AmbientCycleGAN for Establishing Interpretable Stochastic Object Models Based on Mathematical Phantoms and Medical Imaging Measurements
Xichen Xu, Wentao Chen, Weimin Zhou
TL;DR
The paper introduces AmbientCycleGAN, a noise-robust extension of CycleGAN that translates mathematical phantoms into realistic, interpretable stochastic object models (SOMs) using noisy imaging measurements. By integrating a measurement operator and adversarial/cycle losses, the method enables controllable translation from phantom domains to real-image domains while preserving content. Numerical results on synthetic CLB phantoms and real mammograms demonstrate improved image fidelity (lower FID), realistic texture statistics, and task-based performance similarity to ground truth, along with demonstrated interpretable control of object features. This approach supports more comprehensive, task-based evaluations of medical imaging systems by accounting for measurement noise and enabling realistic, controllable object variability. The proposed framework holds promise for constructing realistic, interpretable SOMs that can underpin robust IQ assessments and optimization of imaging pipelines.
Abstract
Medical imaging systems that are designed for producing diagnostically informative images should be objectively assessed via task-based measures of image quality (IQ). Ideally, computation of task-based measures of IQ needs to account for all sources of randomness in the measurement data, including the variability in the ensemble of objects to be imaged. To address this need, stochastic object models (SOMs) that can generate an ensemble of synthesized objects or phantoms can be employed. Various mathematical SOMs or phantoms were developed that can interpretably synthesize objects, such as lumpy object models and parameterized torso phantoms. However, such SOMs that are purely mathematically defined may not be able to comprehensively capture realistic object variations. To establish realistic SOMs, it is desirable to use experimental data. An augmented generative adversarial network (GAN), AmbientGAN, was recently proposed for establishing SOMs from medical imaging measurements. However, it remains unclear to which extent the AmbientGAN-produced objects can be interpretably controlled. This work introduces a novel approach called AmbientCycleGAN that translates mathematical SOMs to realistic SOMs by use of noisy measurement data. Numerical studies that consider clustered lumpy background (CLB) models and real mammograms are conducted. It is demonstrated that our proposed method can stably establish SOMs based on mathematical models and noisy measurement data. Moreover, the ability of the proposed AmbientCycleGAN to interpretably control image features in the synthesized objects is investigated.