High-resolution Magnetic Resonance Imaging Research Articles

Deep learning-based super-resolution of structural brain MRI at 1.5T: application to quantitative volume measurement.

This study investigated the feasibility of using deep learning-based super-resolution (DL-SR) technique on low-resolution (LR) images to generate high-resolution (HR) MR images with the aim of scan time reduction. The efficacy of DL-SR was also assessed through the application of brain volume measurement (BVM). In vivo brain images acquired with 3D-T1W from various MRI scanners were utilized. For model training, LR images were generated by downsampling the original 1mm-2mm isotropic resolution images. Pairs of LR and HR images were used for training 3D residual dense net (RDN). For model testing, actual scanned 2mm isotropic resolution 3D-T1W images with one-minute scan time were used. Normalized root-mean-square error (NRMSE), peak signal-to-noise ratio (PSNR), and structural similarity (SSIM) were used for model evaluation. The evaluation also included brain volume measurement, with assessments of subcortical brain regions. The results showed that DL-SR model improved the quality of LR images compared with cubic interpolation, as indicated by NRMSE (24.22% vs 30.13%), PSNR (26.19 vs 24.65), and SSIM (0.96 vs 0.95). For volumetric assessments, there were no significant differences between DL-SR and actual HR images (p > 0.05, Pearson's correlation > 0.90) at seven subcortical regions. The combination of LR MRI and DL-SR enables addressing prolonged scan time in 3D MRI scans while providing sufficient image quality without affecting brain volume measurement.

Large-scale 3D non-Cartesian coronary MRI reconstruction using distributed memory-efficient physics-guided deep learning with limited training data.

To enable high-quality physics-guided deep learning (PG-DL) reconstruction of large-scale 3D non-Cartesian coronary MRI by overcoming challenges of hardware limitations and limited training data availability. While PG-DL has emerged as a powerful image reconstruction method, its application to large-scale 3D non-Cartesian MRI is hindered by hardware limitations and limited availability of training data. We combine several recent advances in deep learning and MRI reconstruction to tackle the former challenge, and we further propose a 2.5D reconstruction using 2D convolutional neural networks, which treat 3D volumes as batches of 2D images to train the network with a limited amount of training data. Both 3D and 2.5D variants of the PG-DL networks were compared to conventional methods for high-resolution 3D kooshball coronary MRI. Proposed PG-DL reconstructions of 3D non-Cartesian coronary MRI with 3D and 2.5D processing outperformed all conventional methods both quantitatively and qualitatively in terms of image assessment by an experienced cardiologist. The 2.5D variant further improved vessel sharpness compared to 3D processing, and scored higher in terms of qualitative image quality. PG-DL reconstruction of large-scale 3D non-Cartesian MRI without compromising image size or network complexity is achieved, and the proposed 2.5D processing enables high-quality reconstruction with limited training data.

Sleep Quality Moderates the Associations between Cardiorespiratory Fitness and Hippocampal and Entorhinal Volume in Middle-Aged and Older Adults.

As individuals age, the entorhinal cortex (ERC) and hippocampus-crucial structures for memory-tend to atrophy, with related cognitive decline. Simultaneously, lifestyle factors that can be modified, such as exercise and sleep, have been separately linked to slowing of brain atrophy and functional decline. Yet, the synergistic impact of fitness and sleep on susceptible brain structures in aging adults remains uncertain. We examined both independent and interactive associations of fitness and subjective sleep quality with regard to ERC thickness and hippocampal volume in 598 middle-aged and older adults from the Human Connectome Lifespan Aging Project. Cardiorespiratory fitness was assessed using the 2-minute walk test (2MWT), while subjective sleep quality was measured with the continuous Pittsburgh Sleep Quality Index (PSQI) global score. High-resolution structural magnetic resonance imaging was used to examine mean ERC thickness and bilateral hippocampal volume. Through multiple linear regression analyses, we investigated the moderating effects of subjective sleep quality on the association between fitness and brain structure, accounting for age, sex, education, body mass index, gait speed, and subjective physical activity. We found that greater cardiorespiratory fitness, but not subjective sleep quality, was positively associated with bilateral hippocampal volume and ERC thickness. Notably, significant interaction effects suggest poor subjective sleep quality was associated with a weaker association between fitness and both hippocampal volume and ERC thickness. Findings suggest the potential importance of both cardiorespiratory fitness and subjective sleep quality in preserving critical, age-vulnerable brain structures. Interventions targeting brain health should consider potential combined effects of sleep and fitness on brain health.

Exploring the link between tooth loss, cognitive function, andbrain wellness in the context of healthy aging.

The aim of this study was to evaluate the utility of using MRI-derived tooth count, an indirect and nonspecific indicator of oral/periodontal health, and brain age gap (BAG), an MRI-based measure of premature brain aging, in predicting cognition in a population of otherwise healthy adults. This retrospective study utilized data from 329 participants from the University of South Carolina's Aging Brain Cohort Repository. Participants underwent neuropsychological testing including the Montreal Cognitive Assessment (MoCA), completed an oral/periodontal health questionnaire, and submitted to high-resolution structural MRI imaging. The study compared variability on cognitive scores (MoCA) accounted for by MRI-derived BAG, MRI-derived total tooth count, and self-reported oral/periodontal health. We report a significant positive correlation between the total number of teeth and MoCA total scores after controlling for age, sex, and race, indicating a robust relationship between tooth count and cognition, r(208) = .233, p < .001. In a subsample of participants identified as being at risk for MCI (MoCA <= 25, N = 36) inclusion of MRI-based tooth count resulted in an R2 change of .192 (H0 = 0.138 → H1 = 0.330), F(1,31) = 8.86, p = .006. Notably, inclusion of BAG, a valid and reliable measure of overall brain health, did not significantly improve prediction of MoCA scores in similar linear regression models. Our data support the idea that inclusion of MRI-based total tooth count may enhance the ability to predict clinically meaningful differences in cognitive abilities in healthy adults. This study contributes to the growing body of evidence linking oral/periodontal health with cognitive function.

Behavior of Extracranial-to-Intracranial Extended Arterial Dissections of the Vertebral Artery.

Vertebral artery dissections (VADs) may extend from the extracranial to the intracranial vasculature (e+iVAD). We evaluated how the characteristics of e+iVAD differed from those of intracranial VAD (iVAD). From 2002 to 2019, among consecutive patients with cervicocephalic dissection, those with iVAD and e+iVAD were included, and their clinical characteristics were compared. In patients with unruptured dissections, a composite clinical outcome of subsequent ischemic events, subsequent hemorrhagic stroke, or mortality was evaluated. High-resolution magnetic resonance images were analyzed to evaluate intracranial remodeling index. Among 347 patients, 51 (14.7%) had e+iVAD and 296 (85.3%) had iVAD. The hemorrhagic presentation occurred solely in iVAD (0.0% versus 19.3%), whereas e+iVAD exhibited higher ischemic presentation (84.3% versus 27.4%; P<0.001). e+iVAD predominantly presented steno-occlusive morphology (88.2% versus 27.7%) compared with dilatation patterns (11.8% versus 72.3%; P<0.001) of iVAD. The ischemic presentation was significantly associated with e+iVAD (iVAD as a reference; adjusted odds ratio, 3.97 [95% CI, 1.67-9.45]; P=0.002]). Patients with unruptured VAD showed no differences in the rate of composite clinical outcome between the groups (log-rank, P=0.996). e+iVAD had a lower intracranial remodeling index (1.4±0.3 versus 1.6±0.4; P<0.032) and a shorter distance from dural entry to the maximal dissecting segment (6.9±8.4 versus 15.7±7.4; P<0.001). e+iVAD is associated with lower rates of hemorrhages and higher rates of ischemia than iVAD at the time of admission. This may be explained by a lower intracranial remodeling index and less deep intrusion of the dissecting segment into the intracranial space.

Lanthanide Inorganic Nanoparticles Enhance Semiconducting Polymer Nanoparticles Afterglow Luminescence for In Vivo Afterglow/Magnetic Resonance Imaging.

Dual/multimodal imaging strategies are increasingly recognized for their potential to provide comprehensive diagnostic insights in cancer imaging by harnessing complementary data. This study presents an innovative probe that capitalizes on the synergistic benefits of afterglow luminescence and magnetic resonance imaging (MRI), effectively eliminating autofluorescence interference and delivering a superior signal-to-noise ratio. Additionally, it facilitates deep tissue penetration and enables noninvasive imaging. Despite the advantages, only a limited number of probes have demonstrated the capability to simultaneously enhance afterglow luminescence and achieve high-resolution MRI and afterglow imaging. Herein, we introduce a cutting-edge imaging platform based on semiconducting polymer nanoparticles (PFODBT) integrated with NaYF4@NaGdF4 (Y@Gd@PFO-SPNs), which can directly amplify afterglow luminescence and generate MRI and afterglow signals in tumor tissues. The proposed mechanism involves lanthanide nanoparticles producing singlet oxygen (1O2) upon white light irradiation, which subsequently oxidizes PFODBT, thereby intensifying afterglow luminescence. This innovative platform paves the way for the development of high signal-to-background ratio imaging modalities, promising noninvasive diagnostics for cancer.

Association of vulnerable plaques with white matter hyperintensities on high-resolution magnetic resonance imaging.

One of the widespread manifestations of cerebral small vessel disease (CSVD) of the brain parenchyma is white matter lesion, which appears as white matter hyperintensities (WMHs) on magnetic resonance imaging (MRI). Previous studies have illustrated that large artery atherosclerosis is related to CSVD, but the precise progress of pathogenesis remains unknown. High-resolution MRI (HR-MRI) has the ability to delineate intracranial vascular walls, enabling a thorough exploration of the structure and composition of unstable plaques. This study aimed to apply HR-MRI to characterize the wall changes and plaque characteristics of middle cerebral arteries in patients with WMHs and to investigate the correlation between plaque vulnerability parameters and different degrees of WMHs. In this study, 138 patients with acute ischemic stroke at Harbin Medical University's First Clinical Hospital (May 2021 to October 2023) were cross-sectionally reviewed and underwent conventional brain and HR-MRI using T1-weighted 3D volumetric isotropic turbo spin echo acquisition (T1W-3D-VISTA) of the unilateral middle cerebral artery (MCA). According to Fazekas grade (0-6), the patients were divided into two groups: Fazekas score 0-2, no-or-mild WMHs; and Fazekas 3-6, moderate-to-severe WMHs. The intraplaque hemorrhage, plaque distribution, plaque enhancement, plaque load, remodeling pattern, and stenosis of the two groups were measured. Binary logistic regression analysis was conducted to evaluate the relationship between vulnerable plaques and WMHs. Of the participants who were initially considered for inclusion, 71 were deemed eligible, among whom 34 were placed in the no-or-mild WMH group and 37 in the moderate-to-severe WMH group. Between the two groups, there were significant differences in intraplaque hemorrhage (P=0.01), a wide distribution (P=0.02), and plaque enhancement (P=0.02). Univariate analysis showed that WMHs were associated with age [odds ratio (OR) =1.080; 95% confidence interval (CI): 1.020-1.144; P=0.008], hypertension (OR =3.500; 95% CI: 1.276-9.597; P=0.01), intraplaque hemorrhage (OR =3.955; 95% CI: 1.247-12.538; P=0.02), a wide distribution (OR =3.067; 95% CI: 1.159-8.115; P=0.02), and significant plaque enhancement (OR =4.372; 95% CI: 1.101-17.358; P=0.03); however, the multivariate results showed that the only independent factors associated with WMHs were age (OR =1.095; 95% CI: 1.019-1.176; P=0.01) and intraplaque hemorrhage (OR =5.88; 95% CI: 1.466-23.592; P=0.01). Our findings suggest that age and intraplaque hemorrhage may be associated with more severe WMHs in patients with acute ischemic stroke, which may be helpful for further clinical examination and intervention treatment.

Identification of patients with internet gaming disorder via a radiomics-based machine learning model of subcortical structures in high-resolution T1-weighted MRI

It is of vital importance to establish an objective and reliable model to facilitate the early diagnosis and intervention of internet gaming disorder (IGD). A total of 133 patients with IGD and 110 healthy controls (HCs) were included. We extracted radiomic features of subcortical structures in high-resolution T1-weighted MRI. Different combinations of four feature selection methods (analysis of variance, Kruskal–Wallis, recursive feature elimination and relief) and ten classification algorithms were used to identify the most robust combined models for distinguishing IGD patients from HCs. Furthermore, a nomogram incorporating radiomic signatures and independent clinical factors was developed. Calibration curve and decision curve analyses were used to evaluate the nomogram. The combination of analysis of variance selector and logistic regression classifier identified that the radiomic model constructed with 20 features from the right caudate nucleus and amygdala showed better IGD screening performance. The radiomic model produced good areas under the curves (AUCs) in the training, validation and test cohorts (AUCs of 0.961, 0.903 and 0.895, respectively). In addition, sex, internet addiction test scores and radiomic scores were included in the nomogram as independent risk factors for IGD. Analysis of the correction curve and decision curve showed that the clinical-radiomic model has good reliability (C-index: 0.987). The nomogram incorporating radiomic features of subcortical structures and clinical characteristics achieved satisfactory classification performance and could serve as an effective tool for distinguishing IGD patients from HCs.

The clinical characteristics of neutrophil extracellular trap in patients with severe cerebral venous sinus thrombosis and its prognostic value in acute and subacute patients

Objective: To explore the clinical characteristics of neutrophil extracellular trap (NET) in patients with severe cerebral venous sinus thrombosis (CVST) and to study their prognostic value in the acute and subacute phases. Methods: This study is a retrospective case series analysis. Clinical and pathological data of 52 patients with severe cerebral venous sinus thrombosis who underwent endovascular treatment in the Department of Neurosurgery, Tianjin Huanhu Hospital from June 2019 to June 2022 were retrospectively analyzed. There were 20 males and 32 females, with an age of (40.1±13.6) years(range:18 to 66 years). Forty-five healthy physical examinees were included in the control group. High-resolution MRI was used to stage the thrombus, with 11 cases in the acute group, 28 cases in the subacute group, and 13 cases in the chronic group. Thrombus specimens were obtained through endovascular treatment, and the fluorescence intensity of NET in peripheral blood at different time points was analyzed by immunofluorescence contrast,including the double-stranded DNA structure and adhesion protein components (citrolinated histone H3 (CitH3), myeloperoxidase-DNA complex(MPO-DNA), neutrophil elastase (NE)). The NET markers were determined by ELISA. Spearman rank correlation analysis was used to analyze the correlation between the NET markers in peripheral blood of patients with severe cerebral venous sinus thrombosis in the acute and subacute phases and the volume of venous sinus thrombus, the degree of venous sinus recanalization after treatment, and the discharge modified Rankin scale(mRS)score. The accuracy of NET markers in predicting the prognosis of patients with severe cerebral venous sinus thrombosis was analyzed by drawing receiver operating characteristic (ROC) curve and calculating the area under the curve (AUC). Results: The results of immunofluorescence staining and ELISA showed that no NET structure was formed in the peripheral blood of the control group, while CitH3, MPO-DNA and NE levels in the peripheral blood of CVST patients were increased, among which the acute stage group was the highest, followed by the subacute group, and the chronic group was the lowest. Spearman correlation analysis showed that CitH3, MPO-DNA and NE levels in peripheral blood of patients in acute group and subacute group were positively correlated with thrombus volume and mRS score at discharge (P<0.05). The levels of CitH3 and MPO-DNA in peripheral blood of patients with complete venous sinus recanalization were lower than those of patients with partial venous sinus recanalization (P<0.01). ROC curve analysis results showed that MPO-DNA and NE had no predictive ability for the prognosis of CVST patients (P values were 0.614 and 0.324, respectively), and the AUC of CitH3 was 0.800 (95%CI: 0.638~0.962, P=0.032), the best cut-off value was 13.5 μg/L, the sensitivity was 100%, and the specificity was 58.8%. Conclusions: A large number of NET are formed in patients with severe cerebral venous sinus thrombosis in acute stage. Patients with severe cerebral venous sinus thrombosis in acute stage and subacute stage with high peripheral blood NET content has a low rate of complete sinus revascularization and poor neurological function recovery after treatment.

Neuro-Behcet’s Disease Manifesting as Bilateral Fornix and Left Thalamus Infarction

Neuro-Behcet’s disease (NBD) is defined as neurological involvement in Behcet’s disease. A 32-year-old man was admitted due to sudden memory impairment and had a history of recurrent oral/genital ulcers. Brain magnetic resonance imaging (MRI) revealed ischemic lesions in the bilateral fornix and left thalamus, and high-resolution vessel wall MRI demonstrated vasculitis in the anterior communicating artery. We report a rare case of NBD that presented as vasculitis and ischemic stroke in the bilateral fornix and thalamus.

Three-dimensional Spinal Canal Morphometric Analysis and Relevant Spinal Cord Occupational Ratios in Congenital Cervical Spinal Stenosis: A classification algorithm of the stenosis phenotypes and data driven decompression approach.

Three-dimensional Spinal Canal Morphometric Analysis and Relevant Spinal Cord Occupational Ratios in Congenital Cervical Spinal Stenosis: A classification algorithm of the stenosis phenotypes and data driven decompression approach.

Alterations in Brain Morphometric Networks and Their Relationship with Memory Dysfunction in Patients with Type 2 Diabetes Mellitus.

Cognitive dysfunction, a significant complication of type 2 diabetes mellitus (T2DM), can potentially manifest even from the early stages of the disease. Despite evidence of global brain atrophy and related cognitive dysfunction in early-stage T2DM patients, specific regions vulnerable to these changes have not yet been identified. The study enrolled patients with T2DM of less than five years' duration and without chronic complications (T2DM group, n=100) and demographically similar healthy controls (control group, n=50). High-resolution T1-weighted magnetic resonance imaging data were subjected to independent component analysis to identify structurally significant components indicative of morphometric networks. Within these networks, the groups' gray matter volumes were compared, and distinctions in memory performance were assessed. In the T2DM group, the relationship between changes in gray matter volume within these networks and declines in memory performance was examined. Among the identified morphometric networks, the T2DM group exhibited reduced gray matter volumes in both the precuneus (Bonferroni-corrected p=0.003) and insular-opercular (Bonferroni-corrected p=0.024) networks relative to the control group. Patients with T2DM demonstrated significantly lower memory performance than the control group (p=0.001). In the T2DM group, reductions in gray matter volume in both the precuneus (r=0.316, p=0.001) and insular-opercular (r=0.199, p=0.047) networks were correlated with diminished memory performance. Our findings indicate that structural alterations in the precuneus and insular-opercular networks, along with memory dysfunction, can manifest within the first 5 years following a diagnosis of T2DM.

The relationship between symptomatic status and aneurysm wall enhancement characteristics of single unruptured intracranial aneurysm.

We aimed to analyze the aneurysm wall enhancement (AWE) characteristics of asingle unruptured intracranial aneurysm (UIA) and observe the relationship between the symptoms of asingle UIA and the aneurysm wall. In our hospital, 85patients diagnosed with asingle UIA using computed tomography angiography (CTA) were retrospectively analyzed. The patients were divided into symptomatic and asymptomatic groups, including 46asymptomatic and 39symptomatic aneurysms. High-resolution magnetic resonance imaging of the vascular wall (HR-MR-VWI) was utilized to ascertain the presence, degree, and extent of AWE and thick-wall enhancement. In addition to AWE characteristics, morphological parameters of aneurysms, such as maximal size, shape, height, neck width, aspect ratio (AR), and size ratio (SR), were scanned using CTA. The differences in the parameters of asingle UIA between the two groups were compared. An investigation explored the correlation between the symptom status of asingle UIA and AWE. We observed acorrelation between symptom status and maximal size, height, and neck width for asingle UIA, the presence or absence of AWE, and the levels and boundaries of AWE and thick-wall reinforcement. This study found that the AWE range was independently correlated with symptom status in the multivariate regression analysis. Alarger AWE range was an independent risk factor for the onset of symptoms in asingle UIA.

Intensity Score of Vessel Wall Contrast Enhancement in MRI Allows Prediction of Disease Progression in Moyamoya Angiopathy.

The underlying pathophysiological cause of moyamoya angiopathy (MMA) is still unclear. High-resolution vessel wall imaging has become a useful tool. The aim was to study vessel wall contrast-enhancement (VW-CE) as an imaging marker to predict disease progression in MMA. Patients with MMA, who had undergone serial contrast-enhanced high-resolution MRI with concomitant and follow-up digital subtraction angiography, were analyzed retrospectively. VW-CE was semiquantified by measurement of the signal intensity of the vessel wall in in contrast-enhanced high-resolution MRI. A comparative quotient with the contrast-intensity of the pituitary stalk was calculated and graded accordingly from grade 1 to 5. VW-CE status was correlated with disease status, stroke, cerebrovascular reactivity in CO2-triggered blood-oxygen level-dependent MRI, angiographic disease progression, revascularization surgery, and follow-up imaging. Forty eight patients met the inclusion criteria. N = 56 MRI and digital subtraction angiography time-intervals were evaluated for 12 vessel sections per hemisphere each (N = 1344). N = 38 (79%) patients showed VW-CE and N = 10 (21%) did not. VW-CE was only observed in the terminal internal carotid artery and the proximal circle of Willis (N = 96/1344). Notably, patients with VW-CE significantly more often presented with acute infarction in the concomitant MRI. The incidence of angiographically proven disease progression was significantly associated with the incidence of VW-CE, and time to disease progression was earlier in higher grades of VW-CE compared with lower grades. VW-CE is a semiquantifiable marker for disease activity in patients with MMA and associated with disease progression and increased risk of stroke. VW-CE analysis can be routinely performed in patients with MMA to estimate the risk for disease progression and stroke.

The Contribution of Vessel Wall Magnetic Resonance Imaging to the Diagnosis of Primary and Secondary Central Nervous System Vasculitis.

To describe high-resolution brain vessel wall MRI (VW-MRI) patterns and morphological brain findings in central nervous system (CNS) vasculitis patients. Fourteen patients with confirmed CNS Vasculitis from two tertiary centers underwent VW-MRI using a 3T scanner. The images were reviewed by two neuroradiologists to assess vessel wall enhancement characteristics and locations. Fourteen patients were included (six females; average age 48 ± 19 years). Diagnoses included primary CNS vasculitis (PCNSV) in six patients and secondary CNS vasculitis (SCNSV) in eight, half of which were infection-related. Thirteen patients showed vessel wall enhancement, which was intense in eleven patients (84.6%) and concentric in twelve (92.3%), affecting the anterior circulation in nine patients (69.2%), posterior in two patients (15.4%), and both circulations in two patients (15.4%). The enhancement patterns were similar across different CNS vasculitis types. DWI changes corresponded with areas of vessel wall enhancement in 77% of patients. Conclusions: CNS vasculitis is often associated with intense, concentric vessel wall enhancement in VW-MRI, especially in the anterior circulation. The consistent presence of DWI alterations in affected territories suggests a possible link to microembolization or hypoperfusion. These imaging findings complement parenchymal brain MRI and MRA/DSA data, potentially increasing the possibility of a clinical diagnosis of CNS vasculitis.

Preoperative prediction of perineural invasion of rectal cancer based on a magnetic resonance imaging radiomics model: A dual-center study.

Perineural invasion (PNI) has been used as an important pathological indicator and independent prognostic factor for patients with rectal cancer (RC). Preoperative prediction of PNI status is helpful for individualized treatment of RC. Recently, several radiomics studies have been used to predict the PNI status in RC, demonstrating a good predictive effect, but the results lacked generalizability. The preoperative prediction of PNI status is still challenging and needs further study. To establish and validate an optimal radiomics model for predicting PNI status preoperatively in RC patients. This retrospective study enrolled 244 postoperative patients with pathologically confirmed RC from two independent centers. The patients underwent pre-operative high-resolution magnetic resonance imaging (MRI) between May 2019 and August 2022. Quantitative radiomics features were extracted and selected from oblique axial T2-weighted imaging (T2WI) and contrast-enhanced T1WI (T1CE) sequences. The radiomics signatures were constructed using logistic regression analysis and the predictive potential of various sequences was compared (T2WI, T1CE and T2WI + T1CE fusion sequences). A clinical-radiomics (CR) model was established by combining the radiomics features and clinical risk factors. The internal and external validation groups were used to validate the proposed models. The area under the receiver operating characteristic curve (AUC), DeLong test, net reclassification improvement (NRI), integrated discrimination improvement (IDI), calibration curve, and decision curve analysis (DCA) were used to evaluate the model performance. Among the radiomics models, the T2WI + T1CE fusion sequences model showed the best predictive performance, in the training and internal validation groups, the AUCs of the fusion sequence model were 0.839 [95% confidence interval (CI): 0.757-0.921] and 0.787 (95%CI: 0.650-0.923), which were higher than those of the T2WI and T1CE sequence models. The CR model constructed by combining clinical risk factors had the best predictive performance. In the training and internal and external validation groups, the AUCs of the CR model were 0.889 (95%CI: 0.824-0.954), 0.889 (95%CI: 0.803-0.976) and 0.894 (95%CI: 0.814-0.974). Delong test, NRI, and IDI showed that the CR model had significant differences from other models (P < 0.05). Calibration curves demonstrated good agreement, and DCA revealed significant benefits of the CR model. The CR model based on preoperative MRI radiomics features and clinical risk factors can preoperatively predict the PNI status of RC noninvasively, which facilitates individualized treatment of RC patients.

Inter-scanner super-resolution of 3D cine MRI using a transfer-learning network for MRgRT.

Deep-learning networks for super-resolution (SR) reconstruction enhance the spatial-resolution of 3D magnetic resonance imaging (MRI) for MR-guided radiotherapy (MRgRT). However, variations between MRI scanners and patients impact the quality of SR for real-time 3D low-resolution (LR) cine MRI. In this study, we present a personalized super-resolution (psSR) network that incorporates transfer-learning to overcome the challenges in inter-scanner SR of 3D cine MRI.&#xD;Approach: Development of the proposed psSR network comprises two-stages: 1) a cohort-specific SR (csSR) network using clinical patient datasets, and 2) a psSR network using transfer-learning to target datasets. The csSR network was developed by training on breath-hold and respiratory-gated high-resolution (HR) 3D MRIs and their k-space down-sampled LR MRIs from 53 thoracoabdominal patients scanned at 1.5 T. The psSR network was developed through transfer-learning to retrain the csSR network using a single breath-hold HR MRI and a corresponding 3D cine MRI from 5 healthy volunteers scanned at 0.55 T. Image quality was evaluated using the peak-signal-noise-ratio (PSNR) and the structure-similarity-index-measure (SSIM). The clinical feasibility was assessed by liver contouring on the psSR MRI using an auto-segmentation network and quantified using the Dice-similarity-coefficient (DSC).&#xD;Results. Mean PSNR and SSIM values of psSR MRIs were increased by 57.2% (13.8 to 21.7) and 94.7% (0.38 to 0.74) compared to cine MRIs, with the reference 0.55 T breath-hold HR MRI. In the contour evaluation, DSC was increased by 15% (0.79 to 0.91). Average time consumed for transfer-learning was 90 s, psSR was 4.51 ms per volume, and auto-segmentation was 210 ms, respectively.&#xD;Significance. The proposed psSR reconstruction substantially increased image and segmentation quality of cine MRI in an average of 215 ms across the scanners and patients with less than 2 minutes of prerequisite transfer-learning. This approach would be effective in overcoming cohort- and scanner-dependency of deep-learning for MRgRT.&#xD.

MRI morphometry of the anterior and posterior cerebellar vermis and its relationship to sensorimotor and cognitive functions in children

IntroductionThe human cerebellum emerges as a posterior brain structure integrating neural networks for sensorimotor, cognitive, and emotional processing across the lifespan. Developmental studies of the cerebellar anatomy and function are scant. We examine age-dependent MRI morphometry of the anterior cerebellar vermis, lobules I-V and posterior neocortical lobules VI-VII and their relationship to sensorimotor and cognitive functions. MethodsTypically developing children (TDC; n=38; age 9–15) and healthy adults (HAC; n=31; 18–40) participated in high-resolution MRI. Rigorous anatomically informed morphometry of the vermis lobules I-V and VI-VII and total brain volume (TBV) employed manual segmentation computer-assisted FreeSurfer Image Analysis Program [http://surfer.nmr.mgh.harvard.edu]. The neuropsychological scores (WASI-II) were normalized and related to volumes of anterior, posterior vermis, and TBV. ResultsTBVs were age independent. Volumes of I-V and VI-VII were significantly reduced in TDC. The ratio of VI-VII to I-V (∼60%) was stable across age-groups; I-V correlated with visual-spatial-motor skills; VI-VII with verbal, visual-abstract and FSIQ. ConclusionsIn TDC neither anterior I-V nor posterior VI-VII vermis attained adult volumes. The "inverted U" developmental trajectory of gray matter peaking in adolescence does not explain this finding. The hypothesis of protracted development of oligodendrocyte/myelination is suggested as a contributor to TDC's lower cerebellar vermis volumes.

MRI super-resolution using similarity distance and multi-scale receptive field based feature fusion GAN and pre-trained slice interpolation network

Challenges arise in achieving high-resolution Magnetic Resonance Imaging (MRI) to improve disease diagnosis accuracy due to limitations in hardware, patient discomfort, long acquisition times, and high costs. While Convolutional Neural Networks (CNNs) have shown promising results in MRI super-resolution, they often don't look into the structural similarity and prior information available in consecutive MRI slices. By leveraging information from sequential slices, more robust features can be obtained, potentially leading to higher-quality MRI slices. We propose a multi-slice two-dimensional (2D) MRI super-resolution network that combines a Generative Adversarial Network (GAN) with feature fusion and a pre-trained slice interpolation network to achieve three-dimensional (3D) super-resolution. The proposed model requires consecutively acquired three low-resolution (LR) MRI slices along a specific axis, and achieves the reconstruction of the MRI slices in the remaining two axes. The network effectively enhances both in-plane and out-of-plane resolution along the sagittal axis while addressing computational and memory constraints in 3D super-resolution. The proposed generator has a in-plane and out-of-plane Attention (IOA) network that fuses both in-plane and out-plane features of MRI dynamically. In terms of out-of-plane attention, the network merges features by considering the similarity distance between features and for in-plane attention, the network employs a two-level pyramid structure with varying receptive fields to extract features at different scales, ensuring the inclusion of both global and local features. Subsequently, to achieve 3D MRI super-resolution, a pre-trained slice interpolation network is used that takes two consecutive super-resolved MRI slices to generate a new intermediate slice. To further enhance the network performance and perceptual quality, we introduce a feature up-sampling layer and a feature extraction block with Scaled Exponential Linear Unit (SeLU). Moreover, our super-resolution network incorporates VGG loss from a fine-tuned VGG-19 network to provide additional enhancement. Through experimental evaluations on the IXI dataset and BRATS dataset, using the peak signal-to-noise ratio (PSNR), structural similarity index measure (SSIM) and the number of training parameters, we demonstrate the superior performance of our method compared to the existing techniques. Also, the proposed model can be adapted or modified to achieve super-resolution for both 2D and 3D MRI data.

The relation between meniscal dynamics and tibiofemoral kinematics

Over the past 30 years, research on meniscal kinematics has been limited by challenges such as low-resolution imaging and capturing continuous motion from static data. This study aimed to develop a computational knee model that overcomes these limitations and enables the continuous assessment of meniscal dynamics. A high-resolution MRI dataset (n = 11) was acquired in 4 configurations of knee flexion. In each configuration, the menisci were modeled based on the underlying osseous anatomy. Principal Polynomial Shape Analysis (PPSA) was employed for continuous meniscal modeling. Maximal medial anterior horn displacement occurred in 60° of flexion, equaling 6.24 mm posteromedial, while the posterior horn remained relatively stable. At 90° of flexion, the lateral anterior and posterior horn displaced posteromedially, amounting 5.70 mm and 6.51 mm respectively. The maximal observed Average Surface Distance (ASD) equaled 0.70 mm for lateral meniscal modeling in 90° of flexion. Based on our results, a strong relation between meniscal dynamics and tibiofemoral kinematics was confirmed. Expanding on static meniscal modeling and employing PPSA, we derived and validated a standardized and systematic methodological workflow.