Keywords: Kidney, Kidney

Motivation: To understand organ changes in multimorbidity (fibrosis in two or more organs).

Goal(s): To use the MRI data in the UK Biobank (UKBB) to study multi-organ changes.

Approach: An automated pipeline to analyse the UKBB kidney MRI data, including deep learning for kidney cortex and medulla segmentation from T₁ maps, alongside segmentation of the liver, spleen and pancreas to assess their T₁. Analysis of 500 healthy volunteers and 235 participants with kidney, pancreas and liver disease.

Results: Multi-organ changes in addition to the primary diseased organ. For example, elevation in cortical T₁ in kidney disease together with increased pancreatic and liver T₁.

Impact: The automated multi-organ analysis of abdominal MRI data to study multi-organ fibrosis. In the future, this will allow investigations related to the epidemiology, risk factors (genetic and environmental) and natural history of fibrotic multimorbidity.  

Keywords: Prostate, Machine Learning/Artificial Intelligence

Motivation: The use of deep learning reconstruction, combined with Multiplexed Sensitivity Encoding (MUSE), can extend the benefit of distortion robustness in prostate DWI to poor SNR conditions while maintaining a large spatial matrix.

Goal(s): The purpose of this study is to evaluate the quantitative image quality improvement provided by combining MUSE and DLR in DWI of the prostate.

Approach: Quantitative analysis including SNR, CNR and ADC were compared through ROI analysis of MUSE DWI with conventional and DL reconstruction in 50 prostatic cancer patients. 

Results: DLR images demonstrated a significantly higher SNR and CNR.  ADC values were consistent among methods.

Impact: Deep learning reconstruction in combination with MUSE can be exploited for better prostate DWI image quality in cases of low SNR, or traded for increased resolution or reduced scan time.

Keywords: Lung, Lung, Acquisition Methods, Biomarkers, New Trajectories & Spatial Encoding Methods

Motivation: To study lung function using 3D MR spirometry.

Goal(s): To optimize 3D dynamic lung MRI with flexible k-space sampling for UTE acquisition.

Approach: A non-Cartesian UTE sequence is developed to execute arbitrary trajectories stored in a readily available external gradient file library. 3D MR spirometry was then performed on freely-breathing healthy volunteers at 1.5 T.

Results: High-quality 4D lung images are obtained, enabling the extraction of relevant respiratory biomarkers. Image quality can then be optimized by directly playing back the shapes and durations of the readout gradients from the files.

Impact: A non-Cartesian, center-out MR sequence that allows out-of-the-box UTE capabilities with flexible k-space trajectories is developed. The result is high-quality 4D lung imaging in free-breathing and supine conditions. The lung functional biomarkers are expected to be sensitive to pathology.

Keywords: Cancer, Cancer

Motivation: The study is motivated by need to improve rectal cancer treatment planning through deep-learning-based analysis of multiparametric MRI, replacing inconsistent and labor-intensive manual tumor delineation.

Goal(s): The study aims to develop a deep-learning algorithm for automated rectal cancer segmentation in MRI images to improve treatment response predictions.

Approach: A two-tiered U-net architecture with attention gates, optimized through cross-validation, was applied to multi-parametric MRI data from 198 patients.

Results: This approach outperformed existing models, with the highest accuracy achieved by combining different MRI sequences. The results indicate that incorporating functional MRI data with anatomical imaging significantly enhances tumor delineation, potentially informing personalized treatment strategies.

Impact: This deep-learning model significantly improves rectal cancer MRI segmentation, offering a path to more accurate and personalized treatment strategies, potentially leading to better patient outcomes and streamlined workflows in oncological imaging and radiation therapy planning.

Keywords: Breast, Breast, breast tumor; dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI); Ultrafast Breast MRI

Motivation: Studies of ultrafast dynamic contrast-enhanced (DCE)-MRI were previously focused primarily on differentiating between benign and malignant breast tumors, with little research on lymph node metastases.

Goal(s): We searched for noninvasive biomarkers to predict lymph node metastases in patients with breast cancer using ultrafast DCE-MRI.

Approach: Ultrafast DCE-MRI was performed using a GRASP sequence, and the proprietary kinetic indicators were calculated to quantitatively diagnose lymph node metastases.

Results: The relative peak enhancement of patients with lymph node metastasis was significantly higher than that of those without metastasis (area under the curve: 0.671)

Impact: In this feasibility study, we preliminarily explored the role of ultrafast breast MRI in diagnosing lymph node metastasis in patients with infiltrating ductal carcinoma. We found that relative peak enhancement can be used to predict lymph node metastasis.

Keywords: Breast, Breast

Motivation: Breast MRI has exceptional sensitivity but is limited by image quality and several artifacts. Advancements in AI-based reconstruction hold promise for improved image quality and efficiency.

Goal(s): This study assesses the impact of applying a vendor AI-based reconstruction on breast MRI at 3T.

Approach: This study retroactively reconstructed 45 series using a commercially available AI-based reconstruction. Three board-certified radiologists scored traditional and reconstructed sequences for quality and improvement.

Results:  AI reconstruction showed more conspicuous margins as well as an enhanced noise texture. 54 cases showed improvement, 63 showed no change, and 15 exhibited degraded quality. Higher-quality exams were associated with the greatest improvement.

Impact: A retrospective analysis of a recent FDA approved AI based reconstruction method to improve MRI image quality for breast studies.

Keywords: Breast, Breast

Motivation: Motion and breathing artifacts in DCE breast MRI can cause misalignment among each dynamic, resulting in inaccurate tumor assessment.

Goal(s): Our goal was to demonstrate the feasibility of advanced fast elastic image registration (FEIR) for correction of misalignment in breast DCE MRI.

Approach: FEIR was applied and evaluated in 11 patients who underwent breast DCE examinations.

Results: Advanced FEIR clearly improved misalignments among dynamic scans and provided improved accuracy of time intensity curves (TICs).

Impact: FEIR improves motion related misalignments among respective dynamic scans in DCE breast MRI, it could improve the TICs more accurately.

Keywords: Breast, Diffusion/other diffusion imaging techniques

Motivation: Conventional DWI has limitations due to low spatial resolution and geometry distortion. Multiplexed sensitivity-encoding (MUSE) DWI can obtain images with higher resolution and less distortion but require longer acquisition time.

Goal(s): Our aim was to apply deep-learning based reconstruction (DLR) in MUSE DWI for breast imaging, and to investigate if DLR can shorten the scan time while maintaining image quality of MUSE.

Approach: We compared quantitative parameters and subjective image quality of MUSE, MUSE-DLR, and conventional DWI.

Results: MUSE-DLR showed improved image quality than MUSE with slightly longer acquisition time compared to conventional DWI.

Impact: MUSE DWI with deep-learning based reconstruction can enhance the accuracy of clinical breast imaging while maintaining an acceptable scanning time, and also has the potential to improve diffusion imaging in other parts of the human body.

Keywords: Liver, Liver

Motivation: MRI methods for screening onset of fatty liver disease are lacking owing to the inability to isolate the earliest grades of inflammation, ballooning and fibrosis.

Goal(s): To demonstrate the validity and reproducibility of liver multi-component relaxometry (LiverMap®) in screening onset of liver pathologies at both 1.5T and 3.0T.

Approach: Patient cohorts comprised a validation cohort with 106 biopsy-proven MASLD patients and 16 healthy volunteers, and a reproducibility cohort of 30 volunteers with and without MASLD.

Results: LiverMap® distinguished the onset of liver pathologies with AUROCs above 0.94, a repeatability CoV of 1.7%, and a reproducibility CoV of 3.5%.

Impact: LiverMap® is a new approach to screen and monitor progression of chronic liver conditions in ~10 minutes scan time. In metabolic associated steatohepatitis, LiverMap® reliably distinguishes the onset of five key liver pathologies - fat, iron, inflammation, ballooning and fibrosis.

Keywords: fMRI Analysis, Breast, Breast cancer;HER2;IVIM

Motivation: This study aimed to predict HER2 expression states in breast cancer patients using IVIM imaging, offering valuable guidance for anti-HER2 treatment.

Goal(s): To categorize patients into HER2-positive, HER2-low, and HER2-zero groups, analyze IVIM parameters, and assess their relationship with clinicopathological features.

Approach: 67 breast cancer patients were retrospectively analyzed, with IVIM imaging and data collection. Statistical tests were employed to compare the groups.

Results: While no significant differences emerged in clinicopathological features, ADC_fast values differed significantly. Both HER2-positive and HER2-low subgroups exhibited higher ADC_fast values than HER2-zero cases. ADC, ADC_slow, and f showed no significant variations.

Impact: This study demonstrates that ADCfast can predict HER2 expression noninvasively, assisting in personalized treatment planning and prognosis assessment for breast cancer patients pre-surgery, providing valuable insights for clinical decision-making.