Establishing Stochastic Object Models from Noisy Data via Ambient Measurement-Integrated Diffusion
This addresses the problem of realistic anatomical modeling for medical imaging system evaluation, though it appears incremental as an adaptation of diffusion models to noisy data.
The paper tackles the challenge of establishing stochastic object models (SOMs) for medical imaging quality evaluation from noisy clinical data, proposing AMID, an unsupervised diffusion method that learns clean SOMs directly from noisy measurements and shows improved generation fidelity on CT and mammography datasets.
Task-based measures of image quality (IQ) are critical for evaluating medical imaging systems, which must account for randomness including anatomical variability. Stochastic object models (SOMs) provide a statistical description of such variability, but conventional mathematical SOMs fail to capture realistic anatomy, while data-driven approaches typically require clean data rarely available in clinical tasks. To address this challenge, we propose AMID, an unsupervised Ambient Measurement-Integrated Diffusion with noise decoupling, which establishes clean SOMs directly from noisy measurements. AMID introduces a measurement-integrated strategy aligning measurement noise with the diffusion trajectory, and explicitly models coupling between measurement and diffusion noise across steps, an ambient loss is thus designed base on it to learn clean SOMs. Experiments on real CT and mammography datasets show that AMID outperforms existing methods in generation fidelity and yields more reliable task-based IQ evaluation, demonstrating its potential for unsupervised medical imaging analysis.