mlsanityData to 14 Oct 2026

Accelerating multiparametric quantitative MRI using self-supervised scan-specific implicit neural representation with model reinforcement

arXiv 2508.00891 ↗First posted 27 Jul 2025physics.med-ph cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Purpose: To develop a self-supervised scan-specific deep learning framework for reconstructing accelerated multiparametric quantitative MRI (qMRI). Methods: We propose REFINE-MORE (REference-Free Implicit NEural representation with MOdel REinforcement), combining an implicit neural representation (INR) architecture with a model reinforcement module that incorporates MR physics constraints. The INR component enables informative learning of spatiotemporal correlations to initialize multiparametric quantitative maps, which are then further refined through an unrolled optimization scheme enforcing data consistency. To improve computational efficiency, REFINE-MORE integrates a low-rank adaptation strategy that promotes rapid model convergence. We evaluated REFINE-MORE on accelerated multiparametric quantitative magnetization transfer imaging for simultaneous estimation of free water spin-lattice relaxation, tissue macromolecular proton fraction, and magnetization exchange rate, using both phantom and in vivo brain data. Results: Under 4x and 5x accelerations on in vivo data, REFINE-MORE achieved superior reconstruction quality, demonstrating the lowest normalized root-mean-square error and highest structural similarity index compared to baseline methods and other state-of-the-art model-based and deep learning approaches. Phantom experiments further showed strong agreement with reference values, underscoring the robustness and generalizability of the proposed framework. Additionally, the model adaptation strategy improved reconstruction efficiency by approximately fivefold. Conclusion: REFINE-MORE enables accurate and efficient scan-specific multiparametric qMRI reconstruction, providing a flexible solution for high-dimensional, accelerated qMRI applications.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 26 of its 71 references that are in the map. First posted on arXiv 27 Jul 2025.

Builds on

26 of 71 references.

References · 26

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  4. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  5. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  6. 2021NeX: Real-time View Synthesis with Neural Basis Expansioncited by 216
  7. 2021NeRP: Implicit Neural Representation Learning with Prior Embedding for Sparsely Sampled Image Reconstructioncited by 146
  8. 2021NeRF-SR: High-Quality Neural Radiance Fields using Supersamplingcited by 95
  9. 2021Dynamic CT Reconstruction from Limited Views with Implicit Neural Representations and Parametric Motion Fieldscited by 71
  10. 2021Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fieldscited by 48
  11. 2022Spatiotemporal implicit neural representation for unsupervised dynamic MRI reconstructioncited by 36
  12. 2022Neural Implicit k-Space for Binning-free Non-Cartesian Cardiac MR Imagingcited by 35
14 more
  1. 2022Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomographycited by 31
  2. 2017MR fingerprinting Deep RecOnstruction NEtwork (DRONE)cited by 28
  3. 2023IMJENSE: Scan-specific Implicit Representation for Joint Coil Sensitivity and Image Estimation in Parallel MRIcited by 23
  4. 2023Implicit Neural Networks with Fourier-Feature Inputs for Free-breathing Cardiac MRI Reconstructioncited by 15
  5. 2023One for Multiple: Physics-informed Synthetic Data Boosts Generalizable Deep Learning for Fast MRI Reconstructioncited by 15
  6. 2020Learned Proximal Networks for Quantitative Susceptibility Mappingcited by 10
  7. 2021MoDL-QSM: Model-based Deep Learning for Quantitative Susceptibility Mappingcited by 8
  8. 2023SSL-QALAS: Self-Supervised Learning for Rapid Multiparameter Estimation in Quantitative MRI Using 3D-QALAScited by 5
  9. 2023Zero-DeepSub: Zero-Shot Deep Subspace Reconstruction for Rapid Multiparametric Quantitative MRI Using 3D-QALAScited by 5
  10. 2017Recurrent Generative Adversarial Networks for Proximal Learning and Automated Compressive Image Recoverycited by 4
  11. 2021Model-based Synthetic Data-driven Learning (MOST-DL): Application in Single-shot T2 Mapping with Severe Head Motion Using Overlapping-echo Acquisitioncited by 4
  12. 2023High-Dimensional MR Reconstruction Integrating Subspace and Adaptive Generative Modelscited by 4
  13. 2016Model-Based Iterative Reconstruction for Radial Fast Spin-Echo MRIcited by 3
  14. 2019Echo Planar Time-Resolved Imaging (EPTI) with Subspace Reconstruction and Optimized Spatiotemporal Encodingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Learning Subject-Specific Anatomical Representations via Manifold Expansion: Application to Accelerated Multi-Contrast MRIcited by 0