Learning stochastic object models from medical imaging measurements by use of advanced ambient generative adversarial networks

2021/06/30 by Weimin Zhou, Sayantan Bhadra, Frank J. Brooks +2
Computer Science · Engineering · Mathematics · Physics and Astronomy · #Deep learning #Domain Adaptation and Few-Shot Learning #Generative Adversarial Networks and Image Synthesis #Generative grammar #Generative model #Iterative reconstruction #Magnetic resonance imaging #Medical imaging #Model Reduction and Neural Networks #Object (grammar) #Stylized fact #cs.CV #cs.LG #eess.IV #stat.ML

paper · pdf · doi:10.1117/1.jmi.9.1.015503

published as J. Med. Imag. 9(1), 015503 (2022) · Journal of Medical Imaging

openalex publication_date 2022/02/23 · openalex created_date 2022/02/25 · arxiv created 2022/02/27 · arxiv updated 2022/03/01 · openalex updated_date 2026/08/06

Abstract

Purpose: To objectively assess new medical imaging technologies via computer-simulations, it is important to account for the variability in the ensemble of objects to be imaged. This source of variability can be described by stochastic object models (SOMs). It is generally desirable to establish SOMs from experimental imaging measurements acquired by use of a well-characterized imaging system, but this task has remained challenging. Approach: A generative adversarial network (GAN)-based method that employs AmbientGANs with modern progressive or multiresolution training approaches is proposed. AmbientGANs established using the proposed training procedure are systematically validated in a controlled way using computer-simulated magnetic resonance imaging (MRI) data corresponding to a stylized imaging system. Emulated single-coil experimental MRI data are also employed to demonstrate the methods under less stylized conditions. Results: The proposed AmbientGAN method can generate clean images when the imaging measurements are contaminated by measurement noise. When the imaging measurement data are incomplete, the proposed AmbientGAN can reliably learn the distribution of the measurement components of the objects. Conclusions: Both visual examinations and quantitative analyses, including task-specific validations using the Hotelling observer, demonstrated that the proposed AmbientGAN method holds promise to establish realistic SOMs from imaging measurements.

Citations

• Adam: A Method for Stochastic Optimization
• An exponential growth of computational phantom research in radiation protection, imaging, and radiotherapy: a review of the fifty-year history
• Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
• Towards Principled Methods for Training Generative Adversarial Networks
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
• A Style-Based Generator Architecture for Generative Adversarial Networks
• Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
• Markov-Chain Monte Carlo Approximation of the Ideal Observer using Generative Adversarial Networks