Yvonne W. Lui

Objectives: Deep learning (DL)-based reconstruction methods can substantially accelerate MRI acquisition while preserving image quality relative to traditional techniques. However, concerns remain regarding their ability to accurately reconstruct abnormalities at higher acceleration factors. This study quantitatively assesses the impact of higher-order acceleration on image quality in DL-reconstructed brain MRI in normal and abnormal cases, emphasizing the utmost need to render abnormal findings accurately. Materials and Methods: Raw k-space image data from 5847 brain MRI examinations (fastMRI) were used. A radiologist-annotated subset of 1001 examinations (fastMRI+) served as the test set; the remainder were split into training (n=3715) and validation (n=1131) sets. Images were retrospectively undersampled (acceleration factors 2 to 12) and reconstructed using an end-to-end variational network. Image quality metrics, including normalized mean squared error (NMSE), structural similarity index measure (SSIM), and peak signal-to-noise ratio (PSNR), were computed within bounding-box annotations containing abnormalities and in size-matched normal control regions, and at the slice-level. The region-by-acceleration interaction was tested using linear mixed-effects models with a subject-level random intercept. Results: All metrics demonstrated progressive degradation with increasing acceleration across slice-level and bounding-box–level analyses. At lower acceleration rates, bounding boxes with and without abnormalities showed comparable image quality. However, above 4-fold acceleration, NMSE within abnormal regions exhibited a notably sharper increase with rising acceleration compared to normal regions, while abnormal regions demonstrated a significantly faster decline in PSNR and SSIM. This nonsymmetric information loss was particularly evident for NMSE at higher acceleration rates. The region-by-acceleration interaction was statistically significant for all 3 metrics at both levels (all adjusted P <0.001), with the effect largest and most consistent for NMSE. Conclusions: Our findings demonstrate a disproportionate, pathology-localized degradation of reconstruction quality as acceleration increases. This emphasizes the importance of rigorous clinical assessment of image quality in DL-MRI reconstruction, particularly at higher undersampling rates, highlighting the need for reconstruction strategies tailored to maintaining diagnostically critical features.

Purpose: The goal of this work is to introduce an automated method to assess the quality of under‐sampled MRI reconstructions. Theory and Methods: We propose a general framework for pixel‐wise uncertainty quantification in accelerated MRI reconstructions, enabling automatic identification of unreliable regions without using ground‐truth fully‐sampled reference images. Our method integrates conformal quantile regression with learning‐based image reconstruction methods to estimate statistically rigorous pixel‐wise uncertainty intervals. We trained and evaluated our model on Cartesian undersampled brain and knee data obtained from the fastMRI dataset using acceleration factors ranging from 2 to 10. An end‐to‐end Variational Network was used for image reconstruction. Results: Quantitative experiments demonstrate strong agreement between predicted uncertainty maps and true reconstruction error. Using our method, the corresponding Pearson correlation coefficient was higher than 90% at acceleration levels at and above four‐fold; whereas it dropped to less than 70% when the uncertainty was computed using a simpler heuristic notion (magnitude of the residual). Qualitative examples further show the uncertainty maps based on quantile regression capture the magnitude and spatial distribution of reconstruction errors across acceleration factors, with regions of elevated uncertainty aligning with pathologies and artifacts. Conclusion: The proposed framework enables evaluation of reconstruction quality without access to fully‐sampled ground‐truth reference images. It represents a step toward adaptive MRI acquisition protocols that may be able to dynamically balance scan time and diagnostic reliability.

As artificial intelligence (AI) becomes more autonomous and multimodal, existing policy frameworks must adapt. Trustworthy AI in radiology requires translational bialignment, integrating both regulatory and implementation science across the lifecycle, with radiologists bridging policy and clinical practice.

Artificial intelligence (AI) models have shown promise in neuroradiology, yet their real-world generalizability remains uncertain, partly due to variability in imaging acquisition and protocols. We aimed to evaluate the impact of data source, scanner manufacturer, scan mode, slice thickness, and the AI models developed by participating teams on AI performance in this secondary analysis of the 2019 American Society of Functional Neuroradiology (ASFNR) AI Competition. We included 1,177 anonymized noncontrast head CT scans from five institutions. Four teams participated, developing models to detect acute ischemic stroke, intracranial hemorrhage, mass effect, and to assess age-appropriate normality. Generalized estimating equations (GEE) were used to evaluate the effects of the aforementioned variables on model performance, and collinearity diagnostics were applied to exclude redundant variables. Due to collinearity with scanner manufacturer, data source was excluded from the model. Across all tasks, the AI model employed significantly influenced performance. Scanner manufacturer was significantly associated with accuracy in detecting intracranial hemorrhage and acute ischemic stroke but not mass effect or age-based normality. Slice thickness significantly associated with detection of intracranial hemorrhage and mass effect, with thinner slices yielding higher accuracy, but showed no effect on ischemic stroke or normality assessments. Scan mode did not significantly influence performance for any task. This secondary analysis demonstrates that imaging acquisition and protocol variability may significantly affect AI model performance. Scanner manufacturer, slice thickness, and the developed AI model were significantly associated with model accuracy, whereas scan mode had no significant impact. Among these, the developed AI model consistently proved most influential, reflecting the importance of training data, model architecture, and preprocessing methods.

Parallel imaging techniques reduce magnetic resonance imaging (MRI) scan time but image quality degrades as the acceleration factor increases. In clinical practice, conservative acceleration factors are chosen because no mechanism exists to automatically assess the diagnostic quality of undersampled reconstructions. This work introduces a general framework for pixel-wise uncertainty quantification in parallel MRI reconstructions, enabling automatic identification of unreliable regions without access to any ground-truth reference image. Our method integrates conformal quantile regression with image reconstruction methods to estimate statistically rigorous pixel-wise uncertainty intervals. We trained and evaluated our model on Cartesian undersampled brain and knee data obtained from the fastMRI dataset using acceleration factors ranging from 2 to 10. An end-to-end Variational Network was used for image reconstruction. Quantitative experiments demonstrate strong agreement between predicted uncertainty maps and true reconstruction error. Using our method, the corresponding Pearson correlation coefficient was higher than 90% at acceleration levels at and above four-fold; whereas it dropped to less than 70% when the uncertainty was computed using a simpler a heuristic notion (magnitude of the residual). Qualitative examples further show the uncertainty maps based on quantile regression capture the magnitude and spatial distribution of reconstruction errors across acceleration factors, with regions of elevated uncertainty aligning with pathologies and artifacts. The proposed framework enables evaluation of reconstruction quality without access to fully-sampled ground-truth reference images. It represents a step toward adaptive MRI acquisition protocols that may be able to dynamically balance scan time and diagnostic reliability.

BACKGROUND AND PURPOSE: Mild traumatic brain injury (MTBI) is a common public health concern with potential long-term consequences, yet its underlying pathophysiology remains poorly understood. Clinical heterogeneity of individuals having diverse extent and array of symptoms has impeded the identification of reliable imaging biomarkers. Traditional group-level analyses may obscure biologically meaningful subtypes. This study uses latent class analysis (LCA) to classify MTBI subjects into symptom-defined subgroups and examines corresponding WM microstructural alterations using advanced diffusion MRI. MATERIALS AND METHODS: Sixty-one MTBI patients within one month of injury completed the Rivermead Post-Concussion Symptoms Questionnaire (RPQ). LCA was used to identify symptom-based subgroups. Of these, 54 MTBI patients underwent multi-shell diffusion MRI and were compared with 31 controls. WM changes were assessed across subgroups using ROI-based diffusion analyses. RESULTS: LCA identified three distinct MTBI subgroups: those with minimal to no symptoms (31.5%), the cognitively symptomatic (38.9%), and the more globally symptomatic (29.6%). The three groups were associated with different patterns of diffusion MRI differences compared with controls. The cognitively symptomatic subgroup showed predominantly central WM differences, the globally symptomatic subgroup exhibited more peripheral differences with right-hemisphere predominance and sparing the corpus callosum, marked by reduced fractional anisotropy and kurtosis and elevated diffusivities, the less symptomatic subgroup demonstrated focal differences in the callosal genu, with increased fractional anisotropy and kurtosis and decreased diffusivity measures. CONCLUSIONS: MTBI comprises biologically distinct phenotypes with subgroup-specific WM signatures on diffusion MRI. Even individuals with minimal to no symptoms show WM differences compared with controls, underscoring the limitations of symptom reporting alone. Integrating symptom-based classification with advanced diffusion MRI may improve diagnostic precision to help risk stratification and provide insight into mechanisms of injury. ABBREVIATIONS: LCA = latent class analysis; MTBI = mild traumatic brain injury; RPQ = Rivermead post-concussion symptoms questionnaire.

Mild traumatic brain injury (mTBI) is a prevalent yet often overlooked public health concern due to the absence of detectable abnormalities on CT or conventional MRI scans. Approximately 18.3%–31.3% of mTBI patients experience persistent symptoms 3–6 months post‐injury, despite normal imaging results, making diagnosis and treatment challenging. In recent years, advanced neuroimaging modalities have emerged with the potential to reveal subtle physiological and structural brain changes that are invisible to traditional imaging. Diffusion MRI (dMRI), for instance, is particularly valuable for detecting white matter injury; perfusion MRI assesses alterations in cerebral blood flow; sodium MRI ( ²³ Na MRI) provides insights into ionic homeostasis; and functional MRI (fMRI) detects disruptions in functional brain network connectivity. In this review, we first explore the underlying mechanisms of mTBI and then summarize current evidence supporting the use of advanced MRI techniques to detect injury signatures associated with these mechanisms. Finally, we highlight populations at heightened risk for repeated injuries—underscoring the urgent need for more sensitive diagnostic tools that can identify injury early, guide return‐to‐activity decisions, and prevent cumulative brain damage. Evidence Level: N/A. Technical Efficacy: Stage 3.

BACKGROUND AND PURPOSE: Sodium (²³Na) MRI provides unique information about ionic homeostasis in the brain. However, in vivo quantification of regional brain sodium is highly challenging due to low SNR and limited spatial resolution. Here, we employ our novel anatomically guided reconstruction (AGR) method to overcome these challenges and enable precise quantification of regional brain total sodium concentration (TSC). MATERIALS AND METHODS: Thirty-four healthy subjects were studied using a 3T clinical MRI scanner with a dual-tuned (¹H-²³Na) birdcage coil. Sodium images were acquired using a TPI sequence (TR=100ms, TE₁/TE₂=0.5/5ms), while proton (¹H) images were obtained with a standard T1w MPRAGE sequence. AGR was performed with regularization parameters βr =0.67, 2.0, and 6.0. As a baseline comparison, standard reconstruction (SR) was also performed using a re-gridding algorithm with compensation for nonuniform sampling. To assess partial volume effects (PVE) on the reconstruction methods, an erosion experiment was conducted. Internal linear calibration using noise-only background and vitreous humor regions was applied to calculate TSC in ROIs including lobar cortical gray matter (GM), subcortical (including hippocampus, caudate, pallidum, putamen and thalamus), callosal, and whole brain white matter (WM). Bonferroni-corrected pairwise comparison was performed using MANOVA at a significance level P < 0.05. RESULTS: The WM erosion experiments confirmed that TSCAGR was stabilized beyond one voxel erosion in the WM, but TSCSR was decreasing with erosion increasing, showing a reduced PVE in the AGR images. AGR also shows greater separation in TSC between GM and WM compared with SR (GM TSC_SR=49.2±4.6mMol/L, WM TSC_SR=38.1±3.0mMol/L; GM TSC_AGR= 48.6±4.9mMol/L, WM TSC_AGR=30.5±2.8mMol/L). We also found smaller variance of TSC_AGR in WM and GM_subcortical compared with TSC_SR. CONCLUSIONS: The AGR helps sodium quantification in healthy human brains by reducing the partial volume effect and variance of TSC in non-cortical brain regions. Our normative values of TSC in the brain regions set the stage to better understand derangements of sodium metabolism and homeostasis in neurological disease. ABBREVIATIONS: AGR＝ anatomically-guided reconstruction; SR= Standard reconstruction; ²³Na= sodium-23; Na⁺/K⁺ − ATPase= sodium-potassium pump; PVC= partial volume correction; PVE= partial volume effect; TSC= total sodium concentration; VH= vitreous humor

Accurate localization of the ventral intermediate nucleus (VIM) within the dentatorubrothalamic tract (DRTT) is critical for effective neurosurgical treatment of essential tremor (ET). This study evaluated the feasibility and anatomical specificity of quantitative susceptibility mapping (QSM) for direct VIM/DRTT visualization, comparing it with conventional diffusion tractography-based reconstructions. Twenty-seven participants (10 healthy controls, 17 ET patients) were enrolled across two institutions and imaged on 3T MRI systems. QSM-defined VIM/DRTT regions were manually segmented based on characteristic hypointense susceptibility contrast. Whole-brain diffusion tractography was performed to reconstruct the DRTT, pyramidal tract (PT), and medial lemniscus (ML) tracts. Spatial overlap between QSM-and tractography-defined VIM/DRTT regions was calculated, as well as overlap with neighboring PT and ML tracts to assess specificity. Two participants were excluded due to insufficient VIM/DRTT streamlines in tractography reconstruction. In healthy controls, QSM-and tractography-defined VIM/DRTT showed high spatial correspondence (left: 87.6 ± 5.1%; right: 85.3 ± 6.5%). ET patients exhibited slightly lower overlap (mean range: 71.5 - 85.1%). Overlap with neighboring PT and ML tracts was minimal (<3.3%), confirming high anatomical specificity of QSM-derived VIM/DRTT regions. QSM enables direct visualization of the VIM/DRTT with high spatial agreement to conventional tractography-based approaches while demonstrating minimal overlap with adjacent tracts. These findings support QSM as a complementary or standalone imaging modality for improved, patient-specific neurosurgical targeting in ET. DBS = deep brain stimulation; DRTT = dentatorubrothalamic tract; ET = essential tremor; ML = medial lemniscus; MRgFUS = MR-guided focused ultrasound; VIM = ventral intermediate nucleus; PT = pyramidal tract; QSM = quantitative susceptibility mapping; WM = white matter.

Computational competitions are the standard for benchmarking medical image analysis algorithms, but they typically use small curated test datasets acquired at a few centers, leaving a gap to the reality of diverse multicentric patient data. To this end, the Federated Tumor Segmentation (FeTS) Challenge represents the paradigm for real-world algorithmic performance evaluation. The FeTS challenge is a competition to benchmark (i) federated learning aggregation algorithms and (ii) state-of-the-art segmentation algorithms, across multiple international sites. Weight aggregation and client selection techniques were compared using a multicentric brain tumor dataset in realistic federated learning simulations, yielding benefits for adaptive weight aggregation, and efficiency gains through client sampling. Quantitative performance evaluation of state-of-the-art segmentation algorithms on data distributed internationally across 32 institutions yielded good generalization on average, albeit the worst-case performance revealed data-specific modes of failure. Similar multi-site setups can help validate the real-world utility of healthcare AI algorithms in the future.