Keywords: AI Diffusion Models, Image Reconstruction, Low field

Motivation: The high-field-like image reconstruction, mainstream efforts are primarily focused on high or ultra-high fields, lacking in the reconstruction of high-field-like images from low-field ones.

Goal(s): This paper presented a model for reconstructing high-field-like MR images from low-field images with unpaired data.

Approach: we execute a pairing using OT-driven CycleGAN, described as "teacher learning". Subsequently, we use a diffusion model to learn the joint distribution between high-field and low-field images, guiding the reconstruction from low-field to high-field.

Results: The generation experiments of T1W and T2W surpass competing experiments, and the 3-fold acceleration experiment also demonstrates the superiority of the proposed method.

Impact: The proposed method represents the first attempt in the reconstruction (acceleration and generation) of images from low-field to high-field. Its potential benefits for advancing overall healthcare standards could be significant.

Keywords: AI/ML Image Reconstruction, Machine Learning/Artificial Intelligence, perfusion

Motivation: Cardiac perfusion imposes challenges in reconstruction due to intrinsic low SNR, and large signal intensity change. Recently proposed Conditional Denoising Diffusion Probabilistic Models (DDPM) achieves exceptional performance in a broad range of inverse problems.

Goal(s): To reconstruct undersampled cardiac perfusion datasets with conditional DDPM.

Approach: We conduct the Langevin diffusion process on unacquired k-space data. Conditioning on the acquired data is explicitly embedded in the network structure, instead of utilizing Bayes rule to decouple learned unconditional DDPM prior information of perfusion images and MRI sensing model.

Results: Our experimental results validate the good performance of conditional DDPM reconstruction for R=4 accelerated perfusion imaging.

Impact: Our proposed work can help the challenging perfusion reconstruction for higher acceleration rate and benefit clinical diagnosis.

Keywords: AI Diffusion Models, Hyperpolarized MR (Gas)

Motivation: HP ¹²⁹Xe MRI is remarkably beneficial for investigating structural and functional abnormalities in COPD. Typical VDP calculation methods are based on semi-automatic segmentation to quantify ventilation images, such as k-means. They are highly influenced by image noise and artificial thresholds.

Goal(s): Our goal was to improve the accuracy of automatic segmentation-based VDP on different signal-to-noise ratio images with a small amount of training dataset.

Approach: We proposed a conditional diffusion probabilistic model for thoracic cavity mask and ventilation mask segmentation.

Results: This model can preferably segment the target mask, calculate the VDP, and maintain high robustness compared to other methods.

Impact: Our proposed conditional diffusion probabilistic model can preferably automatically segment the thoracic cavity mask and ventilation mask. It can calculate a more accurate VDP, which allows physicians to better evaluate ¹²⁹Xe ventilation images.

Keywords: AI Diffusion Models, Machine Learning/Artificial Intelligence

Motivation: Diffusion model (DM)-based methods demonstrate competitive performance in solving medical imaging inverse problems. However, it remains uncertain whether these methods are vulnerable to distribution shifts, a common issue in traditional learning-based approaches.

Goal(s): Our goal is to conduct experiments to evaluate how well DM-based methods handle distribution shifts in various scenarios. 

Approach: We utilize three different sampling methods based on a pretrained Diffusion model and apply them to four clinical tasks without fine-tuning.

Results: Experiments indicate that DM-based methods efficiently address distribution shifts without requiring fine-tuning. They exhibit robustness to many distribution shifts, even when the test data deviates from the training data.

Impact: DM-based methods reduce resource consumption and the need for extensive training datasets, potentially inspiring further development of DM-based techniques for enhancing in-vivo tasks with limited resources.

Keywords: AI Diffusion Models, Arrhythmia, Non-cartesian sampling, radial

Motivation: Persistent premature ventricular obscure left ventricle (LV) function assessment. Current imaging lacks temporal resolution and methods for effective differentiation of beat morphologies.

Goal(s):  To enhance real-time MRI scans of arrhythmia patients, targeting high temporal resolution for discerning arrhythmia beats.

Approach: We trained an image-domain diffusion model on a public database, optimizing transferability to arrhythmia scans. The model employs prior images during the reverse sampling to impose image-domain constraints.

Results: Achieved a 62% increase in LV signal-to-noise ratio and a 150% increase in LV-to-myocardium contrast-to-noise ratio across 10 real-time scans. Also facilitated direct beat morphology analysis, paving the way for PVC-induced cardiomyopathy studies.

Impact: The trajectory-agnostic diffusion model offers clinicians and patients clearer visualization of real-time arrhythmia scans, potentially assisting the early detection and study of PVC-induced cardiomyopathies. Future research may explore its applicability to other rapid-cycle cardiac phenomena.

Keywords: AI Diffusion Models, Image Reconstruction

Motivation: Although MRI is a powerful medical imaging technique, its utility is limited by its prolonged scan time. Since deep learning methods for reconstructing undersampled MRI haven't achieved rapid and reliable high-resolution results, we investigated diffusion models as a potential solution. 

Goal(s): Improve MRI reconstruction while accelerating the inference process with diffusion model.

Approach: Proposed Patch-based Conditioned Denoising Diffusion Probabilistic Model (PC-DDPM) that predicts the distribution of clean images from noisy input by conditioning on noisy patches.

Results: Experiment result shows PC-DDPM outperforms U-Net, Vision Transformer, and conditioned DDPM by better reconstruction performance and shorter inference time.

Impact: The implementation of patch-based conditioned DDPM for MRI reconstruction can speed up reconstruction and image acquisition while preserving the image quality. Patients could benefit from shorter scan time, and medical facilities could increase the patient throughput. 

Keywords: AI Diffusion Models, Machine Learning/Artificial Intelligence

Motivation: Alzheimer’s Disease Neuroimaging Initiative (ADNI) ASL dataset acquired on Siemens scanners missed M0 images, which prevents CBF quantification for further analysis.

Goal(s): Our goal is to generate the missing M0 for the ADNI ASL dataset using latent diffusion model (LDM).

Approach: A separate training dataset was acquired with the ADNI ASL protocol but with manually disabled background suppression to be used as the M0. A conditional LDM was trained to use acquired control images as the condition to generate M0 images.

Results: The generated M0 with the conditional LDM shows a high fidelity compared to the experimentally acquired M0.

Impact: With generated M0 images, more than 500 ADNI ASL datasets can be further analyzed for CBF to investigate AD progression.

Keywords: AI Diffusion Models, Diffusion Tensor Imaging

Motivation: High-quality diffusion tensor imaging involves fitting a large number of diffusion-encoded images to a tensor model. This challenging process requires long scans and is vulnerable to motion artifacts. There’s a need for accelerated acquisitions while preserving robust diffusion tensor estimates.

Goal(s): To develop a generative diffusion model that produces high-quality tensor metrics using a few diffusion-encoded images.

Approach: The proposed generative model was trained using 300 randomly selected subjects from the Human Connectome Project Dataset and tested on 20 subjects.

Results: Our model demonstrates the ability to generate high-quality tensor metrics for as few as 3 DWIs.

Impact: This study demonstrates that a generative diffusion model can produce high-quality tensor metrics with significant reduction in scan time, potentially eliminating image distortions and artifacts.

Keywords: AI Diffusion Models, Cardiovascular, Myocardial Perfusion MRI

Motivation: Developing deep learning (DL)-based image reconstruction techniques requires raw k-space datasets. The use of magnitude-only MRI images (DICOMs) to obtain k-space can be prohibitive for training robust models.

Goal(s): To synthesize phase-maps of DCE cardiac MRI from magnitude-only images by using the recently emerging diffusion models. 

Approach: A conditional score-based diffusion model (SBDM) is trained to synthesize phase-maps from the magnitude-only images. The value of the synthesized phase-maps is assessed with a DL-based image reconstruction model.

Results: SBDM-derived phase-maps outperformed random and GAN-based phase-map generation methods in terms of reconstruction performance. Qualitative assessment suggests that SBDMs can generate realistic-looking phase-maps.

Impact: We proposed to leverage the emerging generative diffusion models for retrospective phase-map synthesis of DCE cardiac MRI from the magnitude-only images which has the potential to create large k-space datasets using the magnitude-only multi-center registries to improve deep learning-based reconstruction.

Keywords: AI Diffusion Models, Diffusion/other diffusion imaging techniques

Motivation: Diffusion-Weighted Imaging (DWI) suffers from low resolution. Post-acquisition super-resolution can effectively enhance the resolution of DWIs.

Goal(s): We propose a novel post-acquisition DWI super-resolution method based on the conditioned diffusion model.

Approach: We design an effective condition based on Track Density Imaging (TDI), which contains rich high-resolution information. Furthermore, we consider low-resolution DWIs as another condition to preserve the original information of images. 

Results: Extensive experiments on HCP data show that our model is effective in DWI super-resolution and outperforms the cutting-edge models.

Impact: To enhance the resolution of DWIs, we propose a super-resolution method based on conditioned diffusion model. This is beneficial to the clinical practice of DWI.

Keywords: AI Diffusion Models, Machine Learning/Artificial Intelligence

Motivation:  Cardiac cine MRI requires multiple breath-holds to cover the left ventricle. Acquiring images of small matrix size effectively reduces acquisition time but causes a loss of spatial details. 

Goal(s): To further research on the application of diffusion models in accelerating Cardiac cine MRI.  

Approach: A diffusion model was constructed to achieve super-resolution of cardiac cine MRI to restore lost details in low-resolution images.

Results: The proposed diffusion model based super-resolution method can recover high-frequency details for cardiac cine MRI and outperformed the state-of-the-art generative adversarial super-resolution network. 

Impact:  The proposed method yielding good-quality cardiac cine images from low-resolution images helps to accelerate cardiac cine MRI and could be potentially applied to achieve high spatial-temporal real-time cardiac MRI.

Keywords: AI Diffusion Models, Machine Learning/Artificial Intelligence, T1CE, Synthesis

Motivation:  T1W Contrast-enhanced (T1CE) images are obtained with gadolinium administration, but there might be adverse effects related to gadolinium retention.

Goal(s): To generated T1CE images from multi-parametric MRI (mp-MRI) without contrast agents.

Approach:  T1W, T1map, SWI and QSM were obtained from patients with brain metastasis. A novel approach for generating non-contrast enhanced images from mp-MRI was proposed based on the diffusion model, which was trained in 91 cases, evaluated and test 28 and 27 cases respectively.

Results: The proposed model achieves the highest SSIM of 0.78, and the synthetic images are capable of revealing the details of brain tissues.

Impact: Multi-parametric MRI based DDPM provides a feasible approach for generating contrast enhanced images from non-contrast multi-parametric MRI, therefore circumventing the issue of adverse effects of gadolinium retention, which will benefit patients who have to undergo contrast enhanced MRI scans.

Keywords: AI Diffusion Models, Image Reconstruction

Motivation: Medical images in different modalities (MR\PET\CT) can provide different information, which can help to fully understand a patient's condition and assist physicians in making accurate diagnoses and treatment plans. 

Goal(s): Using the diffusion model to generate multiple modal images from a single modality.

Approach: We propose the conditional latent diffusion model (CLDM) guided by category information to address the challenge of completing the target modal image within the same body. 

Results: Compared to images generated by GANs, our model produces higher quality images with enhanced capabilities, particularly in capturing intricate details.

Impact: Our study offers bright future for diffusion models in the complementary field of medical imaging modalities.

Keywords: AI Diffusion Models, fMRI (task based), brain decoding, fMRI

Motivation: Brain decoding has been limited by the need for large data amounts and subject-specific methodologies. Current techniques require extensive scanning, which is costly and time-consuming, restricting their applicability.

Goal(s): The study aims to establish a novel, more efficient approach for cross-subject brain decoding of visual stimuli.

Approach: Using the NSD we applied regularized ridge regression to align brain activity across different subjects on common stimuli representations, employing the state-of-the art Brain-Diffuser pipeline for decoding and image reconstruction.

Results: The ridge regression alignment method surpassed others, enabling consistent cross-subject decoding with significantly reduced data—demonstrating feasibility and a potential 90% scan time reduction.

Impact: A reliable technique for cross-subject, -scanner and -field strength alignment can pave the way for efficient brain decoding without the need for extensive data collection and/or ultra-high field strengths.

Keywords: AI Diffusion Models, Segmentation

Motivation: Glioblastoma, the most prevalent and aggressive adult brain tumor, presents a therapeutic and monitoring challenge due to its diverse morphology and composition.

Goal(s): This study explores the efficacy of utilizing denoising diffusion models with the widely adopted U-Net architecture for enhanced segmentation performance.

Approach: The proposed framework notably improves the segmentation of the tumor, especially the core. This enhancement facilitates an advanced understanding of complex cases and potentially impacts specialist interventions.

Results: Our findings present promising results for further research into more intricate glioblastoma cases, thereby aiding in developing sophisticated, targeted treatment strategies for this disease.

Impact: This study advances U-Net architecture by integrating denoising diffusion models and specialized loss functions, elevating the precision of low-resolution brain tumor segmentation, with an emphasis on balancing improved accuracy against uncertain predictions.

Keywords: AI/ML Image Reconstruction, CEST & MT

Motivation: Chemical exchange saturation transfer (CEST) magnetic resonance (MR) imaging is slow, and rapid radial undersampling significantly compromises the image quality of CEST data.

Goal(s): Our goal is to enhance the image performance of CEST reconstruction under higher radial undersampling.

Approach: A diffusion model is introduced to obtain prior information from MRI data, and its performance is evaluated on CEST data under radial sampling.

Results: The proposed method generated high-quality CEST source images in healthy human data, outperforming iGRASP.

Impact: The proposed method has achieved rapid imaging of CEST data, providing high-quality CEST source images .