REVIEW 25 cited by
Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
read the original abstract
Reconstructing medical images from partial measurements is an important inverse problem in Computed Tomography (CT) and Magnetic Resonance Imaging (MRI). Existing solutions based on machine learning typically train a model to directly map measurements to medical images, leveraging a training dataset of paired images and measurements. These measurements are typically synthesized from images using a fixed physical model of the measurement process, which hinders the generalization capability of models to unknown measurement processes. To address this issue, we propose a fully unsupervised technique for inverse problem solving, leveraging the recently introduced score-based generative models. Specifically, we first train a score-based generative model on medical images to capture their prior distribution. Given measurements and a physical model of the measurement process at test time, we introduce a sampling method to reconstruct an image consistent with both the prior and the observed measurements. Our method does not assume a fixed measurement process during training, and can thus be flexibly adapted to different measurement processes at test time. Empirically, we observe comparable or better performance to supervised learning techniques in several medical imaging tasks in CT and MRI, while demonstrating significantly better generalization to unknown measurement processes.
Forward citations
Cited by 25 Pith papers
-
Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines
DiRIM uses a diffusion model with recurrent score refinement to sample pixel-space joint posteriors of the lensed source and foreground mass map, reproducing mock strong-lens observations to the noise level.
-
UOTIP: Unbalanced Optimal Transport Map for Unpaired Inverse Problems
UOTIP learns an unbalanced optimal transport map from noisy to clean distributions for unpaired inverse problems, incorporating a likelihood cost and proving existence/uniqueness via quadratic cost satisfying the twis...
-
DiLO: Decoupling Generative Priors and Neural Operators via Diffusion Latent Optimization for Inverse Problems
DiLO turns diffusion sampling into deterministic latent optimization to satisfy the manifold consistency requirement for neural operators in inverse problem solving.
-
Sample-efficient evidence estimation of score based priors for model selection
DiME estimates model evidence for diffusion priors by integrating time-marginals from posterior sampling, enabling efficient prior selection and misfit diagnosis in ill-posed inverse problems.
-
Physics Matters in PnP: Recovery Guarantees with the MMSE and NN Denoisers
PnP-FBS with MMSE denoisers recovers the true signal with explicit pointwise and Wasserstein error bounds, provided the denoiser's noise covariance is matched to the preconditioned observation noise.
-
Agentic Autoresearch for CT Reconstruction
An LLM agent autonomously benchmarked 26 CT reconstruction methods and showed that adding mild noise nearly inverts the clean-data ranking, with retraining partially restoring it.
-
From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors
TF-PRDiT uses a frozen 3D diffusion transformer prior with task-specific forward operators and predictor-corrector sampling to solve X-ray-to-CT reconstruction and other volumetric inverse problems without any retraining.
-
From Sparse X-rays to 3D CT: Training-Free Reconstruction with Diffusion Priors
A single frozen 3D diffusion prior, guided at inference by task-specific forward operators, reconstructs CT from 1-12 X-ray views and handles super-resolution, infilling, and deblurring without retraining.
-
Learning the Universe: Posterior Reliability of Neural Generative Models in High-Dimensional Field-Level Inference of Cosmic Initial Conditions
Generative models for cosmological field-level inference can reproduce posterior means and cross-correlations yet fail to capture correct uncertainty geometry when validated against HMC reference samples.
-
Measurement Geometry and Design for Trustworthy Generative Inverse Problems
Introduces a local measurement-manifold compatibility measure that bounds stable reconstruction error under generative priors and motivates fixed and adaptive acquisition rules.
-
KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse Problems
KLIP detects and localizes distribution shifts in inverse problems via KL-divergence between diffusion prior and posterior without calibration data.
-
Variance Reduction for Expectations with Diffusion Teachers
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-o...
-
Score-Based Generative Modeling through Anisotropic Stochastic Partial Differential Equations
Anisotropic SPDEs preserve geometric data structure over longer timescales in score-based generative modeling, yielding better image quality than standard SDE baselines and flow matching in unconditional and condition...
-
Generative Drifting for Conditional Medical Image Generation
GDM reformulates 3D conditional medical image generation as attractive-repulsive drifting with multi-level feature banks to balance distribution plausibility, patient fidelity, and one-step inference, outperforming GA...
-
Jacobian-Aware Posterior Sampling for Inverse Problems
AdaPS adaptively scales likelihood guidance in DDIM posterior sampling via agreement between two surrogates, improving LPIPS/PSNR trade-offs on image restoration tasks without task-specific tuning.
-
Reverse Imaging for Wide-spectrum Generalization of Cardiac MRI Segmentation
Estimating tissue spin properties from a cardiac MRI and synthesizing new sequence contrasts via physics improves zero-shot segmentation across protocols.
-
Joint Reconstruction of Activity and Attenuation in PET by Diffusion Posterior Sampling in Wavelet Coefficient Space
A wavelet diffusion model combined with diffusion posterior sampling enables joint 3D activity-attenuation reconstruction in PET from emission data alone, outperforming MLAA on simulated TOF data.
-
3DGR-CT: Sparse-View CT Reconstruction with a 3D Gaussian Representation
3DGR-CT adapts 3D Gaussian splatting with FBP-guided initialization and differentiable CT projection for sparse-view reconstruction, claiming better accuracy and speed than prior methods.
-
Lyapunov Guidance: A Unified Framework for Stabilizing Generative Flows
Flow guidance is framed as Lyapunov control with a pseudo-projection for stability, but the projected flow is not shown to sample the target conditional distribution.
-
Hallucination-Aware Diffusion Sampling for Inverse Problems via Robust Prior Updates
RPU stabilizes the prior update in diffusion inverse solvers to reduce measurement-conditioned hallucinations, with reported gains on FFHQ and ImageNet.
-
Multi-Objective Learning for Diffusion Models: A Statistical Theory under Semi-Supervised Learning
A semi-supervised MOL framework for diffusion models with generalization bounds depending only on specialist model complexity, extended to diffusion policies for sequential decisions.
-
Variance Reduction for Expectations with Diffusion Teachers
CARV introduces a hierarchical Monte Carlo estimator with amortized reuse, importance sampling, and stratification that yields 2-3x effective compute gains on diffusion-teacher pipelines while cutting gradient varianc...
-
Diffusion Models for Solving Inverse Problems via Posterior Sampling with Piecewise Guidance
Piecewise guidance in diffusion posterior sampling cuts inference time 23-25% on inpainting and super-resolution with negligible PSNR/SSIM loss while handling measurement noise.
-
Dual Ascent Diffusion for Inverse Problems
A dual ascent optimization framework is introduced for MAP estimation with diffusion priors, claimed to outperform prior methods on image restoration in quality, noise robustness, speed, and data fidelity.
-
A Survey on Diffusion Models for Inverse Problems
A survey that introduces taxonomies for categorizing pre-trained diffusion model methods applied to inverse problems and analyzes their connections and challenges.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.