Solving a Nonlinear Blind Inverse Problem for Tagged MRI with Physics and Deep Generative Priors

• URL: http://arxiv.org/abs/2603.00882v1
• Date: Sun, 01 Mar 2026 03:04:52 GMT
• Title: Solving a Nonlinear Blind Inverse Problem for Tagged MRI with Physics and Deep Generative Priors
• Abstract summary: We introduce a blind and nonlinear inverse framework for tagged MRI.<n>It unifies anatomical image recovery, high-resolution cine image synthesis, and motion estimation.<n>Our approach yields high-resolution anatomy images, cine images, and more accurate motion than specialized methods.
• Score: 13.337165064590025
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tagged MRI enables tracking internal tissue motion non-invasively. It encodes motion by modulating anatomy with periodic tags, which deform along with tissue. However, the entanglement between anatomy, tags and motion poses significant challenges for post-processing. The existence of tags and imaging blur hinders downstream tasks such as segmenting anatomy. Tag fading, due to T1-relaxation, disrupts the brightness constancy assumption for motion tracking. For decades, these challenges have been handled in isolation and sub-optimally. In contrast, we introduce a blind and nonlinear inverse framework for tagged MRI that, for the first time, unifies these tasks: anatomical image recovery, high-resolution cine image synthesis, and motion estimation. At its core, the synergy of MR physics and generative priors enables us to blindly estimate the unknown forward imaging models and high-resolution underlying anatomy, while simultaneously tracking 3D diffeomorphic Lagrangian motion over time. Experiments on tagged brain MRI demonstrate that our approach yields high-resolution anatomy images, cine images, and more accurate motion than specialized methods.

Related papers

• MotionDPS: Motion-Compensated 3D Brain MRI Reconstruction [39.243053176227065]
  We propose a motion-compensated 3D MRI that estimates the anatomical image, rigid-body motion parameters, and coil sensitivity maps directly from motion-corrupted k-space data.<n>Our approach integrates pretrained 3D complex-valued score-based diffusion models as expressive anatomical image priors within a physics-based forward model.<n> Experiments on simulated and real-motion brain MRI datasets demonstrate that the proposed method achieves improved image quality and motion robustness.
  arXiv  Detail & Related papers  (2026-05-21T07:53:06Z)
• Accelerating 3D Photoacoustic Computed Tomography with End-to-End Physics-Aware Neural Operators [74.65171736966131]
  Photoacoustic computed tomography (PACT) combines optical contrast with ultrasonic resolution, achieving deep-tissue imaging beyond the optical diffusion limit.<n>Current implementations require dense transducer arrays and prolonged acquisition times, limiting clinical translation.<n>We introduce Pano, an end-to-end physics-aware model that directly learns the inverse acoustic mapping from sensor measurements to volumetric reconstructions.
  arXiv  Detail & Related papers  (2025-09-11T23:12:55Z)
• Brightness-Invariant Tracking Estimation in Tagged MRI [7.804326076893715]
  We introduce the brightness-invariant tracking estimation technique for tagged MRI.<n>BRITE disentangles the anatomy from the tag pattern in the observed tagged image sequence and simultaneously estimates the Lagrangian motion.<n>Results show that BRITE achieves more accurate motion and strain estimates as compared to other state of the art methods, while also being resistant to tag fading.
  arXiv  Detail & Related papers  (2025-05-23T20:48:23Z)
• X$^{2}$-Gaussian: 4D Radiative Gaussian Splatting for Continuous-time Tomographic Reconstruction [64.2059940799033]
  Current methods discretize temporal resolution into fixed phases with respiratory gating devices.<n>X$2$-Gaussian, a novel framework, enables continuous-time 4DCT reconstruction by integrating dynamic radiative splatting with self-supervised respiratory motion learning.
  arXiv  Detail & Related papers  (2025-03-27T17:59:57Z)
• Fully Unsupervised Dynamic MRI Reconstruction via Diffeo-Temporal Equivariance [2.260147251787331]
  Supervised learning methods are flawed as they assume periodicity, disallowing imaging of true motion.<n>We propose an unsupervised framework to learn to reconstruct dynamic MRI sequences from undersampled measurements alone.<n>Our method is agnostic to the underlying neural network architecture and can be used to adapt the latest paradigms and post-processing approaches.
  arXiv  Detail & Related papers  (2024-10-11T09:16:30Z)
• MindFormer: Semantic Alignment of Multi-Subject fMRI for Brain Decoding [50.55024115943266]
  We introduce a novel semantic alignment method of multi-subject fMRI signals using so-called MindFormer. This model is specifically designed to generate fMRI-conditioned feature vectors that can be used for conditioning Stable Diffusion model for fMRI- to-image generation or large language model (LLM) for fMRI-to-text generation. Our experimental results demonstrate that MindFormer generates semantically consistent images and text across different subjects.
  arXiv  Detail & Related papers  (2024-05-28T00:36:25Z)
• Volumetric Reconstruction Resolves Off-Resonance Artifacts in Static and Dynamic PROPELLER MRI [76.60362295758596]
  Off-resonance artifacts in magnetic resonance imaging (MRI) are visual distortions that occur when the actual resonant frequencies of spins within the imaging volume differ from the expected frequencies used to encode spatial information. We propose to resolve these artifacts by lifting the 2D MRI reconstruction problem to 3D, introducing an additional "spectral" dimension to model this off-resonance.
  arXiv  Detail & Related papers  (2023-11-22T05:44:51Z)
• On Sensitivity and Robustness of Normalization Schemes to Input Distribution Shifts in Automatic MR Image Diagnosis [58.634791552376235]
  Deep Learning (DL) models have achieved state-of-the-art performance in diagnosing multiple diseases using reconstructed images as input. DL models are sensitive to varying artifacts as it leads to changes in the input data distribution between the training and testing phases. We propose to use other normalization techniques, such as Group Normalization and Layer Normalization, to inject robustness into model performance against varying image artifacts.
  arXiv  Detail & Related papers  (2023-06-23T03:09:03Z)
• Deep learning network to correct axial and coronal eye motion in 3D OCT retinal imaging [65.47834983591957]
  We propose deep learning based neural networks to correct axial and coronal motion artifacts in OCT based on a single scan. The experimental result shows that the proposed method can effectively correct motion artifacts and achieve smaller error than other methods.
  arXiv  Detail & Related papers  (2023-05-27T03:55:19Z)
• Joint fMRI Decoding and Encoding with Latent Embedding Alignment [77.66508125297754]
  We introduce a unified framework that addresses both fMRI decoding and encoding. Our model concurrently recovers visual stimuli from fMRI signals and predicts brain activity from images within a unified framework.
  arXiv  Detail & Related papers  (2023-03-26T14:14:58Z)
• DRIMET: Deep Registration for 3D Incompressible Motion Estimation in Tagged-MRI with Application to the Tongue [11.485843032637439]
  Tagged magnetic resonance imaging(MRI) has been used for decades to observe and quantify the detailed motion of deforming tissue. This paper presents a novel unsupervised phase-based 3D motion estimation technique for tagged MRI.
  arXiv  Detail & Related papers  (2023-01-18T00:16:30Z)
• STRESS: Super-Resolution for Dynamic Fetal MRI using Self-Supervised Learning [2.5581619987137048]
  We propose STRESS, a self-supervised super-resolution framework for dynamic fetal MRI with interleaved slice acquisitions. Our proposed method simulates an interleaved slice acquisition along the high-resolution axis on the originally acquired data to generate pairs of low- and high-resolution images. Evaluations on both simulated and in utero data show that our proposed method outperforms other self-supervised super-resolution methods.
  arXiv  Detail & Related papers  (2021-06-23T13:52:11Z)
• DeepTag: An Unsupervised Deep Learning Method for Motion Tracking on Cardiac Tagging Magnetic Resonance Images [10.434681088538866]
  We propose a novel deep learning-based fully unsupervised method for in vivo motion tracking on t-MRI images. Our method has been validated on a representative clinical t-MRI dataset.
  arXiv  Detail & Related papers  (2021-03-04T00:42:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.