Pretrained segmentation models for cardiac magnetic resonance imaging (MRI) struggle to generalize across different imaging sequences due to significant variations in image contrast. These variations arise from changes in imaging protocols, yet the same fundamental spin properties, including proton density, T₁, and T₂ values, govern all acquired images. With this core principle, we introduce Reverse Imaging, a novel physics-driven method for cardiac MRI data augmentation and domain adaptation to fundamentally solve the generalization problem. Our method reversely infers the underlying spin properties from observed cardiac MRI images, by solving ill-posed nonlinear inverse problems regularized by the prior distribution of spin properties. We acquire this “spin prior” by learning a generative diffusion model from the multiparametric SAturation-recovery single-SHot acquisition sequence (mSASHA) dataset, which offers joint cardiac T₁ and T₂ maps. Our method enables approximate but meaningful spin-property estimates from MR images, which provide an interpretable “latent variable” that lead to highly flexible image synthesis of arbitrary novel sequences. We show that Reverse Imaging enables highly accurate segmentation across vastly different image contrasts and imaging protocols, realizing wide-spectrum generalization of cardiac MRI segmentation.

In this work, we aimed to develop and evaluate multi-band outer volume suppression pulses for increased acceleration rates in simultaneous multi-slice accelerated cardiac MRI. MB-OVS pulses were constructed from a multi-band combination of two slab-selective saturation pulses and tested for various pulse shapes using Bloch simulation and phantom experiment. The MB-OVS pulses were interleaved between imaging pulses to ensure homogeneous suppression throughout the cardiac cycle/imaging window in vivo. Simultaneous multi-slice (SMS) CINE and first-pass myocardial perfusion scans with and without the proposed MB-OVS pulses were compared in terms of residual artifacts at high acceleration rates. Among the tested pulses, both Bloch simulation and phantom experiments showed that amplitude-optimized sinc pulses provided the best trade-off in suppression efficiency, the required B+ 1 , SAR, and slab profile. CINE imaging with 5-fold SMS-OVS acceleration significantly outperformed imaging without MB-OVS, maintaining leakage-free image quality, even when adding 2-fold in-plane acceleration. SMS-OVS also enabled perfusion imaging in 9 slices with 1.7 × 1.7 mm2 resolution, achieving a 16-fold spatial-only acceleration while ensuring accurate contrast dynamics without leakage artifacts. Interleaved MB-OVS modules enabled thorough leakage artifact suppression in cardiac SMS-accelerated CINE and perfusion imaging, particularly at high acceleration rates. The proposed approach may be promising for unlocking further acceleration potential of SMS in cardiac imaging.

Deformable medical image registration is traditionally formulated as an optimization problem. While classical methods solve this problem iteratively, recent learning-based approaches use weight-tied neural networks to mimic this process by unrolling the prediction of deformation fields in a fixed number of steps. However, classical methods typically converge after sufficient iterations, but learning-based unrolling methods lack a theoretical convergence guarantee and show instability empirically. In addition, unrolling methods have a practical bottleneck at training time: GPU memory usage grows linearly with the unrolling steps due to backpropagation through time (BPTT). To address both theoretical and practical challenges, we propose DEQReg, a novel registration framework based on Deep Equilibrium Models (DEQ), which formulates registration as an equilibrium-seeking problem, establishing a natural connection between classical optimization and learning-based unrolling methods. DEQReg maintains constant memory usage, enabling theoretically unlimited iteration steps. Through extensive evaluation on the public brain MRI and lung CT datasets, we show that DEQReg can achieve competitive registration performance, while substantially reducing memory consumption compared to state-of-the-art unrolling methods. We also reveal an intriguing phenomenon: the performance of existing unrolling methods first increases slightly then degrades irreversibly when the inference steps go beyond the training configuration. In contrast, DEQReg achieves stable convergence with its inbuilt equilibrium-seeking mechanism, bridging the gap between classical optimization-based and modern learning-based registration methods.

Spin-lattice relaxation time (T1) is an important biomarker in cardiac parametric mapping for characterizing myocardial tissue and diagnosing cardiomyopathies. Conventional Modified Look-Locker Inversion Recovery (MOLLI) acquires 11 breath-hold baseline images with interleaved rest periods to ensure mapping accuracy. However, prolonged scanning can be challenging for patients with poor breathholds, often leading to motion artifacts that degrade image quality. In addition, T1 mapping requires a voxel-wise nonlinear fitting to a signal recovery model involving an iterative estimation process. Recent studies have proposed deep-learning approaches for rapid T1 mapping using shortened sequences to reduce acquisition time for patient comfort. Nevertheless, existing methods overlook important physics constraints, limiting interpretability and generalization. In this work, we present an accelerated, end-to-end T1 mapping framework leveraging Physics-Informed Neural Ordinary Differential Equations (ODEs) to model temporal dynamics and address these challenges. Our method achieves high-accuracy T1 estimation from a sparse subset of baseline images and ensures efficient null index estimation at the test time. Specifically, we develop a continuous-time LSTM-ODE model to enable selective Look-Locker (LL) data acquisition with arbitrary time lags. Experimental results show superior performance in T1 estimation for both native and post-contrast sequences and demonstrate the strong benefit of our physics-based formulation over direct data-driven T1 priors.

Cardiac magnetic resonance imaging (MRI) provides detailed and quantitative evaluation of the heart’s structure, function, and tissue characteristics with high-resolution spatial–temporal imaging. However, its slow imaging speed and motion artifacts are notable limitations. Undersampling reconstruction, especially data-driven algorithms, has emerged as a promising solution to accelerate scans and enhance imaging performance using highly under-sampled data. Nevertheless, the scarcity of publicly available cardiac k-space datasets and evaluation platform hinder the development of data-driven reconstruction algorithms. To address this issue, we organized the Cardiac MRI Reconstruction Challenge (CMRxRecon) in 2023, in collaboration with the 26th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI). CMRxRecon presented an extensive k-space dataset comprising cine and mapping raw data, accompanied by detailed annotations of cardiac anatomical structures. With overwhelming participation, the challenge attracted more than 285 teams and over 600 participants. Among them, 22 teams successfully submitted Docker containers for the testing phase, with 7 teams submitted for both cine and mapping tasks. All teams use deep learning based approaches, indicating that deep learning has predominately become a promising solution for the problem. The first-place winner of both tasks utilizes the E2E-VarNet architecture as backbones. In contrast, U-Net is still the most popular backbone for both multi-coil and single-coil reconstructions. This paper provides a comprehensive overview of the challenge design, presents a summary of the submitted results, reviews the employed methods, and offers an in-depth discussion that aims to inspire future advancements in cardiac MRI reconstruction models. The summary emphasizes the effective strategies observed in Cardiac MRI reconstruction, including backbone architecture, loss function, pre-processing techniques, physical modeling, and model complexity, thereby providing valuable insights for further developments in this field.

Image registration is essential for medical image applications where alignment of voxels across multiple images is needed for qualitative or quantitative analysis. With recent advances in deep neural networks and parallel computing, deep learning-based medical image registration methods become competitive with their flexible modeling and fast inference capabilities. However, compared to traditional optimization-based registration methods, the speed advantage may come at the cost of registration performance at inference time. Besides, deep neural networks ideally demand large training datasets while optimization-based methods are training-free. To improve registration accuracy and data efficiency, we propose a novel image registration method, termed Recurrent Inference Image Registration (RIIR) network. RIIR is formulated as a meta-learning solver for the registration problem in an iterative manner. RIIR addresses the accuracy and data efficiency issues, by learning the update rule of optimization, with implicit regularization combined with explicit gradient input.

We extensively evaluated RIIR on brain MRI, lung CT, and quantitative cardiac MRI datasets, in terms of both registration accuracy and training data efficiency. Our experiments showed that RIIR outperformed a range of deep learning-based methods, even with only 5% of the training data, demonstrating high data efficiency. Key findings from our ablation studies highlighted the important added value of the hidden states introduced in the recurrent inference framework for meta-learning. Our proposed RIIR offers a highly data-efficient framework for deep learning-based medical image registration.

Accurate biventricular segmentation of cardiac magnetic resonance (CMR) cine images is essential for the clinical evaluation of heart function. However, compared to left ventricle (LV), right ventricle (RV) segmentation is still more challenging and less reproducible. Degenerate performance frequently occurs at the RV base, where the in-plane anatomical structures are complex (with atria, valve, and aorta) and vary due to the strong interplanar motion. In this work, we propose to address the currently unsolved issues in CMR segmentation, specifically at the RV base, with two strategies: first, we complemented the public resource by reannotating the RV base in the ACDC dataset, with refined delineation of the right ventricle outflow tract (RVOT), under the guidance of an expert cardiologist. Second, we proposed a novel dual encoder U-Net architecture that leverages temporal incoherence to inform the segmentation when interplanar motions occur. The inter-planar motion is characterized by loss-of-tracking, via Bayesian uncertainty of a motion-tracking model. Our experiments showed that our method significantly improved RV base segmentation taking into account temporal incoherence. Furthermore, we investigated the reproducibility of deep learning-based segmentation and showed that the combination of consistent annotation and loss of tracking could enhance the reproducibility of RV segmentation, potentially facilitating a large number of clinical studies focusing on RV.

Purpose: Evaluate the feasibility of quantification of Relaxation Along a Fictitious Field in the 2nd rotating frame (RAFF2) relaxation times in the human myocardium at 3 T.

Methods: TRAFF2 mapping was performed using a breath-held ECG-gated acquisition of five images: one without preparation, three preceded by RAFF2 trains of varying duration, and one preceded by a saturation prepulse. Pixel-wise TRAFF2 maps were obtained after three-parameter exponential fitting. The repeatability of TRAFF2, T1, and T2 was assessed in phantom via the coefficient of variation (CV) across three repetitions. In seven healthy subjects, TRAFF2 was tested for precision, reproducibility, inter-subject variability, and image quality (IQ) on a Likert scale (1 = Nondiagnostic, 5 = Excellent). Additionally, TRAFF2 mapping was performed in three patients with suspected cardiovascular disease, comparing it to late gadolinium enhancement (LGE), native T1, T2, and ECV mapping.

Results: In phantom, TRAFF2 showed good repeatability (CV < 1.5%) while showing no (R2=0.09) and high (R2=0.99) correlation with T1 and T2, respectively. Myocardial TRAFF2 maps exhibited overall acceptable image quality (IQ = 3.0±1.0) with moderate artifact levels, stemming from off-resonances near the coronary sinus. Average TRAFF2 time across subjects and repetitions was 79.1 ± 7.3 ms. Good precision (7.6 ± 1.4%), reproducibility (1.0 ± 0.6%), and low inter-subject variability (10.0 ± 1.8%) were obtained. In patients, visual agreement of the infarcted area was observed in the TRAFF2 map and LGE.

Conclusion: Myocardial TRAFF2 quantification at 3 T was successfully achieved in a single breath-hold with acceptable image quality, albeit with residual off-resonance artifacts. Nonetheless, preliminary clinical data indicate potential sensitivity of TRAFF2 mapping to myocardial infarction detection without the need for contrast agents, but off-resonance artifacts mitigation warrants further investigation.

Quantitative cardiac magnetic resonance imaging (MRI) is an increasingly important diagnostic tool for cardiovascular diseases. Yet, co-registration of all baseline images within the quantitative MRI sequence is essential for the accuracy and precision of quantitative maps. However, co-registering all baseline images from a quantitative cardiac MRI sequence remains a nontrivial task because of the simultaneous changes in intensity and contrast, in combination with cardiac and respiratory motion. To address the challenge, we propose a novel motion correction framework based on robust principle component analysis (rPCA) that decomposes quantitative cardiac MRI into low-rank and sparse components, and we integrate the groupwise CNN-based registration backbone within the rPCA framework. The low-rank component of rPCA corresponds to the quantitative mapping (i.e. limited degree of freedom in variation), while the sparse component corresponds to the residual motion, making it easier to formulate and solve the groupwise registration problem. We evaluated our proposed method on cardiac T1 mapping by the modified Look-Locker inversion recovery (MOLLI) sequence, both before and after the Gadolinium contrast agent administration. Our experiments showed that our method effectively improved registration performance over baseline methods without introducing rPCA, and reduced quantitative mapping error in both in-domain (pre-contrast MOLLI) and out-of-domain (post-contrast MOLLI) inference. The proposed rPCA framework is generic and can be integrated with other registration backbones.

Deep learning-based methods have achieved prestigious performance for magnetic resonance imaging (MRI) reconstruction, enabling fast imaging for many clinical applications. Previous methods employ convolutional networks to learn the image prior as the regularization term. In quantitative MRI, the physical model of nuclear magnetic resonance relaxometry is known, providing additional prior knowledge for image reconstruction. However, traditional reconstruction networks are limited to learning the spatial domain prior knowledge, ignoring the relaxometry prior. Therefore, we propose a relaxometry-guided quantitative MRI reconstruction framework to learn the spatial prior from data and the relaxometry prior from MRI physics. Additionally, we also evaluated the performance of two popular reconstruction backbones, namely, recurrent variational networks (RVN) and variational networks (VN) with U-Net. Experiments demonstrate that the proposed method achieves highly promising results in quantitative MRI reconstruction.

Quantitative T1 mapping by MRI is an increasingly important tool for clinical assessment of cardiovascular diseases. The cardiac T1 map is derived by fitting a known signal model to a series of baseline images, while the quality of this map can be deteriorated by involuntary respiratory and cardiac motion. To correct motion, a template image is often needed to register all baseline images, but the choice of template is nontrivial, leading to inconsistent performance sensitive to image contrast. In this work, we propose a novel deep-learning-based groupwise registration framework, which omits the need for a template, and registers all baseline images simultaneously. We design two groupwise losses for this registration framework: the first is a linear principal component analysis (PCA) loss that enforces alignment of baseline images irrespective of the intensity variation, and the second is an auxiliary relaxometry loss that enforces adherence of intensity profile to the signal model. We extensively evaluated our method, termed “PCA-Relax”, and other baseline methods on an in-house cardiac MRI dataset including both pre- and post-contrast T1 sequences. All methods were evaluated under three distinct training-and-evaluation strategies, namely, standard, one-shot, and test-time-adaptation. The proposed PCA-Relax showed further improved performance of registration and mapping over well-established baselines. The proposed groupwise framework is generic and can be adapted to applications involving multiple images.

Purpose: The aim of this study is to develop and optimize an adiabatic (Formula presented.) ((Formula presented.)) mapping method for robust quantification of spin-lock (SL) relaxation in the myocardium at 3T. Methods: Adiabatic SL (aSL) preparations were optimized for resilience against (Formula presented.) and (Formula presented.) inhomogeneities using Bloch simulations. Optimized (Formula presented.) -aSL, Bal-aSL and (Formula presented.) -aSL modules, each compensating for different inhomogeneities, were first validated in phantom and human calf. Myocardial (Formula presented.) mapping was performed using a single breath-hold cardiac-triggered bSSFP-based sequence. Then, optimized (Formula presented.) preparations were compared to each other and to conventional SL-prepared (Formula presented.) maps (RefSL) in phantoms to assess repeatability, and in 13 healthy subjects to investigate image quality, precision, reproducibility and intersubject variability. Finally, aSL and RefSL sequences were tested on six patients with known or suspected cardiovascular disease and compared with LGE, (Formula presented.), and ECV mapping. Results: The highest (Formula presented.) preparation efficiency was obtained in simulations for modules comprising 2 HS pulses of 30 ms each. In vivo (Formula presented.) maps yielded significantly higher quality than RefSL maps. Average myocardial (Formula presented.) values were 183.28 (Formula presented.) 25.53 ms, compared with 38.21 (Formula presented.) 14.37 ms RefSL-prepared (Formula presented.). (Formula presented.) maps showed a significant improvement in precision (avg. 14.47 (Formula presented.) 3.71% aSL, 37.61 (Formula presented.) 19.42% RefSL, p < 0.01) and reproducibility (avg. 4.64 (Formula presented.) 2.18% aSL, 47.39 (Formula presented.) 12.06% RefSL, p < 0.0001), with decreased inter-subject variability (avg. 8.76 (Formula presented.) 3.65% aSL, 51.90 (Formula presented.) 15.27% RefSL, p < 0.0001). Among aSL preparations, (Formula presented.) -aSL achieved the better inter-subject variability. In patients, (Formula presented.) -aSL preparations showed the best artifact resilience among the adiabatic preparations. (Formula presented.) times show focal alteration colocalized with areas of hyper-enhancement in the LGE images. Conclusion: Adiabatic preparations enable robust in vivo quantification of myocardial SL relaxation times at 3T.

The self-configuring nnU-Net has achieved leading performance in a large range of medical image segmentation challenges. It is widely considered as the model of choice and a strong baseline for medical image segmentation. However, despite its extraordinary performance, nnU-Net does not supply a measure of uncertainty to indicate its possible failure. This can be problematic for large-scale image segmentation applications, where data are heterogeneous and nnU-Net may fail without notice. In this work, we introduce a novel method to estimate nnU-Net uncertainty for medical image segmentation. We propose a highly effective scheme for posterior sampling of weight space for Bayesian uncertainty estimation. Different from previous baseline methods such as Monte Carlo Dropout and mean-field Bayesian Neural Networks, our proposed method does not require a variational architecture and keeps the original nnU-Net architecture intact, thereby preserving its excellent performance and ease of use. Additionally, we boost the segmentation performance over the original nnU-Net via marginalizing multi-modal posterior models. We applied our method on the public ACDC and M &M datasets of cardiac MRI and demonstrated improved uncertainty estimation over a range of baseline methods. The proposed method further strengthens nnU-Net for medical image segmentation in terms of both segmentation accuracy and quality control.

Quantitative MRI (qMRI) of the heart has become an important clinical tool for examining myocardial tissue properties. Because heart is a moving object, it is usually imaged with electrocardiogram and respiratory gating during acquisition, to “freeze” its motion. In reality, gating is more-often-than-not imperfect given the heart rate variability and nonideal breath-hold. qMRI of the heart, consequently, is characteristic of varying image contrast as well as residual motion, the latter compromising the quality of quantitative mapping. Motion correction is an important step prior to parametric mapping, however, a long-standing difficulty for registering the dynamic sequence is that the contrast across frames varies wildly: depending on the acquisition scheme some frames can have extremely poor contrast, which fails both traditional optimization-based and modern learning-based registration methods. In this work, we propose a novel framework named DisQ, which Disentangles Quantitative mapping sequences into the latent space of contrast and anatomy, fully unsupervised. The disentangled latent spaces serve for the purpose of generating a series of images with identical contrast, which enables easy and accurate registration of all frames. We applied our DisQ method to the modified Look-Locker inversion recovery (MOLLI) sequence, and demonstrated improved performance of T₁ mapping. In addition, we showed the possibility of generating a dynamic series of baseline images with exactly the same shape, strictly registered and perfectly “frozen". Our proposed DisQ methodology readily extends to other types of cardiac qMRI such as T₂ mapping and perfusion.