Functional connectivity (FC) and intrinsic neural timescales (INT) characterize the spatio-temporal neural dynamics of binge-type eating disorders (EDs). We examined FC and INT abnormalities in visual-related regions of patients with binge-type EDs, focusing on the impact of depression severity. We recruited 72 patients with binge-type EDs and 39 healthy controls (HCs). Patients were divided into two groups: Group 1 (minimal/mild depression) and Group 2 (moderate/severe depression). FC alterations in key visual-related regions across three groups were analyzed using ANCOVA (P < 0.05, FWE-corrected). INT was further assessed in regions with significant FC changes (P < 0.05, FDR-corrected). Correlations of FC and INT with clinical measures, as well as between FC and INT, were examined. Seventeen brain subregions exhibited altered FC, with Group 2 showing more pronounced disruptions than Group 1 and HCs. These alterations primarily involved nodes within the sensorimotor, reward, and inhibitory control networks. Additionally, significant INT differences in the sensorimotor and heteromodal regions were observed between Group 2 and HCs. Correlation analyses suggested trend-level associations between FC and clinical characteristics, as well as between FC and INT in Group 2. Collectively, these findings indicate that FC and INT disruptions in visual-related regions are aggravated by depression severity in binge-type EDs.

To prospectively compare the image quality and diagnostic performance of ultra-high-field 5 T MRI with that of standard 3 T in patients with suspected prostate cancer (PCa). Sixty-seven consecutive patients received prostate scan at both 5 T and 3 T MRI systems. Two radiologists independently evaluated the images in a double-blind manner. A head-to-head comparison of 5 T and 3 T MRI was conducted from both qualitative and quantitative perspectives. Pathological results from prostate biopsy and radical prostatectomy were used as the gold standard to evaluate the diagnostic performance. 5 T MRI demonstrated superior image quality and enhanced visualization of prostatic anatomical structures, including prostatic capsule, seminal vesicle and neurovascular bundles. The lesion delineation was significantly improved in 5 T MRI. The elevated field strength resulted in a significantly higher signal-to-noise ratio, contrast-to-noise ratio, edge rise distance and lesion slope profile in both T2WI and DWI sequences without introducing additional artifacts. Moreover, 5 T MRI demonstrated improved diagnostic performance for biopsy outcomes and pathological features than 3 T. 5 T MRI effectively improves PCa assessment compared to 3 T. Our study provides preliminary evidence for the feasibility of 5 T MRI in PCa diagnosis and evaluation.

Rationale and Objectives While guidelines recommend tests like the FIB-4 index and liver stiffness measurements (LSM) to identify high-risk Metabolic dysfunction-associated steatotic liver disease (MASLD) patients, their actual accuracy in predicting liver-related events (LREs) remains unclear. Here, we systematically evaluate their prognostic performance to better inform clinical decisions. Materials and Methods We systematically searched Cochrane Library, Embase, PubMed and Web of Science (up to January 7, 2026), to identify studies utilizing non-invasive tests (NITs) for predicting incident LREs and reporting their prognostic performance. Subgroup analyses and meta-regression were performed based on dataset characteristics to explore potential sources of heterogeneity. All pooled analyses were conducted using a random-effects model. Results This meta-analysis included a total of 30 studies involving 67,533 patients with MASLD. The results demonstrated that for predicting incident LREs, the pooled C-index for Vibration-Controlled Transient Elastography (VCTE), the FIB-4 index, and Magnetic Resonance Elastography (MRE) were 0.83 (95% CI: 0.79–0.87), 0.82 (95% CI: 0.78–0.85), and 0.78 (95% CI: 0.64–0.91), respectively. In the evaluation of secondary outcomes, the pooled C-index of VCTE for predicting hepatocellular carcinoma (HCC) was 0.78 (95% CI: 0.70–0.86). Regarding mortality risk prediction, the pooled C-index for VCTE and the FIB-4 index were 0.83 (95% CI: 0.76–0.89) and 0.75 (95% CI: 0.66–0.84), respectively. Conclusion The FIB-4 index and LSM measured by VCTE exhibit robust prognostic discrimination for LREs in MASLD. Existing evidence supports the FIB-4 index and VCTE as routine non-invasive prognostic tests. Furthermore, the prognostic performance of MRE requires additional validation in future research.

Automatic lesion classification holds great promise for improving clinical diagnostic workflows, yet its practical application is hindered by domain shifts in multi-center medical images, which cause significant performance degradation. Although domain generalization (DG) with multi-source data offers a solution, a significant challenge remains: effectively suppressing domain-specific style variations to learn subtle, discriminative lesion features, which are often obscured by pronounced domain discrepancies. To address this challenge, we propose a novel framework named Frequency swapping and Soft-mask disentanglement for Domain Generalization (FSDG) for Domain Generalization. Our FSDG is designed to learn discriminative lesion features robust to domain shift through three key synergistic modules: a Fourier Amplitude Swap Module (FASM) that synthesizes domain-disturbed images by swapping high-frequency components to mitigate style variations; a Complementary Soft-mask Disentanglement Module (CSDM) that decomposes these images into distinct lesion-discriminative and domain-specific features; and a Domain Mixup with Consistency Regularization Module (DMCR) that enforces hybrid consistency constraints to ensure robust feature learning. These modules form a cohesive pipeline that can be flexibly integrated with different feature backbones, which we demonstrate on both single-modality and multi-modality tasks to enhance domain generalization for lesion diagnosis. Extensive experiments are conducted on two types of datasets: a publicly available multi-center skin lesion dataset from six hospitals, and a private multi-center Hepatocellular Carcinoma Microvascular Invasion (HCC-MVI) multi-parameters Magnetic Resonance Imaging(mp-MRI) dataset from five hospitals. Results show that the proposed FSDG achieves average accuracy of 81.89% and 79.05% on the single-modality skin lesion and multi-modality HCC-MVI tasks, respectively. On the skin lesion task, this represents an improvement of 11.43% over the baseline and a 0.87% margin over the second-best method. Our approach consistently outperforms several baseline and state-of-the-art methods across various domain combinations. These findings validate the effectiveness and strong generalization capability of FSDG in medical image domain generalization, demonstrating its potential to facilitate the broader clinical application of diagnostic models trained on limited multi-center data.

This study aimed to explore the prognostic value of body composition (BC) parameters derived from CT imaging and their derived phenotypes following resection of hepatocellular carcinoma (HCC). Retrospective collection of HCC patients who underwent liver resection at 5 medical centers. TotalSegmentator was employed to segment adipose and muscle tissues on CT images. Manual corrections were performed at the L3 level to extract tissue area and CT density parameters. Cox proportional hazards models were used to identify potential prognostic parameters for 2-year recurrence-free survival (RFS) and construct BC phenotypes. Further exploration was conducted on the prognostic value of the BC phenotypes. A total of 497 patients were included (mean age, 59.3 ± 11.0 years; 396 men; cirrhosis prevalence, 53.50

BACKGROUND:Cognitive impairment is a relatively prevalent comorbidity in chronic obstructive pulmonary disease (COPD), yet its neuropathological mechanism remains poorly understood. METHODS:We enrolled 48 stable COPD patients, categorized into cognitively normal (CogN, n = 22) and impaired (Cog, n = 26) groups based on Montreal Cognitive Assessment (MoCA) scores, along with 34 matched healthy controls. All participants underwent 3T MRI with quantitative susceptibility mapping (QSM) to quantify regional brain iron content. Group comparisons of whole-brain and region-of-interest susceptibility were performed. Mediation analysis was then used to test whether specific brain iron deposition mediates the relationship of both COPD status and peripheral inflammatory markers with cognitive performance. RESULTS:Cog patients showed increased total iron in the right cerebellum crus I, while CogN patients exhibited higher paramagnetic susceptibility (χpara) in the left orbitofrontal cortex (OFC), right precentral gyrus, and right brainstem. χpara in the left OFC and right brainstem were positively correlated with total MoCA, abstraction, and orientation scores. Mediation analysis demonstrated that χpara of the left OFC mediated the effects of both COPD status and systemic neutrophil counts on impaired abstraction. Additionally, right brainstem χpara mediated the relationship between COPD and deficits in orientation. CONCLUSIONS:COPD patients with cognitive impairment exhibited distinct patterns of brain iron deposition. Importantly, deposition in several key regions served as a potential mediator, linking both COPD and systemic inflammation to specific cognitive deficits. These preliminary findings suggest a possible association between brain iron accumulation and cognitive impairment in COPD, offering candidate neuroimaging markers for early identification.  .

To refine the diagnostic criteria for rim arterial phase hyperenhancement (Rim APHE) and to evaluate the impact of this modification on the diagnostic performance for primary liver malignancies. This multicenter, retrospective study included patients with pathologically confirmed primary liver malignancies who underwent preoperative magnetic resonance imaging (MRI) before June 2021. Thirteen different measurement methods for Rim APHE were evaluated to determine the optimal criterion based on diagnostic performance. Two radiologists independently reviewed all observations, assigned Liver Imaging Reporting and Data System (LI-RADS) categories according to version 2018. The diagnostic performance of LI-RADS using original versus modified Rim APHE criteria was compared. The study enrolled 272 patients, including 204 with Hepatocellular carcinoma (HCC) (170 men and 34 women; mean age, 57 years ±10) and 68 with non-HCC malignancies (53 men and 15 women; mean age, 56 years ±10). The optimal criterion for Rim APHE was the total thickness of the thickest part of peripheral hyperenhancement to tumor diameter (area under the receiver operating characteristic (ROC) curve [AUC] = 0.852; P < .001). With implementation of the modified Rim APHE criterion, the LR-5 criteria showed significantly superior AUC (0.770 vs. 0.752, p = .007), sensitivity (76.0

Background:Large language models (LLMs) have shown considerable potential for extracting information from free-text radiology reports, enabling efficient data use, large-scale data mining, and a wide range of secondary analyses and clinical applications. This study aimed to evaluate the performance of LLMs in extracting diagnostically relevant information from multicenter free-text liver magnetic resonance imaging (MRI) reports, explore the clinical utility of LLM-generated structured reports, and investigate optimal prompting strategies for multicenter data. Methods:In this retrospective multicenter study, 800 free-text liver MRI reports from four medical centers (Beijing Friendship Hospital, Tianjin Medical University General Hospital, The Second Affiliated Hospital of Xi'an Jiaotong University, Sir Run Run Shaw Hospital) were collected to evaluate the information extraction performance of two LLMs-DeepSeek-V3 and ChatGPT-4o-using radiologist-annotated structured data as the reference standard. Three prompting strategies were applied: zero-shot prompting, global few-shot prompting (using shared examples across centers), and center-specific few-shot prompting (using examples specific to each center), with example counts set to 2-12. Model performance was evaluated using field-level F1 scores, and report-level extraction success was defined as the correct extraction of ≥80% report fields. Additionally, an exploratory clinical evaluation was conducted using 20 reports from one center, in which 10 radiologists and 10 clinicians evaluated the readability and clinical usability of free-text, manually structured, and LLM-generated reports on a 5-point Likert scale. Results:Few-shot prompting significantly outperformed zero-shot prompting for both LLMs, with the largest gains in macro F1 observed when k was increased from 0 to 2 (∆DeepSeek-V3: global 0.106, center-specific 0.127; ∆ ChatGPT-4o: global 0.086, center-specific 0.107). Performance plateaued at k=4 [DeepSeek-V3: global 0.848 (0.838-0.858), center-specific 0.865 (0.856-0.875); ChatGPT-4o: global 0.835 (0.824-0.845), center-specific 0.861 (0.851-0.870)], with adjacent-k gains <0.01. Center-specific prompting consistently outperformed global prompting (∆F1: 0.017-0.024 for DeepSeek-V3; 0.014-0.026 for ChatGPT-4o). In the exploratory clinical evaluation, structured reports received higher scores for clarity and communication than free-text reports (both P<0.001), while LLM-generated reports received scores comparable to those of manually structured reports (both P>0.05). Conclusions:LLMs demonstrated strong performance in extracting diagnostically relevant information from Chinese multicenter liver MRI reports. In the exploratory clinical evaluation, the LLM-generated structured reports showed the potential to improve report clarity and facilitate clinical communication. Global prompting showed good performance across centers, while center-specific prompting further improved accuracy by adapting to local reporting styles.

BACKGROUND AND PURPOSE:Isolated congenital middle ear malformation (CMEM) contributes significantly to congenital hearing loss and growth problems. This study aims to compare 0.1-mm isotropic ultra-high-resolution CT (U-HRCT) and conventional high-resolution CT (HRCT) for assessing isolated CMEM, using surgical exploration as the standard. MATERIALS AND METHODS:This single-center retrospective study included patients with surgically confirmed isolated CMEM who underwent U-HRCT or HRCT from January 2015 to April 2025. Middle ear abnormalities were identified based on operative outcomes and 4 subtypes were classified via the Teunissen standard. Two neuroradiologists blinded to surgical outcomes reviewed CT images for 10 subtle structural abnormalities and specific subtypes. The comparison of U-HRCT and HRCT in terms of interobserver and intraobserver agreement and detection of structural abnormalities and subtypes of CMEM were analyzed. RESULTS:The U-HRCT and HRCT groups included 61 patients (69 ears) and 37 patients (44 ears), respectively. U-HRCT exhibited significantly higher interobserver and intraobserver agreement and stronger concordance with surgical findings for all 10 abnormalities compared with HRCT. It also showed superior diagnostic sensitivity for CMEM (100.0% versus 90.9%; P = .013) and outperformed HRCT in differentiating clinical subtypes (0.774 versus 0.352; P<.001). U-HRCT achieved accuracies exceeding 0.85 in identifying all abnormalities and outperformed HRCT in detecting specific abnormalities including abnormal long process of the incus, lenticular process, abnormal stapes superstructure, stapes footplate fixation, and oval window atresia (P < .05). CONCLUSIONS:Isotropic 0.1-mm U-HRCT significantly outperforms conventional HRCT in diagnosing CMEM, differencing subtypes, and detecting subtle abnormalities, supporting its clinical superiority for precise preoperative evaluation.

INTRODUCTION:Some patients with Charcot-Marie-Tooth disease (CMT) exhibit prolonged auditory brainstem response (ABR) latencies or abnormal waveforms, suggesting potential damage to the peripheral auditory nerve or central auditory pathways. Diffusion tensor imaging (DTI), a non-invasive neuroimaging technique, can detect the integrity and functional properties of white matter structures with high sensitivity. However, research on the association between DTI characteristics and ABR changes in patients with CMT remains relatively limited, and whether both modalities reflect synergistic damage to central-peripheral nerve axons or myelin sheaths remains unclear. In this study, we aimed to analyze cerebral white matter microstructural abnormalities in patients with CMT using DTI and explore their correlation with ABR, thereby exploring the pathophysiological mechanisms of the central auditory pathway in patients with CMT. METHODS:This study included 14 patients with CMT and 14 healthy controls. DTI data were acquired using a 3.0T MRI scanner. Fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) were calculated. The latencies and interpeak latencies of the auditory pathway were measured using ABR. DTI metrics were compared between the two groups, and the relationship between DTI parameters and ABR results was analyzed in patients with CMT. RESULTS:Compared with the healthy controls, patients with CMT exhibited significantly decreased FA values and significantly increased MD, AD, and RD values in brain regions p < 0.05), including the occipital part of the corona radiata, inferior longitudinal fasciculus, anterior thalamic radiation, and inferior fronto-occipital fasciculus. ABR interpeak latencies correlated positively with FA in the left inferior longitudinal fasciculus and negatively with AD. Three participants did not complete the ABR test. ABR latencies in CMT patients were significantly correlated with AD values in the anterior thalamic radiation and corpus callosum (p < 0.05). CONCLUSION:Abnormal central white matter microstructure (axonal degeneration, demyelination) in patients with CMT may lead to auditory pathway dysfunction by impairing neural conduction efficiency. The multimodal correlation analysis of DTI and ABR provides new insights into the mechanism of central nervous system involvement in CMT, suggesting its potential as a clinical biomarker.

OBJECTIVES:To access the impact of intravenous contrast on the diagnostic efficacy of abdominal spectral CT-based vertebral hydroxyapatite (HAP) concentration measurement for bone mineral density (BMD) assessment in menopausal women, women undergoing menopausal transition, and men older than 50 years with liver cirrhosis. METHODS:One hundred and seventy-two patients (mean age, 63.78 ± 7.20 years; range, 51-82 years) with liver cirrhosis enrolled in the study. These individuals underwent comprehensive abdominal spectral abdominal spectral CT scans, which included both unenhanced and contrast-enhanced arterial phase (AP) and portal venous phase (VP). Vertebral HAP concentration was quantified in the medullary compartment of vertebral body (L1-L3) using HAP-based material decomposition images. The receiver operating characteristic (ROC) curves were adapted to investigate the diagnostic efficacy of using unenhanced, AP and VP HAP concentrations for evaluating BMD validated by T-scores on dual-energy X-ray absorptiometry. RESULTS:HAP values were significantly different among the 3 scan phases (all P < .05). By adjusting thresholds, high accuracies were obtained for detecting low bone mass (osteoporosis or osteopenia) with HAP measurements in all scan phases (all areas-under-ROC > 0.9). The data did not reveal a statistically significant disparity between the unenhanced and AP (P = .055) to detect low bone mass. The efficacies for detecting low bone mass had statistically significant reduction with HAP concentrations in VP (P = .012). CONCLUSIONS:Vertebral HAP concentrations increased in AP and VP compared to unenhanced phase. ADVANCES IN KNOWLEDGE:Adjusting thresholds higher in contrast-enhanced phases may maintain high detection efficacies for low bone mass.

Renal biopsy has certain limitations for diagnosing membranous nephropathy (MN). The aim is to explore the value of MRI for diagnosing MN. MN patients were divided into two subgroups based on estimated glomerular filtration rate, including the mild group and moderate to severe group. Quantitative T1 mapping and renal blood flow (RBF) of bilateral kidneys were measured, including renal cortical T1 mapping (cT1) value, medullary T1 mapping (mT1) value, cortical RBF value (cRBF), and medullary RBF (mRBF) value. The Student’s t-test, Mann–Whitney U test, chi-square test, and one-way analysis of variance were used. Forty-seven MN patients and 54 matched healthy controls (HC) were prospectively enrolled. The cT1 and mT1 average values of HC were significantly lower than those of both MN subgroups (all p < 0.001) after adjusting for age and sex. Compared with the mild group and HC group, the moderate to severe group had lower cRBF (all p < 0.050) and mRBF average values (p = 0.012 and p < 0.001, respectively). The combination model of the T1 mapping and RBF values for differentiating MN from HC had a higher area under the curve of 0.87 (95

Background COPD is a systemic disorder associated with cognitive impairment and affective dysfunction. However, the underlying neurobiological mechanisms remain unclear. This study examines brain reorganisation in patients with COPD and investigates potential neural mediators of cognitive and affective deficits. Methods We enrolled 51 COPD patients and 50 age-and sex-matched healthy controls. All participants underwent high-resolution structural magnetic resonance imaging (MRI) and resting-state functional MRI. Comprehensive neuropsychological assessments for cognitive function (Montreal Cognitive Assessment (MoCA)) and affective symptoms (Beck Depression Inventory (BDI) and State-Trait Anxiety Inventory (STAI)) were conducted. Voxel-wise analyses compared grey matter volume, fractional amplitude of low-frequency fluctuations (fALFF) and functional connectivity strength between groups. Mediation analysis was performed to explore causal pathways linking COPD, brain alterations and cognitive-affective dysfunction. Results COPD patients exhibited significant cognitive deficits (lower MoCA scores) compared with healthy controls, and greater affective symptom burden (higher BDI and STAI scores). Neuroimaging revealed no grey matter volume differences, but distinct functional abnormalities: increased fALFF in bilateral lingual gyri and decreased fALFF in the right inferior orbitofrontal and left middle occipital regions, alongside enhanced long-range functional connectivity strength in the right frontal and fusiform areas (cluster-level p<0.05, family-wise error-corrected). Functional connectivity between bilateral lingual gyri was strengthened in those with COPD and correlated with anxiety symptoms. Critically, mediation analysis demonstrated that increased fALFF in the left lingual gyrus and enhanced interhemispheric connectivity in the lingual region mediated COPD-related cognitive decline, suggesting compensatory mechanisms. Conclusions COPD is associated with functional brain reorganisation, particularly in cognitive and emotional regions, without overt structural changes. The lingual gyrus emerges as a key compensatory hub, where heightened activity and connectivity may mediate cognitive impairment. These findings illuminate neuroprotective pathways in COPD and propose the lingual gyrus as a potential target for interventions aimed at preserving cognitive function.

Background:Simulated microgravity, modeled by head-down tilt (HDT), induces cephalad fluid shifts that perturb intracranial hemodynamics and may affect cognitive function. However, the temporal adaptation of cerebral arterial blood flow (CaBF), both during simulated microgravity and throughout the recovery phase, remains incompletely understood. Methods:In this study, 38 healthy male participants underwent a 7-day -6° HDT protocol followed by a 5-day recovery phase. Four-dimensional flow magnetic resonance imaging (4D flow MRI) was performed at 8 time points [baseline, HDT 12 h, HDT 1 d, HDT 3 d, HDT 7 d, recovery (R) 1 d, R 3 d, and R 5 d] to quantify CaBF and total cerebral blood inflow (TCBI) in the basilar artery (BA), left and right internal carotid arteries (ICAL and ICAR), and left and right middle cerebral arteries (MCAL and MCAR). Systemic vitals and fasting cortisol/renin were collected, and a computerized reaching task assessed reaction time (RT), movement time (MT), and peak velocity (PV). Time effects were tested with repeated-measures analysis of variance (RM ANOVA) or the Friedman test. Predictors of ≥10% TCBI decrease during HDT and ≥10% TCBI increase during the recovery phase were assessed using logistic regression, and flow-behavior associations were examined using Spearman correlation. Results:No significant vessel lumen area changes were found after post-hoc analysis, despite an overall difference observed in the MCAR (χ²=17.40, P=0.015). However, average blood flow significantly changed in the ICAL (χ²=34.16, P<0.001), MCAL (χ²=73.11, P<0.001), and MCAR (χ²=49.02, P<0.001), while BA was stable (RM ANOVA F=0.787, P=0.599) and ICAR showed no significant pairwise effects despite an overall difference (χ²=16.35, P=0.022). TCBI progressively declined during HDT and rebounded rapidly at the onset of recovery (P<0.001). Logistic regression identified systolic blood pressure (SBP) as an independent predictor of a ≥10% TCBI reduction during HDT [P=0.044, odds ratio (OR)=3.004, 95% confidence interval (CI) 1.028-8.777], and baseline cortisol levels predicted significant TCBI decreases from baseline to HDT 7 d (P=0.047, OR=1.306, 95% CI 1.004-1.699). Cognitive-motor testing further revealed phase-dependent changes, with RT and MT generally shortening, most consistently in the no-beep condition, while PV remained stable with beep but increased without beep. Apart from an exploratory negative correlation between TCBI rebound and cued PV (r=-0.360, P=0.031), TCBI changes were largely decoupled from behavioral outcomes. Conclusions:This study demonstrates vessel-specific, lateralized adaptation of cerebral arterial inflow during 7 days of -6° HDT and 5 days of recovery, with anterior circulation more responsive to posture-induced fluid shifts and TCBI gradually decreasing then rapidly rebounding after re-ambulation. Interindividual TCBI susceptibility reflects blood pressure and endocrine status, while cognitive-motor changes remain weakly coupled, underscoring the importance of incorporating early-recovery assessments into HDT studies to better characterize cerebrovascular readaptation after re-ambulation. Clinical Trials Registry:ChiCTR2500096128.

Background:Quantitative magnetic resonance imaging (MRI) is an advanced technique that can map the physical properties (T1, T2, and proton density [PD]) of different tissues, offering crucial insights for disease diagnosis. Nonetheless, the practical application of this technology is indeed constrained by several factors, with the most notable being the protracted scanning duration. Objective:This study aimed to explore whether deep learning (DL)-based superresolution reconstruction of ultrafast whole brain synthetic MRI can obtain quantitative T1/T2/PD maps that are closely approximated to those from routine clinical scans, while substantially shortening scan time and preserving diagnostic image quality. Methods:A total of 151 healthy adults and 7 individuals with different pathologies were prospectively enrolled. Each individual was examined twice on a 3.0T scanner using routine and fast synthetic MRI protocols. The routine scans (acquisition matrix: 320×256) were interpolated to 512 by 512 for clinical display and served as reference images. The fast scans (acquisition matrix: 192×128) were preprocessed to 256 by 256 and used as inputs to a superresolution generative adversarial network (SRGAN), which reconstructed them to the same 512 by 512 interpolated resolution as the reference. For each quantitative chart, 120 (75.95%) healthy individuals' images were used for training, and 38 (24.05%) individuals' images (healthy individuals: n=31, 19.62%; patients: n=7, 4.43%) were used for testing. Agreement was assessed with a paired t test, two 1-sided tests, Bland-Altman analysis, and coefficients of variation. Results:DL reconstructed and reference T1/T2/PD values were strongly correlated (T1: R²=0.98; T2: R²=0.97; and PD: R²=0.99). The slopes of the linear regression were near 1.0 both for T1 (0.9418) and PD (0.9946), whereas T2 values were moderate, as the slope of the linear regression was 0.8057. Additionally, the average biases of T1, T2, and PD values were small (0.93%, -0.85%, and 0.31%, respectively). The intra- and intergroup coefficient of variation for most of the brain regions stayed below 5%, especially for PD values, and after DL reconstruction, it still has quantitative accuracy for lesions. Quantitative and qualitative analyses of image quality also indicate that SRGAN markedly suppressed noise and artifacts in fast acquisitions, restoring structural fidelity (structural similarity image measure) and signal fidelity (peak signal-to-noise ratio) close to the level of routine scans while substantially improving perceptual naturalness over fast scans (as measured by the naturalness image quality evaluator), although not yet matching that of routine imaging. Conclusions:SRGAN superresolution applied to ultrafast synthetic MRI yields whole brain T1, T2, and PD maps that show strong correlation with routine synthetic MRI while halving acquisition time and maintaining diagnostic image quality. Although T1 and PD values exhibit near-ideal agreement, and T2 values demonstrate a moderate systematic underestimation, this approach represents a promising step toward accelerating clinical deployment of quantitative brain imaging.

Due to the scarcity of labeled data, semi-supervised segmentation learning has gained significant attention. However, accurate predictions of hard-to-identify boundaries in medical images remains challenging, especially when learning from unlabeled data. To address this issue, we propose a semi-supervised boundary-aware medical image segmentation method Via Symmetric Boundary-Foreground Collaboration (SBFC). Specifically, SBFC framwork constructs a symmetric dual-task segmentation (SDTS) network containing two symmetric segmentation models, each consisting of a dual-task U-shaped net with one encoder and two task-specific decoders for foreground and boundary segmentation. Using the predicted foreground, boundary probability maps and segmentation and derived boundary labels, a novel compound optimization objective function is proposed. This function integrates Cross-Task Consistency Regularization (CTCR) and Cross-Model Consistency Regularization (CMCR) for unlabeled data with supervised optimization for labeled data. Comprehensive experiments conducted on five public medical image datasets show that our method outperforms state-of-the-art comparative methods in terms of multiple consensus segmentation and boundary evaluation metrics.

Metabolic instability can affect cognitive function, but the mechanisms are largely unknown. To address this, we investigated the association between metabolic parameter variability, brain volume, cerebral blood flow (CBF), and cognitive performance, and evaluated whether CBF and brain volume mediate this relationship. Participants were prospectively included from the Kailuan study. Between 2006 and 2020, the variability in metabolic parameters such as systolic blood pressure, fasting blood glucose, low-density lipoprotein cholesterol, and body mass index was evaluated using the coefficient of variation (CV). Starting in 2020, brain MRI and the Montreal Cognitive Assessment (MoCA) were performed continuously as part of the seventh follow-up visit and subsequent assessments. Generalized linear regression models were used to analyze the associations between metabolic variability, CBF, brain volume, and cognitive performance. Mediation analysis was performed to evaluate the mediation effects of CBF or brain volume. A total of 1894 participants (mean age, 55.4 ± 10.9 years; 51.8

Objectives To establish normative T1 and T2 relaxation times for the liver, pancreas, and kidneys at 5.0 T MRI, providing reference data for imaging parameter optimization and quantitative diagnosis. Materials and Methods Standardized T1/T2 phantoms were used for in vitro validation. From January to March 2025, healthy adults underwent 5.0 T abdominal MRI. T1/T2 maps were obtained using Modified Look-Locker Inversion Recovery (MOLLI) and T2-prepared gradient echo (T2 prep) sequences. Values, reproducibility, and correlations with age, sex, and other factors were evaluated. Results Results from the 10 tubes showed excellent agreement with MOLLI-based T1 and T2-prep-based T2 values and reference standards. The final cohort consisted of 41 participants. In healthy volunteers at 5.0 T MRI, mean T1 values were 1131.68±123.03ms(liver), 1164.63±57.81ms(pancreas), 1753.62±80.44ms (kidney cortex), and 2175.06±100.80ms (kidney medulla); mean T2 values were 31.16±3.37ms, 47.48±4.55ms, 59.36±6.35ms, and 41±4.07ms, respectively. T1 and T2 showed excellent reproducibility. Correlation analysis demonstrated a significant linear negative correlation between R2* and liver T1, and the R2* corrected liver T1 was 1156.57±69.25ms. Liver T2 decreased with age, and both measured and corrected liver T1 decreased with waist-to-hip ratio. Measured T1 and T2 of liver and kidney (cortex and medulla) were all lower in males than females, but liver corrected T1 showed no sex difference. Conclusion This study reports normative T1 and T2 relaxation times of the liver, pancreas, renal cortex, and medulla at 5.0 T MRI, confirming the method's feasibility and reproducibility, thus providing reference values for parameter optimization and future disease-related research. Key Points Question Quantitative 5.0 T MRI is diagnostically significant, but normative reference values for abdominal T1/T2 relaxation times are currently lacking.Findings We established normative T1/T2 values for abdominal organs at 5.0 T MRI, providing a reference for protocol optimization and diagnosis.Clinical relevance This study establishes normative T1 and T2 relaxation times for abdominal organs at 5.0 T MRI. These reproducible, quantitative reference values are essential for optimizing imaging protocols and provide a robust baseline for diagnosing abdominal diseases.

Few-shot medical image segmentation aims to delineate previously unseen anatomical structures using only a few labeled samples. Prototype-based methods have emerged as the dominant paradigm due to their strong generalization ability. However, most existing methods follow a query-agnostic prototype generation paradigm, overlooking intra-class variation. To overcome this limitation, we propose the IteRative Self-guided Prototype Enhancement Network (IR-SPENet), a query-centric framework that progressively refines support prototypes to better adapt to diverse query appearances. Specifically, we design a Hybrid Prototype Generation (HPG) module that constructs a global prototype to represent holistic semantics, together with an adaptive number of local prototypes to encode fine-grained details, enabling multi-granularity modeling of support-query discrepancies. Nevertheless, due to large appearance variations, not all local support prototypes are equally informative for a given query. To selectively emphasize relevant prototypes, we introduce a Query-guided Support Prototype Refinement (Q-SPR) module, which leverages optimal transport to re-weight local support prototypes according to query-specific information. By iteratively applying Q-SPR, IR-SPENet progressively enhances prototype quality and robustness against intra-class variation. Extensive experiments on three public medical image segmentation benchmarks demonstrate that IR-SPENet consistently outperforms existing methods, achieving leading performance.