Aug 2026· IEEE Transactions on Medical Imaging· Vol PP, pp. 1-1· 0 citations
Medicine
TL;DR
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.
Abstract
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.
Cardiac magnetic resonance (CMR) imaging provides complementary information on cardiac anatomy, function, and tissue characterization across multiple sequences and views. In this work, we investigate foundation model pretraining for 2D CMR and introduce CMRVision, a CMR-specific foundation model trained using DINOv3-style self-supervised learning on a multi-center, multi-sequence cohort of 36 million CMR images. We systematically evaluate architectural and training design choices for domain-specific pretraining. CMRVision is evaluated on two downstream tasks: multi-task segmentation across cine, late gadolinium enhancement (LGE), and mapping sequences, and cine view classification. Our experiments show that CMR-specific pretraining, smaller patch sizes, and patch-level objectives consistently improve downstream performance. Across a multi-task segmentation benchmark, CMRVision achieved the strongest overall performance, outperforming prior natural-image (NI), medical-image, supervised, and CMR foundation model baselines. Improvements were modest but consistent across structures and sequences, with Dice scores ranging from 0.940-0.967 for LV and 0.855-0.905 for myocardium, and reaching 0.929 for RV, 0.920 for LA, and 0.931 for RA. The largest gains were observed for myocardium segmentation in LGE and mapping images. In a zero-shot segmentation task on unseen LGE long-axis views, the model achieved an average Dice score of 0.692, demonstrating cross-view generalization. For cine view classification, CMRVision achieved the highest average accuracy (0.906), compared to prior methods reported in the literature. These results highlight the potential of CMRVision to support robust and generalizable cardiac MRI analysis across multiple sequences and views.
Athira J. Jacob, Puneet Sharma, D. Rueckert· 0 citations
Cardiac magnetic resonance imaging (CMR) produces rich sequential data such as temporal cine videos and spatial LGE/mapping stacks, yet most deep learning approaches process individual 2D slices, discarding this context. We present MR-JEPA, a self-supervised video foundation model for CMR that extends LeJEPA to 3D spatiotemporal inputs through tubelet tokenization, spatiotemporal masking augmentation, and initialization from a 2D CMR foundation model. Unlike prior CMR video models limited to cine data, MR-JEPA is pretrained on multi-sequence data (cine, LGE, mapping) from 10,505 patients across two centers without annotations. We evaluate the frozen encoder on six downstream tasks using a unified multi-view gated attention architecture: LV ejection fraction, RV ejection fraction, three myocardial strains (GLS, GCS, GRS), and four-class disease detection. MR-JEPA outperforms other compared methods on all five regression tasks, including both a domain-specific CMR model pretrained on more data with text supervision and a natural-video foundation model, achieving an LV EF MAE of 4.79% (r =0.764) and a GLS MAE of 1.87 (r=0.805), with 21-27% MAE reductions over baselines on strain tasks. For disease detection, MR-JEPA achieved a macro AUG of 0.868, remaining competitive with the domain-specific baseline despite using a fully self-supervised pretraining objective. These results demonstrate the potential of a unified video encoder for robust, multi-view utilization of diverse CMR sequences in clinical cardiac quantification and diagnosis.
Athira J. Jacob, Puneet Sharma, D. Comaniciu et al.· 0 citations
Cardiac magnetic resonance imaging (MRI) plays a critical role in diagnosing cardiovascular diseases; however, acquiring large, annotated datasets remains a significant challenge due to ethical, economic, and logistical constraints. In this paper, we propose a generative framework based on diffusion models for the controllable synthesis of anatomically consistent cardiac MRI scans with corresponding segmentation labels. Our approach combines Low-Rank Adaptation (LoRA) to generate pathology-aware label maps from textual prompts, and ControlNet to guide image synthesis using both semantic and spatial conditioning. This enables the creation of a fully annotated synthetic dataset aligned with cardiac pathologies and phases, supporting supervised training of segmentation models without additional manual labeling. We evaluate the proposed framework in terms of image realism using Fréchet Inception Distance (FID), Kernel Inception Distance (KID), and Fréchet Radiomic Distance (FRD), as well as downstream segmentation performance using a SegFormer model trained on real, synthetic, and combined datasets. Results show that the proposed method improves segmentation accuracy, particularly in data-limited settings. Beyond in-domain evaluation on the ACDC dataset, cross-dataset experiments on the multi-center M&Ms cohort demonstrate improved generalization and robustness to domain shifts. These findings highlight the potential of text-guided diffusion pipelines to generate high-quality, semantically consistent medical imaging data for robust and generalizable AI training.
H. Fouadi, M. Kas, Y. Ruichek et al.· Computerized Medical Imaging...· 0 citations
Whole-heart segmentation from CT and MRI is essential for quantitative cardiac image analysis, but remains challenging under multi-center and multi-modality distribution shift. In the CARE whole-heart segmentation task, models must generalize from limited labeled sites to unseen acquisition distributions, where variation in spacing, intensity, reconstruction texture, and anatomy can degrade out-of-distribution performance. We propose a modality-routed 3D cardiac segmentation pipeline that combines TotalSegmentator-initialized nnU-Netv2 models with site-characterized, label-preserving appearance augmentation. We first characterize the available sites using measurable image properties and use this analysis to motivate candidate data-space generalization routes. The final retained recipe applies Bias Field + Bezier appearance augmentation, combining smooth spatial intensity perturbation with nonlinear intensity remapping, followed by lightweight class-wise largest-connected-component cleanup. On the primary held-out-site validation splits, the final configuration improves CT mean Dice from 0.8350 to 0.9135 and MRI mean Dice from 0.7695 to 0.7830, while also reducing HD95. These results suggest that site-motivated appearance augmentation is a practical strategy for improving cross-site robustness in limited-data whole-heart segmentation. Our code can be found in https://github.com/Purdue-M2/Improving-Cross-Site-Whole-Heart-Segmentation
Tanishqua H Mudaliar, Justin Li, Daniel Lin et al.· 0 citations
Experimental results across several CT inverse problem settings show that Flow Matching-based approaches consistently outperform diffusion-based methods in terms of PSNR, SSIM, and perceptual quality, while requiring fewer sampling steps.
Brain tumor segmentation in magnetic resonance imaging (MRI) is a critical task for diagnosis and treatment planning. Despite the success of deep learning architectures such as U-Net and its variants, performance degradation across datasets remains a major challenge, particularly under domain shift and limited annotated data. To address this issue, this study systematically evaluates how individual MRI sequences influence model robustness across two well-known datasets. A ResUNet-based framework is employed, where each modality is trained independently to isolate its effect under a controlled cross-dataset evaluation protocol with tumor size stratification, without target-domain training, or with limited domain adaptation. Results show that the T2f/FLAIR sequence achieves the best cross-dataset performance, with Dice scores exceeding 75%. It consistently outperforms other modalities across most tumor size ranges, while multi-sequence training further improves performance. Additionally, even limited target-domain adaptation yields rapid initial gains, reducing the need for extensive annotations and costly retraining. Our source code is publicly available at https://github.com/henrique-zan/brain_tumor_segmentation/.
Henrique Zan Grande, João G. Pitol, Lucas B. Schuck et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
