Fontan-associated liver disease (FALD) is associated with morbidity and mortality in patients with palliated single ventricle congenital heart disease. To develop machine learning models using radiomic features from T1-weighted, T2-weighted, and diffusion-weighted MRI with pertinent clinical variables to predict Fontan failure and correlates of FALD severity in patients who underwent the Fontan operation. In this retrospective study of abdominal MRI examinations and clinical record data from 131 Fontan palliation patients (age range 9.1 - 53.3years old), radiomic features from the liver and spleen were extracted using axial T1-weighted, T2-weighted fat-suppressed, and diffusion-weighted sequences. Patients were categorized by a composite clinical outcome (i.e., Fontan failure) and by correlates of FALD severity, including liver shear stiffness and portal hypertension. Support vector machine (SVM) and multivariable logistic regression models were used to perform two-class classification using radiomic features and/or clinical data. All models were trained and evaluated using five-fold cross-validation (CV). The best radiomic-only model utilized T2-weighted imaging of both organs with logistic regression to predict the presence of portal hypertension, achieving an AUROC of 0.85±0.01. Clinical-only models showed inferior diagnostic accuracy with the highest AUROC of 0.70±0.08. Combining radiomic and clinical features also did not enhance performance compared to radiomic-only models, with the highest AUROC of 0.77±0.05. Ensemble modeling, which incorporated radiomics from all three MRI sequences, yielded AUROCs ranging from 0.33 to 0.72. Models incorporating radiomic features from abdominal MRI in Fontan circulation patients demonstrate moderate diagnostic performance for predicting Fontan failure as well as correlates of FALD severity. These models outperformed models containing only clinical electronic health record data and did not improve with ensembled radiomic and clinical data.

Prediction of tumor downstaging in locally advanced rectal cancer after neoadjuvant therapy: The value of MRI features of tumor heterogeneity.

This study sought to determine the intrasession repeatability of the diffusion-weighted (DW) arterial spin labeling (ASL) sequence at different postlabel delays (PLDs). We first performed numerical simulations to study the accuracy of the two-compartment water exchange rate (Kw) fitting model with added Gaussian noise for DW PLDs at 1500, 1800, and 2100 ms. Ten young, healthy participants then underwent a structural T1 scan and two intrasession in vivo DW ASL scans at each PLD on a 3T MRI. The Kw, arterial transit time (ATT), and cerebral blood flow maps were linearly registered to the structural images, which were then segmented using FreeSurfer into masks with 35 bilateral gray-matter regions. Simulation results showed that the Kw fitting model performed at an error rate less than 10% at physiological ATTs and Kw values, but that error and bias increased at a PLD of 2100 ms and at ATT ranges where the overall blood signal fraction (A1) is low. In vivo analysis showed a significant positive correlation between intrasession measurements of regional Kw at a DW PLD of 1800 ms (β = 0.33, p < 0.001) only. Furthermore, a significant positive relationship between Kw and cerebral blood flow was seen at a DW PLD of 1500 ms (β = 0.26, p = 0.005) and DW PLD of 2100 ms (β = 0.39, p = 0.006). Overall, DW ASL provides the strongest intrasession repeatability at a PLD of 1800 ms in young, healthy subjects, and a simulation study shows accurate Kw fits at physiologic range of ATTs and Kw values.

To evaluate if co-registering Diffusion-Weighted Imaging (DWI) before generating Apparent Diffusion Coefficient (ADC) maps can improve differentiating benign and malignant breast lesions in MRI based on the A6702 thresholds. This IRB-approved study involved an in-house dataset and the publicly available ACRIN-6698 dataset, both including multi b-value DWI. In phase one, 16 ANTs library-based co-registration methods were evaluated on a subset of n = 138 cases from our in-house cohort. The quantitative assessment included mean ADC values of manually segmented lesions (diagnostic metrics using individual and A6702-defined thresholds) and coefficient of Variation. In the second phase, the best-performing methods were tested for generalizability on an unseen set of 40 cases (20 from in-house and 20 from external dataset). Three blinded readers segmented lesions on co-registered and non-co-registered ADC maps. Agreement and consistency were evaluated via Bland-Altman, segmentation distance, and intraclass correlation coefficient. Rigid co-registration using DWI at b = 750s/mm2 as reference (b750-Rigid) improved accuracy of both optimal/conservative A6702 trial thresholds with sensitivity/specificity increasing from 93%/10% to 97%/30% and 100%/30% respectively. Mean ADC values were not significantly different after co-registration (p > 0.05). Co-registration of DWI images before ADC map generation, particularly using b750-Rigid registration, seems promising for improving lesion classification in breast MRI. Further validation is warranted.

Acute pancreatitis (AP) is associated with a high mortality rate that is directly related to its severity. Limited research has been conducted on the role of DWI-MRI in the diagnosis and staging of acute pancreatitis as it pertains to the revised Atlanta classification. The objective of this study was to examine the role of diffusion-weighted (DW) magnetic resonance imaging (MRI) in early diagnosis and staging of acute pancreatitis in correlation to the revised Atlanta classification. According to the revised Atlanta classification, a prospective assessment was performed to examine the correlation between DW MRI and apparent diffusion coefficient (ADC) values with the severity of acute pancreatitis (AP) in a sample of 34 patients diagnosed with AP. The mean ADC value of mild edematous pancreatitis was 1.14±0.06x10-3 mm2/sec, moderate edematous pancreatitis was 1.18±0.16x10-3 mm2/sec, severe necrotizing pancreatitis was 1.99±0.06x10-3 mm2/sec, and that of the normal pancreas was 1.54±0.05 x10-3 mm2/sec. Based on the revised Atlanta classification, there was a significant difference between the ADC values of normal pancreas and acute, severe, and mild/moderate pancreatitis, while there was no significant difference between mild and moderate pancreatitis cases. ROC analysis yielded high accuracy in differentiating normal pancreas from acute pancreatitis and severe pancreatitis from non-severe pancreatitis (AUC=0.827 and 0.870, respectively). In the current study, the qualitative assessment of DWI images indicated that all cases of mild acute pancreatitis (AP) displayed true diffusion restriction, while facilitated diffusion was observed in 80% of patients diagnosed with necrotizing pancreatitis. Our findings have validated the outcomes of earlier research regarding the average ADC values of both the healthy and acutely inflamed pancreas. According to the Revised Atlanta Classification, DWI has the ability to assist in the prompt diagnosis of acute pancreatitis and to differentiate mild forms from severe ones. DW-MRI using both qualitative and quantitative methods provides a concise, safe, and radiation-free imaging method for early detection and assessing the severity of acute pancreatitis.

To evaluate the performance of model-based dynamic contrast-enhanced (DCE)-MRI and diffusion-weighted imaging (DWI) in determining the disease activity of thyroid-associated ophthalmopathy (TAO), and to establish their additional value to fat-suppressed T2-weighted imaging (FS-T2WI) for staging TAO. Seventy-two patients with TAO (48 active, 96 eyes; 24 inactive, 48 eyes) were prospectively enrolled. DCE-MRI, DWI and FS-T2WI were scanned for pre-treatment evaluation. Simplified histogram parameters (min, mean, max) of DCE-MRI-derived Ktrans, Kep and Ve, apparent diffusion coefficient (ADC) and signal intensity ratio (SIR) on FS-T2WI of extraocular muscles were calculated for each orbit and compared between active and inactive groups. Multivariate analyses were used to identify independent indicators for disease activity. Receiver operating characteristic (ROC) curves analyses and DeLong tests were performed to evaluate and compare the performances of the identified significant imaging parameters and their combinations. Active TAO patients showed significantly higher mean and maximum Ve, higher minimum, mean and maximum ADC, higher minimum, mean and maximum SIR than inactive patients (p < 0.05). Mean SIR (odds ratio (OR) = 3.449, p = 0.002), mean ADC (OR = 1.008, p < 0.001), and mean Ve (OR = 14.138, p = 0.022) were found to be independent predictors of active TAO. Combination of mean Ve, mean ADC and mean SIR outperformed mean SIR alone in staging TAO (area under ROC curves, 0.839 vs 0.769, p = 0.016). DCE-MRI and DWI could determine the disease activity of TAO and provide additional value to FS-T2WI in staging TAO. Question Fat-suppressed T2-weighted imaging was the most commonly used imaging technique for determining the disease activity of thyroid-associated ophthalmopathy; however, its performance needs to be improved. Findings Dynamic contrast-enhanced magnetic resonance imaging and diffusion-weighted imaging could provide added value to fat-suppressed T2-weighted imaging for determining the clinical activity of thyroid-associated ophthalmopathy. Clinical relevance Dynamic contrast-enhanced magnetic resonance imaging and diffusion-weighted imaging can provide information about tissue permeability and water molecule diffusion of extraocular muscles in patients with thyroid-associated ophthalmopathy (TAO), and therefore provide additional value to fat-suppressed T2-weighted imaging in staging TAO.

Background: Stroke and subclinical cerebral ischemia remain important neurological complications of transcatheter aortic valve replacement (TAVR). The Sentinel cerebral embolic protection (CEP) device is designed to capture embolic debris during TAVR, but its impact on clinical and imaging outcomes remains incompletely characterized. Methods: PubMed, Embase, and Cochrane databases were systematically searched for randomized controlled trials (RCTs) comparing Sentinel CEP versus no protection when TAVR was performed. Outcomes of interest included all stroke, disabling stroke, infarct volume by diffusion-weighted MRI in protected and unprotected areas, all-cause mortality, acute kidney injury, and major vascular complications. Risk ratios (RRs) and median differences with 95% confidence intervals (CIs) were calculated using random-effects models and trial sequential analysis (TSA) assessed evidence robustness. Results: Four RCTs including 10,986 patients were analyzed. Sentinel CEP did not significantly reduce clinical stroke (RR 0.88, 95% CI 0.69-1.12) or disabling stroke (RR 0.68, 95% CI 0.41-1.14). Pooled DW-MRI data showed a significant reduction in new ischemic lesion volume within Sentinel CEP-protected territories (difference in medians -75.7 mm3; 95% CI -130.4 to -21.0). Subgroup analyses in elderly, female, and high-surgical-risk patients revealed no benefit with Sentinel CEP. Additionally, TSA indicated that current data are underpowered for definitive conclusions. Conclusions: The Sentinel CEP device during TAVR did not significantly reduce clinical stroke but was associated with lower MRI-detected ischemic lesion volumes compared with no protection. Further adequately powered RCTs integrating clinical and imaging endpoints are needed to define its role in neuroprotection during TAVR.

We report the case of a Japanese man in his 60s undergoing hemodialysis for end-stage renal disease due to autosomal dominant polycystic kidney disease, who had experienced repeated hepatic cyst infections. Despite treatment with oral antibiotics, including minocycline and trimethoprim-sulfamethoxazole, he presented with fever and was admitted to our hospital. Diffusion-weighted magnetic resonance imaging demonstrated a high signal intensity in a large hepatic cyst, and percutaneous transhepatic drainage was performed. Enterococcus faecium was isolated from the cyst fluid. Three intracystic minocycline infusions were administered in combination with intravenous vancomycin after dialysis. The patient achieved clinical improvement and remained free from recurrence until day 253 of illness. Infections in large cysts tend to be refractory, and drainage alone may be insufficient, particularly in immunocompromised patients on hemodialysis. Intracystic sclerotherapy with minocycline offers both antimicrobial and sclerosing effects, with previous reports demonstrating cyst shrinkage and infection control in non-dialysis patients. To our knowledge, this is the first report describing successful intracystic minocycline infusion in a patient undergoing hemodialysis, and no recurrence or significant adverse events were observed. Intracystic minocycline infusion sclerotherapy may be a safe and effective therapeutic option for hepatic cyst infection in this population.

Accurate estimation of intravoxel incoherent motion (IVIM) parameters from diffusion-weighted MRI remains challenging due to the ill-posed nature of the inverse problem and high sensitivity to noise, particularly in the perfusion compartment. In this work, we propose a probabilistic deep learning framework based on deep ensembles (DEs) of mixture density networks (MDNs), enabling estimation of total predictive uncertainty and decomposition into aleatoric (AU) and epistemic (EU) components. The method was benchmarked against nonprobabilistic neural networks, a Bayesian fitting approach, and a probabilistic network with single Gaussian parametrization. Supervised training was performed on synthetic data, and evaluation was conducted on both simulated and invivo brain mouse dataset. The reliability of the quantified uncertainties was assessed using calibration curves, output distribution sharpness, and the continuous ranked probability score (CRPS). MDNs produced more calibrated and sharper predictive distributions for the diffusion coefficient ( ) and the perfusion fraction ( ) parameters, although slight overconfidence was observed in the pseudodiffusion coefficient ( ). The robust coefficient of variation (RCV) indicated smoother invivo estimates for with MDNs compared with Gaussian model. Despite the training data covering the expected physiological range, elevated EU invivo suggests a mismatch with real acquisition conditions, highlighting the importance of incorporating EU, which was allowed by DE. Overall, we present a comprehensive framework for IVIM fitting with uncertainty quantification, which enables the identification and interpretation of unreliable estimates. The proposed approach can also be adopted for fitting other physical models through appropriate architectural and simulation adjustments.

To evaluate whether periodically rotated overlapping parallel lines with enhanced reconstruction-diffusion-weighted imaging (PROPELLER-DWI) combined with deep learning-based reconstruction (DLR) improves head and neck DWI, we conducted a primary comparison of PROPELLER-DWI with DLR at varying strengths and without DLR, and a secondary comparison of DLR-processed PROPELLER-DWI with DLR-processed single-shot echo-planar imaging (EPI)-DWI. Ten healthy adults (8 males, 2 females) participated in the study. PROPELLER-DWI and single-shot EPI-DWI images were acquired using a 3-Tesla MRI system (Discovery MR750w; GE Healthcare, Waukesha, WI, USA) with various recon deep-learning strength (DLS) values: off (DLS-Off), low (DLS-L), medium (DLS-M), and high (DLS-H). We measured the SNR and contrast ratio on DWI images and value of coefficient of variation (CV) on apparent diffusion coefficient (ADC) maps for a quantitative evaluation. For a qualitative evaluation, we visually evaluated the overall image quality, degree of geometric distortion, and magnetic susceptibility artifacts. The SNRs for PROPELLER and EPI-DWI improved with the increase in the DLS level, with DLS-H showing a significantly higher SNR than DLS-Off. ADC maps demonstrated lower CVs at higher DLS levels, significantly lower in DLS-H than DLS-Off. The qualitative evaluation revealed that PROPELLER-DWI with DLR (at all DLS levels: -L, -M, and -H) provided significantly better overall image quality than that without DLR. In addition, PROPELLER-DWI demonstrated significantly higher qualitative scores across all evaluation items (i.e., overall image quality, geometric distortion, and magnetic susceptibility artifacts) compared with EPI-DWI. In head and neck DWI, PROPELLER-based acquisition with DLR enabled the acquisition of visually superior image quality. This approach is clinically useful for the head and neck radiology.

Prostate cancer is the most commonly diagnosed cancer among men in 112 countries, accounting for approximately 15% of all cancer cases. Whilst the 5-year survival rate for localised disease exceeds 90%, there is a significant drop to 50% if metastases are present. Following the VISION and TheraP trials, 177Lu-PSMA-therapy was approved for treatment of metastatic castrate resistant prostate cancer by the FDA and EMA 2022. Patient selection for 177Lu-PSMA-therapy is now relatively well defined, guided by PSMA-PET/CT criteria established in pivotal trials. Nevertheless, clinical consensus on appropriate criteria is still evolving, and additional imaging modalities such as 18F-FDG PET, post-therapy SPECT/CT, or emerging techniques such as whole-body diffusion-weighted MRI may serve as valuable adjuncts to identify PSMA-negative or treatment-resistant disease that may not be apparent on PSMA-PET/CT alone. This review examines the current evidence on imaging biomarkers and complementary diagnostic techniques used for patient selection, treatment monitoring, and response assessment in [¹⁷⁷Lu]Lu-PSMA-617 therapy for metastatic castrate resistant prostate cancer. Baseline imaging biomarkers on PSMA-PET/CT, such as mean standardised uptake value (SUVmean), PSMA-avid total tumour volume, and inter-lesional PSMA heterogeneity, have shown promise in predicting treatment response and assessing outcomes. Additionally, statistical prognostic models have been developed to predict treatment efficacy, though further validation is required. Imaging plays a crucial role and should be considered alongside blood biomarkers, clinic-demographic history, and circulating tumour markers to improve patient selection for 177Lu-PSMA-therapy.Critical relevance statementPSMA-PET/CT is the established imaging modality for patient selection for ¹⁷⁷Lu-PSMA-therapy, while ¹⁸F-FDG PET, post-therapy SPECT/CT, and emerging techniques such as whole-body diffusion-weighted MRI can be adjunctive for patient selection, response assessment and long-term monitoring.Key PointsPSMA-PET/CT is the mainstay for patient selection for ¹⁷⁷Lu-PSMA-therapy. 18F-FDG PET, SPECT/CT or whole-body diffusion-weighted MRI could be used as adjuncts.Interim and longitudinal PSMA-PET/CT offer sensitive detection of progression, quantitative biomarkers for response assessment, and standardised frameworks.Advances in AI, radiomics, and standardisation frameworks may refine prognostication, enable personalised dosimetry, and integrate imaging biomarkers into clinical practice, though further validation is required.Graphical

Precise localization of perfusion deficits in diffusion-weighted MRI (DWI) is critical for acute ischemic stroke management. However, existing deep learning methods typically produce discrete binary masks, failing to capture the continuous nature of ischemic injury and discarding valuable intra-lesion information. We propose StrokeFlow, a novel framework that represents the ischemic region as a continuous field. Our coordinate-based network is trained to output a smooth ischemic density field, representing voxel-level infarction probability. Furthermore, we introduce a vector flow head, explicitly supervised to learn a vector field that aligns with the negative gradient of the Apparent Diffusion Coefficient (ADC) map, thereby modeling the directionality of the perfusion deficit. Evaluated on the public ISLES 2022 dataset, StrokeFlow demonstrated superior lesion boundary accuracy, significantly outperforming strong baselines in the 95% Hausdorff Distance metric. The model also showed enhanced sensitivity in detecting small and multifocal lesions. By shifting the paradigm from discrete segmentation to continuous, functionally-aware fields, StrokeFlow offers a more biologically plausible and interpretable tool for a nuanced clinical assessment of ischemic stroke.

Cerebral Embolic Protection During Transcatheter Aortic Valve Replacement: A Systematic Review of Effects on Diffusion-Weighted MRI Lesions, Clinical Stroke, and Early Cognition

Background &amp; Objective: To determine diagnostic accuracy of Diffusion Weighted Magnetic Resonance Imaging indifferentiation between benign and malignant soft tissue tumors keeping histopathology as gold standard.Methodology: Atotal of 176 patients meeting inclusion criteria underwent MRI, including DWI sequences at b-values of0, 50, and 1000 s/mm² and ADC values were calculated from corresponding maps. ROI was placed on the solid tumorcomponent of mass. Post-contrast imaging was also performed. All MRIs were interpreted by blinded, qualifiedradiologists to ensure unbiased results. Definitive diagnoses were confirmed through histopathological analysis bycertified pathologists.Results: 98 (55.69%) were aged 13–40 years and 78 (44.1%) were 41–75 years, with a mean age of 40.62±10.13 years.There were 94 males (53.5%) and 82 females (46.5%). Tumor sizes ranged from 3.1 cm to 11.5 cm, with a mean size of6.3 cm. The average ADC value of benign masses (1.50 × 10⁻³ mm²/s) was higher than that of malignant masses (0.83 ×10⁻³ mm²/s). A cutoff ADC value of 1.1 × 10⁻³ mm²/s provided sensitivity of 85.51%, specificity of 86.84%, PPV of88.89%, NPV of 82.50%, and diagnostic accuracy of 85.88%. Histopathology showed 97 masses (55.3%) were malignantand 79 (44.7%) were benign.Conclusion: Diffusion-weighted MRI (DWI) is a non-invasive, cost-effective imaging tool with 85.5% sensitivity and86.8% specificity for evaluating soft tissue masses. It can aid early detection of malignant tumors, improving patientoutcomes through timely diagnosis.

Network-based analysis of differential white matter connectivity in major depressive disorder with and without comorbid anxiety.

Background/Objectives: This study examined the clinical utility of diffusion-weighted whole-body magnetic resonance imaging with background body signal suppression (DWIBS) for differentiating infectious from non-infectious aortitis. Methods: The study included 32 patients with suspected inflammatory aortitis who underwent non-contrast computed tomography (NCCT) and magnetic resonance imaging. We evaluated the diagnostic performance of DWIBS using the spinal cord as a reference, NCCT, and their combination. The diagnosis of infectious aortitis was adjudicated based on imaging, clinical, and laboratory findings. We conducted a sensitivity analysis using a stricter definition of infectious aortitis that required both surgical and microbiological confirmation. Results: Fifteen patients were diagnosed with infectious aortitis. The sensitivity, specificity, and areas under the receiver operating characteristic curves were 93.3%, 70.6%, and 0.82, respectively, for NCCT; 93.3%, 76.5%, and 0.85, respectively, for DWIBS; and 86.7%, 94.1%, and 0.90, respectively, for the combination of both modalities. In the sensitivity analysis, the combined DWIBS and NCCT approach demonstrated a specificity of 87.5% and a sensitivity of 70.8%. Conclusions: DWIBS using the spinal cord as a reference appears to be a promising diagnostic tool for differentiating infectious from non-infectious aortitis, especially when combined with NCCT.

BackgroundMost Parkinson's disease (PD) patients experience cognitive impairment. Normal cognitive function is supported by the neuromodulatory mechanisms of the cholinergic system. The primary source of cortical cholinergic input are projections from the nucleus basalis of Meynert (NBM) in the basal forebrain. There is evidence that NBM integrity and PET cortical cholinergic function are associated with cognition in PD. We previously found that the integrity of cortical cholinergic projections, measured using anatomically constrained tractography from diffusion‐weighted MRI (DWI), was associated with cognitive function in PD. Here, we test whether cholinergic projection integrity is associated with longitudinal cognitive function.MethodWe used Bayesian linear mixed effects models to examine the association between longitudinal change in cognition and baseline structural integrity of cholinergic cortical pathways in PD participants (baseline n = 101; follow‐up n = 59; average follow‐up time = 3.2[0.5] years). Neuropsychological testing examined four cognitive domains. Cortical cholinergic integrity was measured using a data‐driven composite score derived from principal component analysis of three DWI measures of cortical cholinergic projection microstructural integrity from our previous work (mean diffusivity, free water fraction, and fibre density and cross‐section). Models accounted for age and allowed for a varying intercept per participant and varying slope for time.ResultBaseline cortical cholinergic projection integrity (β = 0.19 [0.04,0.34], p = 98%) was independently associated with cognition; however, there was no evidence cognitive performance was associated with time in this sample (β = 0.13 [‐0.08,0.25], p <95%). As such, we did not find evidence of an interaction between baseline cortical cholinergic projection integrity and time (β = 0.04 [‐0.09,0.11], p <95%)).ConclusionWe found strong evidence for a modest association between baseline cortical cholinergic integrity and cognition in PD. This suggests that the composite measure of cortical cholinergic projection integrity used in this analysis was consistently related to cognitive performance across assessment timepoints but there was no evidence baseline integrity predicted differential rates of cognitive decline. Combining measures from additional components of the brain cholinergic system, or from other neurotransmitter systems, may provide greater insight into cognitive trajectories in PD.

Grey matter structure is central to neuroscience, as cellular morphology varies by type and is influenced by neurological conditions. Understanding these variations is essential for studying brain function and disease mechanisms. Diffusion-weighted MRI (dMRI) offers a non-invasive way to examine cellular microstructure, but its accuracy depends on identifying which morphological features influence its measurements. Despite increasing interest, no systematic study has defined the key neural cell features relevant to dMRI interpretation. Here, we analyzed over 11,800 three-dimensional cellular reconstructions across three species and nine cell types, establishing reference values for critical traits grouped into structural, shape, and topological categories. We also identified which of these traits are most relevant to dMRI sensitivity. In addition, we provide high-resolution 3D surface meshes representative of each cell type and species. These meshes, compatible with Monte Carlo simulators, offer a valuable resource for modeling and interpreting gray matter microstructure Carlo simulators, offering a valuable resource for the modelling community.

Diffusion-weighted imaging (DWI) of the head and neck is essential for various clinical applications but is often hampered by artifacts and reduced image quality. Deep learning (DL) reconstruction has the potential to enhance the quality of head and neck DWI. This study aims to evaluate the performance of an accelerated, DL-reconstructed DWI (DWIDL) in terms of image quality and diagnostic confidence. This retrospective study included patients who underwent clinically indicated head and neck DWI at 1.5 T and 3 T between August 2023 and January 2024 at atertiary care center. Imaging was performed at low b‑values (0 or 50 sec/mm2) and high b‑values (800 sec/mm2), and apparent diffusion coefficient (ADC) maps were computed. After acquiring standard single-shot echoplanar imaging DWI sequences, the raw MR datasets underwent simulated acceleration by reducing the number of signal averages. These accelerated exams were then reconstructed using anovel DL-based algorithm that combined DL-based k‑space to image reconstruction with DL-based super-resolution processing (DWIDL). Three readers analyzed the images using avisual Likert score to evaluate image sharpness, artifacts, noise, overall image quality, and diagnostic confidence. Comparisons were made using the Wilcoxon signed-rank test. Aquantitative analysis of signal-to-noise ratio (SNR), contrast-to-noise ratio (CNR) and apparent diffusion coefficient values (ADC) was also performed. The study included 30patients (mean age, 55 ± 19years; range, 24-84; 18men) with various pathologies. Scan times were reduced by 67% at 1.5 T and up to 55% at 3 T. The quantitative analysis revealed aminimal but statistically significant decrease in SNR and CNR in the deep learning-reconstructed images (p = 0.002 and p < 0.001, respectively). However, readers reported no significant differences between DWI and DWIDL regarding image quality parameters or diagnostic confidence for both low and high b‑value images, as well as the ADC (all p > 0.05). DL reconstruction of head and neck DWI is feasible, significantly reducing examination time without compromising image quality or diagnostic confidence. This technique enables accelerated and effective diagnostic DWI of the head and neck.

White matter structure-function decoupling in juvenile myoclonic epilepsy