TY - GEN
T1 - Advancing the AmbientGAN for learning stochastic object models
AU - Zhou, Weimin
AU - Bhadra, Sayantan
AU - Brooks, Frank J.
AU - Granstedt, Jason L.
AU - Li, Hua
AU - Anastasio, Mark A.
N1 - Publisher Copyright:
Copyright © 2021 SPIE.
PY - 2021
Y1 - 2021
N2 - Medical imaging systems are commonly assessed and optimized by use of objective-measures of image quality (IQ) that quantify the performance of an observer at specific tasks. Variation in the objects to-be-imaged is an important source of variability that can significantly limit observer performance. This object variability can be described by stochastic object models (SOMs). In order to establish SOMs that can accurately model realistic object variability, it is desirable to use experimental data. To achieve this, an augmented generative adversarial network (GAN) architecture called AmbientGAN has been developed and investigated. However, AmbientGANs cannot be immediately trained by use of advanced GAN training methods such as the progressive growing of GANs (ProGANs). Therefore, the ability of AmbientGANs to establish realistic object models is limited. To circumvent this, a progressively-growing AmbientGAN (ProAmGAN) has been proposed. However, ProAmGANs are designed for generating two-dimensional (2D) images while medical imaging modalities are commonly employed for imaging three-dimensional (3D) objects. Moreover, ProAmGANs that employ traditional generator architectures lack the ability to control specific image features such as fine-scale textures that are frequently considered when optimizing imaging systems. In this study, we address these limitations by proposing two advanced AmbientGAN architectures: 3D ProAmGANs and Style-AmbientGANs (StyAmGANs). Stylized numerical studies involving magnetic resonance (MR) imaging systems are conducted. The ability of 3D ProAmGANs to learn 3D SOMs from imaging measurements and the ability of StyAmGANs to control fine-scale textures of synthesized objects are demonstrated.
AB - Medical imaging systems are commonly assessed and optimized by use of objective-measures of image quality (IQ) that quantify the performance of an observer at specific tasks. Variation in the objects to-be-imaged is an important source of variability that can significantly limit observer performance. This object variability can be described by stochastic object models (SOMs). In order to establish SOMs that can accurately model realistic object variability, it is desirable to use experimental data. To achieve this, an augmented generative adversarial network (GAN) architecture called AmbientGAN has been developed and investigated. However, AmbientGANs cannot be immediately trained by use of advanced GAN training methods such as the progressive growing of GANs (ProGANs). Therefore, the ability of AmbientGANs to establish realistic object models is limited. To circumvent this, a progressively-growing AmbientGAN (ProAmGAN) has been proposed. However, ProAmGANs are designed for generating two-dimensional (2D) images while medical imaging modalities are commonly employed for imaging three-dimensional (3D) objects. Moreover, ProAmGANs that employ traditional generator architectures lack the ability to control specific image features such as fine-scale textures that are frequently considered when optimizing imaging systems. In this study, we address these limitations by proposing two advanced AmbientGAN architectures: 3D ProAmGANs and Style-AmbientGANs (StyAmGANs). Stylized numerical studies involving magnetic resonance (MR) imaging systems are conducted. The ability of 3D ProAmGANs to learn 3D SOMs from imaging measurements and the ability of StyAmGANs to control fine-scale textures of synthesized objects are demonstrated.
KW - generative adversarial networks
KW - objective assessment of image quality
KW - signal detection
KW - stochastic object model
UR - http://www.scopus.com/inward/record.url?scp=85105497583&partnerID=8YFLogxK
U2 - 10.1117/12.2581687
DO - 10.1117/12.2581687
M3 - Conference contribution
AN - SCOPUS:85105497583
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2021
A2 - Samuelson, Frank W.
A2 - Taylor-Phillips, Sian
PB - SPIE
T2 - Medical Imaging 2021: Image Perception, Observer Performance, and Technology Assessment
Y2 - 15 February 2021 through 19 February 2021
ER -