Keywords: AI/ML Image Reconstruction, Visualization, Mid-Field MRI, Denoising

Motivation: Recent advancements in 0.55T MRI systems present promising opportunities for affordable and accessible MRI. Enhancing SNR to mitigate the inherent limitations of mid field strength is a crucial step in advancing this technology.

Goal(s): In this study, we aim to advance 0.55T MRI for speed and quality through a deep-learning-driven general denoise method processing low-SNR scans of various body parts and sequences.

Approach: We constructed a model with a spatial-temporal attention mechanism and employed massive complex image data for training.

Results: The proposed method significantly improves low SNR single-repetition images at 0.55T, making the results comparable or superior to the averages of multi-repetitions.

Impact: With robust denoising on mid-field systems, enhanced image quality and quicker scans can be expected for more accurate diagnoses and improved patient experience. New sequences can be developed and paired to further advance the system.

Keywords: Analysis/Processing, Low-Field MRI, Diffusion-Weighted Imaging

Motivation: Diffusion-weighted imaging (DWI) is crucial for lesion detection but suffers from inherently low signal-to-noise ratio (SNR), especially in low-field settings.

Goal(s): The goal of this work is to accelerate low-field prostate DWI, reducing the number of image repetitions and scan time while maintaining image quality.

Approach: We present a self-supervised denoising method employing Stein's unbiased risk estimator (SURE) and a physics-based noise model and evaluate the denoising results without relying on ground-truth data.

Results: Our method excels in preserving image content, outperforming other denoising techniques. This allows a substantial reduction in scan time, making it a promising advancement in low-field DWI.

Impact: Our proposed denoising approach accelerates low-field prostate DWI via self-supervised denoising, improving scan efficiency without compromising image quality. We further demonstrate how to employ a physics-based noise model to evaluate denoising performance in the absence of noise-free ground-truth data.

Keywords: Analysis/Processing, Machine Learning/Artificial Intelligence, Multi-Atlas Segmentation

Motivation: Multi-atlas segmentation (MAS) of MR brain images with lesions is of great clinical significance but remains challenging due to registration inaccuracy caused by pathologies.

Goal(s): Our goal was to improve the MAS performance of pathological brain images by restoring more accurate normal images form lesion data.

Approach: We integrate a novel subspace-assisted generative model into the MAS framework for estimation of subject-specific posterior normative distribution, which can effectively extract a “hypothetical” normal image from the lesion data, thus enhancing the accuracy of lesion segmentation.

Results: Our method produced significantly improved results in normal recovery and MAS compared to the state-of-the-art methods.

Impact: The proposed method significantly improves the performance of segmentation of MR brain images with lesions, which may provide a useful tool for tissue segmentation in pathological brain images.

Keywords: Analysis/Processing, Brain, Semi-supervised learning

Motivation: Obtaining labeled data for visual pathway (VP) segmentation can be laborious and time-consuming. Therefore, it is crucial to develop algorithms with good performance in situations with limited labeled samples. 

Goal(s): The goal is to propose a label-efficient self-ensembling network (LESEN) for VP segmentation.

Approach: We first introduce the LESEN model which consists of a student model and a teacher model that learn from each other using supervised and unsupervised losses. Additionally, a novel reliable unlabeled sample selection (RUSS) method is introduced to enhance the effectiveness of the LESEN model.

Results: The LESEN model surpasses existing techniques on the human connectome project (HCP) dataset.

Impact: The proposed LESEN model can improve visual pathway segmentation accuracy and reliability with limited labeled data, advancing multi-parametric MRI analysis in clinical and research settings.

Keywords: Analysis/Processing, Quantitative Imaging, Deep Learning, Generalized CNN, R2*, HIC

Motivation: Although R2*-MRI is extensively validated to assess hepatic iron content(HIC), different MRI sequences are used, hence multiple sequence-specific convolutional neural networks(CNNs) have been proposed for automated liver segmentation and HIC estimation.

Goal(s): Assess feasibility of generalized CNN with limited training datasets to automate liver segmentation across various MRI sequences used to quantify HIC in clinical practice.

Approach: Data of twenty-nine patients scanned using multi-echo 2D/3D breath-hold and free-breathing Cartesian and radial GRE sequences were used to train U-Net CNN using incremental learning.

Results: Excellent agreement was obtained between manual and single generalized U-Net for liver segmentation and R2* estimation across multiple MRI sequences.

Impact: Generalized CNN using incremental learning minimizes the need for extensive training datasets to segment liver across multiple MRI sequences. With additional fine-tuning and validation, this approach can be widely applicable for sequence-independent liver segmentation and assessment of hepatic iron content.

Keywords: Analysis/Processing, Segmentation, Vessel wall imaging, intracranial calcification, multimodal fusion

Motivation: Recently, MRI-based intracranial arterial calcification segmentation has got increasing interest due to its clinical value, but current approaches to this challenging problem suffer from poor performance.

Goal(s): To develop a deep learning model for enhancing calcification segmentation on MRI by using CT as additional training resource.

Approach: A dissimilarity loss is proposed to align the latent features learned from MRI and CT of the same subject, thus making MR feature simpler and it easier for segmentation.

Results: Compared with several commonly used segmentation networks, our model demonstrates superior performance in calcification segmentation. The ablation study further shows the effectiveness of the dissimilarity loss.

Impact: The proposed model could be applied in clinical scenarios to automatically segment calcification on cerebral MR scans and it does not require CT imaging. Radiologists could leverage the segmentation result in the analysis of various vessel plaque components.

Keywords: Analysis/Processing, Segmentation, Fetal Brain MRI; Artificial Intelligence

Motivation: Automatic segmentation of fetal brain remains challenging partially due to the dynamically changing anatomical structures during fetal brain development.

Goal(s): To enhance segmentation accuracy through incorporating gestational age-specific information as a guidance, we introduce AtlasSeg, a dual-U-shape network with dense attentive interactions.

Approach: By providing atlas volume and segmentation label at the corresponding gestational age, AtlasSeg effectively extracts the contextual features of age-specific patterns and structures that assist segmentations.

Results: AtlasSeg demonstrated superior performance against six other segmentation networks in both standard and out-of-distribution experiments, in two fetal MRI datasets. Ablation tests further demonstrated the role of atlas guidance.

Impact: Through gestational age-specific atlas-guided information, AtlasSeg can serve as an accurate and robust automatic segmentation tool for its superior performance in both in-distribution and out-of-distribution tests, which is useful for quantitative analysis in large-scale fetal brain studies.

Keywords: Analysis/Processing, Focused Ultrasound, UTE MRI, image guided therapy

Motivation: There’s a clinical interest in exploring  an alternative option using ultrashort-time-echo MRI to replace CT imaging for accurate transcranial FUS treatment planning.

Goal(s): To employ a deep learning approach to generate synthetic CT images from a limited UTE-MRI dataset.

Approach: A deep learning framework based on 3D Transformer U-net is applied to the paired UTE-CT dataset and acoustic simulation is performed to validate the results.

Results: Utilizing UTE MRI can offer synthetic CT as an alternative to traditional CT imaging. The simulations showed a minimal maximum acoustic pressure difference of less than8% and a focus shift of less than1.5mm compared to CT-based simulations.

Impact: This study introduces a novel multi-task deep learning approach that enables accurate synthetic CT generation from limited UTE-MRI data. This innovation provides a cost-effective and radiation-free alternative to traditional CT imaging, significantly enhancing transcranial focused ultrasound treatment planning.

Keywords: AI/ML Image Reconstruction, Liver

Motivation: Hepatobiliary phase (HBP) has important clinical diagnostic value for liver diseases, but its long acquisition time can pose issues with scanning resources and patient cooperation.

Goal(s): Our goal was to design a generative model for HBP synthesis based on early phases in hepatobiliary-specific contrast-enhanced MRI.

Approach: We proposed a multi-task learning deep learning model and evaluated its performance on a multi-center dataset.

Results: The proposed model exhibited superior HBP synthesis performance compared to the classic Pix2Pix model. The synthetic HBP was comparable to the real HBP, and significantly outperformed early phases in subsequent liver fibrosis grading tasks.

Impact: The proposed approach has the potential to accurately synthesize HBP, which is expected to be extended to clinical practice for rapid acquisition of HBP in hepatobiliary-specific contrast-enhanced MRI, thereby significantly reducing scanning time and alleviating clinical stress.

Keywords: Analysis/Processing, Artifacts, Metal implants, simulation, augmentation

Motivation: AI medical imaging solutions are impacted by the presence metal implants and a design of appropriate synthesis method can improve robustness of DL models.  

Goal(s): Simulation of  patient medical condition like metal artifacts in MRI medical images.

Approach: The proposed method blends regions from template images containing metal artifacts into target images by using metal segmentation mask for selection, blending this region into a chosen target image RoI .

Results: Improvement in knee classification accuracy of 8% and decrease in spine plane distance error by 25-40% and plane angle error by 4-30% using the proposed approach.

Impact: A data adaptive metal simulation method in semantically relevant regions in anatomy ensures robust of DL models in patients with metal implants who hitherto would not have benefitted from AI driven tasks .