Enhancing Implicit Neural Representations with Image Feature Embedding for Unsupervised Cardiac Cine MRI Reconstruction

A Bilevel Sensitivity-Corrected Reconstruction Framework with Deep Priors for Parallel MRI

A model-driven bilevel optimization framework that couples SENSE-based image reconstruction with SPIRiT-based k-space calibration through shared CSMs, and introduces a deep-prior-guided regularization strategy that preserves the structure of classical linear regularizers while adaptively learning spatially varying regularization weights from denoised intermediate reconstructions.

Optimized Multi-Contrast Self-Supervised MRI Reconstruction Using Learned K-Space Partitioning

Objective: Deep Learning has shown promise in accelerating MRI by reconstructing high-quality images from under-sampled data. While recent work has leveraged multi-contrast information to improve reconstruction performance, these methods rely on supervised learning, which requires fully sampled k-space for training. One method, self-supervised learning via data undersampling (SSDU), enables direct training on under-sampled k-space by partitioning it into two sets, with a network mapping between the two. In this work, we improve MRI self-supervised MRI reconstruction with two modifications. Methods: We propose a multi-contrast self-supervised learning framework that jointly trains on multiple under-sampled contrasts without requiring fully sampled k-space data as a reference. Moreover, we learn an optimal self-supervised data partitioning for each contrast in an end-to-end manner, further enhancing reconstruction quality. Specifically, we learn an optimal partitioning probability distribution, which is sampled to generate a mask for partitioning. Results: Experiments on two publicly available multi-contrast MRI datasets demonstrate the improved reconstruction quality of our proposed self-supervised multi-contrast learned partitioning method compared to the current single-contrast self-supervised learning methods. We also demonstrate that learning the partitioning of k-space data further enhances the fidelity of reconstructions. Conclusion: Multi-contrast reconstruction combined with learned partitioning improves reconstruction fidelity over single-contrast self-supervised MRI reconstructions. Significance: Our method can facilitate higher image fidelity and/or accelerated MRI protocol times compared to previous self-supervised methods, and without requiring fully sampled k-space for training.

Reverse Imaging: Any-Sequence Generalization for Cardiac MRI Segmentation.

Pretrained segmentation models for cardiac magnetic resonance imaging (MRI) often fail to generalize across imaging sequences due to substantial contrast variations. These variations arise from different imaging protocols, yet fundamentally, all contrasts are governed by the same underlying tissue properties, primarily captured by three components: the magnetization strength (M0), T1, and T2. Building on this insight, we introduce Reverse Imaging, a physics-driven framework for data augmentation and domain generalization in cardiac MRI. Our method infers tissue properties from observed MR images with annotation by solving an ill-posed nonlinear inverse problem, regularized by a generative prior. The prior is learned from the multiparametric saturation-recovery single shot acquisition (mSASHA) dataset for joint cardiac T1 and T2 mapping. In inference, we characterize imaging sequences as weak, moderate, or strong observations according to the physical information they provide and the degree of ill-posedness. This motivates an iterative prior-learning strategy that uses moderate T1-mapping observations to alleviate mSASHA data scarcity via pseudo tissue-property estimates. We further integrate MRI physics into posterior inference by expressing the sequence model as a likelihood term guiding the reverse diffusion process. For widely used but weak cine observations, we develop a sequence-specific ControlNet to improve efficiency and spatial consistency. Extensive experiments on eight unseen cardiac MRI sequences with markedly different contrast mechanisms show that Reverse Imaging yields plausible tissue-property estimates, supports synthesis of diverse yet physically consistent contrasts, and improves segmentation robustness under severe cross-sequence shifts.

A cross-domain deep learning framework with graph CNN extrapolation for MRI reconstruction

Cardiac MRI Reconstruction Using Diffusion Priors and Multi-Scale Transformer-Based Feature Modeling.

The advancement of Healthcare 4.0 has driven a growing demand for intelligent cardiac magnetic resonance imaging (MRI) reconstruction to support precision diagnosis and treatment. Currently, while Transformer based reconstruction methods can effectively capture global dependencies in images, they still have some limitations: insufficient high-frequency detail recovery, inconsistent reconstructed structures under undersampling, and poor model interpretability. These issues affect their re liability and practicality in real-world clinical scenarios. This paper proposes a diffusion-based multi-scale feature fusion transformer (DMFT) for cardiac MRI reconstruction, aiming to balance reconstruction accuracy and efficiency. DMFT introduces a compact diffusion latent prior, enhancing the recovery of fine anatomical structures in just eight diffusion iterations. We embed the proposed multi-scale feature fusion (MsFF) module into the Transformer back bone network to further improve feature representation, achieving effective interaction between the latent prior and image features at different spatial scales. This design helps improve the recovery of local details while maintaining global anatomical consistency. The proposed method was evaluated on both the CMR×Recon benchmark dataset and an in-house cardiac MRI dataset. Experimental results at four different acceleration factors show that DMFT consistently achieves superior reconstruction performance com pared to several representative methods. DMFT particularly achieves significant improvements in PSNR, SSIM, and NMSE at 8x and 10x acceleration factors without introducing excessive computational overhead. These results indicate that DMFT provides a promising framework for accurate and efficient cardiac MRIreconstruction, and structure aware prior guidance offers additional interpretability support in Healthcare 4.0 scenarios.

Contrastive Joint-Embedding Prediction for Representation Learning in Structural MRI

Self-supervised learning offers a compelling approach for medical imaging, where labeled data are scarce and acquisition costs are high. We present COJEPA, a self-supervised framework for volumetric brain MRI that combines a joint-embedding predictive architecture (JEPA) with a contrastive loss (CO), targeting two complementary properties: local predictivity and global discriminability. The model is trained without labels on T1-weighted structural MRI from two cohorts (HCP-YA and AABC, $N{=}2286$, ages 22 to 90), extending I-JEPA to 3D with foreground-aware block masking, a hierarchical convolutional patch embedding, and world-space sinusoidal positional encodings. We evaluate all three objectives across zero-shot twin retrieval, brain tumor segmentation (BraTS 2024), and age regression (OpenBHB). COJEPA achieves the best monozygotic twin recall at rank@1 (0.84), the best finetuning age MAE (2.55 years on OpenBHB 3.0T), and matches CO on BraTS whole-tumor Dice, demonstrating that the combined objective yields representations that are simultaneously discriminative and locally structured.