exactly computable solutions so that the whole network can be trained end-to-end in an efficient manner. Unlike existing hyperparameter learning methods, our proposed framework generates patient-specific hyperparameters from the sinogram of the same patient. Numerical studies demonstrate the effectiveness of our proposed approach compared to bi-level optimization.

Keywords:

bi-level optimization

dynamic programming

hyperparameter learning

low dose CT

sinogram smoothing

Patient-specific hyperparameter learning for optimization-based CT image reconstruction

Abstract

Journal

Organization