Purpose: To develop a free‐running (free‐breathing, retrospective cardiac gating) 3D myocardial T₁ mapping with isotropic spatial resolution.Methods: The free‐running sequence is inversion recovery (IR)‐prepared followed by continuous 3D golden angle radial data acquisition. 1D respiratory motion signal is extracted from the k‐space center of all spokes and used to bin the k‐space data into different respiratory states, enabling estimation and correction of 3D translational respiratory motion, whereas cardiac motion is recorded using electrocardiography and synchronized with data acquisition. 3D translational respiratory motion compensated T₁ maps at diastole and systole were generated with 1.5 mm isotropic spatial resolution with low‐rank inversion and high‐dimensionality patch‐based undersampled reconstruction. The technique was validated against conventional methods in phantom and 9 healthy subjects.Results: Phantom results demonstrated good agreement (R² = 0.99) of T₁ estimation with reference method. Homogeneous systolic and diastolic 3D T₁ maps were reconstructed from the proposed technique. Diastolic septal T₁ estimated with the proposed method (1140 ± 36 ms) was comparable to the saturation recovery single‐shot acquisition (SASHA) sequence (1153 ± 49 ms), but was higher than the modified Look‐Locker inversion recovery (MOLLI) sequence (1037 ± 33 ms). Precision of the proposed method (42 ± 8 ms) was comparable to MOLLI (41 ± 7 ms) and improved with respect to SASHA (87 ± 19 ms).Conclusions: The proposed free‐running whole heart T₁ mapping method allows for reconstruction of isotropic resolution 3D T₁ maps at different cardiac phases, serving as a promising tool for whole heart myocardial tissue characterization.

Non-rigid motion-corrected reconstruction has been proposed to account for the complex motion of the heart in free-breathing 3D coronary magnetic resonance angiography (CMRA). This reconstruction framework requires efficient and accurate estimation of non-rigid motion fields from undersampled images at different respiratory positions (or bins). However, state-of-the-art registration methods can be time-consuming. This paper presents a novel unsupervised deep learning-based strategy for fast estimation of inter-bin 3D non-rigid respiratory motion fields for motion-corrected free-breathing CMRA. The proposed 3D respiratory motion estimation network (RespME-net) is trained as a deep encoder-decoder network, taking pairs of 3D image patches extracted from CMRA volumes as input and outputting the motion field between image patches. Using image warping by the estimated motion field, a loss function that imposes image similarity and motion smoothness is adopted to enable training without ground truth motion field. RespME-net is trained patch-wise to circumvent the challenges of training a 3D network volume-wise which requires large amounts of GPU memory and 3D datasets. We perform 5-fold cross-validation with 45 CMRA datasets and demonstrate that RespME-net can predict 3D non-rigid motion fields with subpixel accuracy (0.44 ± 0.38 mm) within -10 seconds, being -20 times faster than a GPU-implemented state-of-the-art non-rigid registration method. Moreover, we perform non-rigid motion-compensated CMRA reconstruction for 9 additional patients. The proposed RespME-net has achieved similar motion-corrected CMRA image quality to the conventional registration method regarding coronary artery length and sharpness.

In the field of healthcare, the acquisition of sample is usually restricted by multiple considerations, including cost, labor- intensive annotation, privacy concerns, and radiation hazards, therefore, synthesizing images-of-interest is an important tool to data augmentation. Diffusion models have recently attained state-of-the-art results in various synthesis tasks, and embedding energy functions has been proved that can effectively guide the pre-trained model to synthesize target samples. However, we notice that current method development and validation are still limited to improving indicators, such as Fréchet Inception Distance score (FID) and Inception Score (IS), and have not provided deeper investigations on downstream tasks, like disease grading and diagnosis. Moreover, existing classifier guidance which can be regarded as a special case of energy function can only has a singular effect on altering the distribution of the synthetic dataset. This may contribute to in-distribution synthetic sample that has limited help to downstream model optimization. All these limitations remind that we still have a long way to go to achieve controllable generation. In this work, we first conducted an analysis on previous guidance as well as its contributions on further applications from the perspective of data distribution. To synthesize samples which can help downstream applications, we then introduce uncertainty guidance in each sampling step and design an uncertainty-guided diffusion models. Extensive experiments on four medical datasets, with ten classic networks trained on the augmented sample sets provided a comprehensive evaluation on the practical contributions of our methodology. Furthermore, we provide a theoretical guarantee for general gradient guidance in diffusion models, which would benefit future research on investigating other forms of measurement guidance for specific generative tasks. Codes and models are available at: https://github.com/yangqy1110/MGDM