AJNR. American journal of neuroradiology最新文献

{"title":"Magnetic Resonance Imaging versus Noncontrast Computed Tomography for Selecting Patients with Acute Ischemic Stroke of Large Vessel Occlusion for Endovascular Thrombectomy: A Systematic Review and Meta-Analysis.","authors":"Seyed Behnam Jazayeri, Sherief Ghozy, Alireza Hasanzadeh, Mohamed Elfil, Ali Ahmadzade, Ehsan Naseh, Alzhraa S Abbas, Ramanathan Kadirvel, Alejandro A Rabinstein, David F Kallmes","doi":"10.3174/ajnr.A8775","DOIUrl":"https://doi.org/10.3174/ajnr.A8775","url":null,"abstract":"<p><strong>Background: </strong>Neuroimaging in the acute phases after the onset of the stroke symptoms is necessary to determine large vessel occlusion presence as well as the extent of the ischemic insult before deeming eligibility for endovascular thrombectomy (EVT).</p><p><strong>Purpose: </strong>To evaluate the clinical outcomes in acute ischemic stroke patients selected for EVT based on initial imaging; non-contrast computed tomography (NCCT) compared to those selected using magnetic resonance imaging (MRI).</p><p><strong>Data sources: </strong>PubMed, Embase, Scopus, and Web of Science were searched from inception to August, 2024.</p><p><strong>Study selection: </strong>We included observational studies comparing functional independence (mRS 0-2), successful reperfusion (TICI 2b-3), symptomatic intracerebral hemorrhage (sICH) or mortality in patients selected for EVT using NCCT±CT angiography versus MRI ±MR angiography. We excluded studies that used perfusion imaging in their patient selection for EVT.</p><p><strong>Data analysis: </strong>Data were pooled using random-effects model, and heterogeneity was assessed using I² statistics. A subgroup analysis was performed to determine the effect of treatment window (<6h vs >6h from last known well). The quality of eligible studies was assessed by using Newcastle Ottawa Scale.</p><p><strong>Data synthesis: </strong>Seven studies (n=3,940 patients) met the inclusion criteria. Two studies had low risk of bias and others had some concerns. Patients with MRI selection showed better chances of functional independence (Odds ratio (OR), 1.85 [95% CI, 1.28-2.67]; p<0.01, I²=45%), lower rates of sICH (OR 0.59, 95% CI 0.39-0.89; p=0.01, I2=0%), reduced 90 days mortality (OR 0.63, 95% CI 0.51-0.78; p<0.01, I²=0%) and no difference in successful reperfusion (OR 0.99, 95% CI 0.62-1.58; p=0.95, I²=0%) compared to NCCT in patients treated within 6 hours of stroke onset. There were no significant differences in any endpoints between MRI and NCCT for patients treated beyond 6 hours.</p><p><strong>Limitations: </strong>Our meta-analysis comprised only observational studies, with different populations and imaging protocols limiting the strength of the conclusions.</p><p><strong>Conclusions: </strong>Within the crucial <6-hour window, MRI's superior patient selection justifies its use despite longer acquisition times. Beyond 6 hours, the focus should shift to rapid EVT access rather than imaging modality choice, as the benefits of MRI diminish.</p><p><strong>Abbreviations: </strong>EVT = Endovascular Thrombectomy; IVT = Intravenous Thrombolysis; AIS-LVO = Acute Ischemic Stroke-Large Vessel Occlusion.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning-based generation of DSC MRI parameter maps using DCE MRI data.","authors":"Haoyang Pei, Yixuan Lyu, Sebastian Lambrecht, Doris Lin, Li Feng, Fang Liu, Paul Nyquist, Peter van Zijl, Linda Knutsson, Xiang Xu","doi":"10.3174/ajnr.A8768","DOIUrl":"https://doi.org/10.3174/ajnr.A8768","url":null,"abstract":"<p><strong>Background and purpose: </strong>Perfusion and perfusion-related parameter maps obtained using dynamic susceptibility contrast (DSC) MRI and dynamic contrast enhanced (DCE) MRI are both useful for clinical diagnosis and research. However, using both DSC and DCE MRI in the same scan session requires two doses of gadolinium contrast agent. The objective was to develop deep-learning based methods to synthesize DSC-derived parameter maps from DCE MRI data.</p><p><strong>Materials and methods: </strong>Independent analysis of data collected in previous studies was performed. The database contained sixty-four participants, including patients with and without brain tumors. The reference parameter maps were measured from DSC MRI performed following DCE MRI. A conditional generative adversarial network (cGAN) was designed and trained to generate synthetic DSC-derived maps from DCE MRI data. The median parameter values and distributions between synthetic and real maps were compared using linear regression and Bland-Altman plots.</p><p><strong>Results: </strong>Using cGAN, realistic DSC parameter maps could be synthesized from DCE MRI data. For controls without brain tumors, the synthesized parameters had distributions similar to the ground truth values. For patients with brain tumors, the synthesized parameters in the tumor region correlated linearly with the ground truth values. In addition, areas not visible due to susceptibility artifacts in real DSC maps could be visualized using DCE-derived DSC maps.</p><p><strong>Conclusions: </strong>DSC-derived parameter maps could be synthesized using DCE MRI data, including susceptibility-artifact-prone regions. This shows the potential to obtain both DSC and DCE parameter maps from DCE MRI using a single dose of contrast agent.</p><p><strong>Abbreviations: </strong>cGAN=conditional generative adversarial network; K^trans=volume transfer constant; rCBV=relative cerebral blood volume; rCBF=relative cerebral blood flow; V_e=extravascular extracellular volume; V_p=plasma volume.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Predicting 1p/19q Codeletion Status in Glioma Using MRI-Derived Radiomics; A Systematic Review and Meta-Analysis of Diagnostic Accuracy.","authors":"Amir Mahmoud Ahmadzadeh, Nima Broomand Lomer, Mohammad Amin Ashoobi, Danial Elyassirad, Benyamin Gheiji, Mahsa Vatanparast, Seyed Ali Jalalian, Mehdi Arab, Farrokh Seilanian Toosi, Girish Bathla, Shahriar Faghani","doi":"10.3174/ajnr.A8771","DOIUrl":"https://doi.org/10.3174/ajnr.A8771","url":null,"abstract":"<p><strong>Background: </strong>The 1p/19q codeletion is a key genetic marker in gliomas and plays a crucial role in prognosis and treatment decisions. Traditional methods for detecting this genetic alteration rely on invasive tissue biopsies.</p><p><strong>Purpose: </strong>This systematic review and meta-analysis aimed to evaluate the performance of magnetic resonance imaging (MRI)-derived radiomics-based models to predict glioma 1p/19q codeletion status.</p><p><strong>Data sources: </strong>A literature search was conducted in four databases-PubMed, Web of Science, Embase, and Scopus.</p><p><strong>Study selection: </strong>We selected the studies that assessed the performance of radiomics-based models in determining 1p/19q codeletion status.</p><p><strong>Data analysis: </strong>The METhodological RadiomICs Score (METRICS) was used to evaluate study quality. Pooled diagnostic estimates were calculated, and heterogeneity was assessed using the I² statistic. Subgroup and sensitivity analyses were performed to investigate potential sources of heterogeneity. Deeks' funnel plot was used to assess publication bias.</p><p><strong>Data synthesis: </strong>Twenty-eight studies met the inclusion criteria for the systematic review. A meta-analysis of 10 studies yielded a pooled sensitivity of 0.82 (95% CI: 0.67-0.91), specificity of 0.80 (95% CI: 0.70-0.88), positive diagnostic likelihood (DLR) of 4.14 (95%CI: 2.62-6.52), negative DLR of 0.23 (95% CI: 0.12-0.43), diagnostic odds ratio of 18.37 (95% CI: 7.36-45.85), and area under the curve of 0.87 (95% CI: 0.84-0.90). Subgroup analysis revealed significant differences based on the country and segmentation method.</p><p><strong>Limitations: </strong>Our meta-analysis is limited by small number of studies with external validation cohorts.</p><p><strong>Conclusions: </strong>MRI-derived radiomics-based models demonstrated good predictive performance for glioma 1p/19q codeletion status, highlighting their potential as a non-invasive tool for glioma characterization and for aiding in treatment decision-making.</p><p><strong>Abbreviations: </strong>DLR: diagnostic likelihood ratio, DOR: diagnostic odds ratio, AUC =area under the curve; HOIV: holdout internal validation, EV = external validation.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Subarachnoid Space Measurements in the Second Trimester Using MR Imaging.","authors":"Onur Simsek, Amirreza Manteghinejad, Mix Wannasarnmetha, Apoorva Kotha, Sara R Teixeira, Deborah Zarnow, Erin S Schwartz, Matthew T Whitehead","doi":"10.3174/ajnr.A8773","DOIUrl":"https://doi.org/10.3174/ajnr.A8773","url":null,"abstract":"<p><strong>Background and purpose: </strong>The subarachnoid space is an important component of the developing intracranial compartment. As fetal brain MRI is becoming more commonplace for early CNS disease diagnosis, it is imperative to determine age-based standards for normal subarachnoid space depth. We aim to provide 2D reference measurements of the supratentorial subarachnoid spaces in apparently healthy mid and later second-trimester fetuses.</p><p><strong>Materials and methods: </strong>In this cross-sectional study, we included all singleton fetal brain MRIs between gestational weeks 19 and 27 without visible pathologies. The frontal, insular, and inferior temporal subarachnoid space widths were measured from the inner calvarium to the brain surface bilaterally. Intra-class coefficients (ICC) and Bland-Altman plots were utilized to evaluate agreement between two raters. Left-and right-side measurements were compared using Wilcoxon tests. Quade tests were used to compare measurements between males and females. Generalized additive modeling for location, scale, and shape (GAMLSS) was used to create centile curves.</p><p><strong>Results: </strong>A total of 159 cases were included. ICC was highest (0.943) for the coronal plane insula width and lowest (0.667) for the coronal plane frontal width. Neither left-right (p>0.573) nor male-female (p>0.102) measurements were significantly different when considering age as a confounder; therefore, a single chart was created for each measurement.</p><p><strong>Conclusions: </strong>Subarachnoid space depth adapts to the growing calvarium during the mid-to late second trimester. This study provides normal reference ranges for future clinical and research purposes.</p><p><strong>Abbreviations: </strong>GA = Gestational Age; SAS = Subarachnoid Space.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mitigating brain MR imaging degradation due to ferumoxytol therapy in patients with iron deficiency anemia.","authors":"Seunghong Rhee, An M Tran, Thomas J O'Neill","doi":"10.3174/ajnr.A8772","DOIUrl":"https://doi.org/10.3174/ajnr.A8772","url":null,"abstract":"<p><p>Ferumoxytol, an FDA-approved treatment for iron deficiency anemia, is frequently used off-label as an MRI contrast agent. However, its unintended effects on brain MRI following anemia treatment, particularly in SWI and GRE sequences, remain insufficiently addressed. This study evaluates the optimal time interval between therapeutic ferumoxytol administration and brain MRI to minimize such effects. Analyzing 40 patients who underwent MRI within 3 months of ferumoxytol treatment, we found that 68% exhibited enhancement or signal drop on T1 weighted images and 63% showed susceptibility artifacts on SWI/GRE sequences. A 5-6 day interval between ferumoxytol administration and MRI examination is recommended to reduce these effects.ABBREVIATIONS: SWI = susceptibility weighted imaging; GRE = gradient recalled echo; MRI = magnetic resonance imaging.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Carotid Plaque-RADS: Inter-and intra-reader agreement and learning curve analysis in Computed Tomography Angiography.","authors":"Luca Saba, Roberta Scicolone, Gian Luca Chabert, Daniel Bos, Anna Kopczak, Mahmud Mossa-Basha, Jae W Song, Roberto Sanfilippo, Andreas Schindler, Andrew N Nicolaides, M Eline Kooi, Tobias Saam, Riccardo Cau, Giuseppe Lanzino","doi":"10.3174/ajnr.A8769","DOIUrl":"https://doi.org/10.3174/ajnr.A8769","url":null,"abstract":"<p><strong>Background and purpose: </strong>Atherosclerotic disease of the carotid arteries is a major cause of ischemic stroke. Traditionally, the degree of stenosis has been regarded as the primary parameter for predicting stroke risk, but emerging evidence highlights the importance of carotid plaque composition and morphology. Recently, the Carotid Plaque-Reporting and Data System (RADS) has been introduced to standardize carotid plaque assessment beyond the degree of carotid stenosis. However, its reliability in routine radiological practice has yet to be established.</p><p><strong>Purpose: </strong>This study assesses the inter-reader agreement, intra-reader agreement and learning curve associated with Carotid Plaque-RADS.</p><p><strong>Materials and methods: </strong>In this retrospective study 500 subjects who underwent computed tomography angiography (CTA) for suspected carotid atherosclerosis were assessed. Three readers with varying experience levels in vascular imaging independently evaluated all CTAs in five blocks using Carotid Plaque-RADS. To assess the impact of reader experience and potential improvement over time, inter-reader agreement between the three pairs of readers was calculated for each block using Cohen's kappa (κ), enabling a comparison of agreement sequentially across the blocks. Intra-reader agreement was calculated on a random block of 100 patients (192 carotid arteries).</p><p><strong>Results: </strong>After exclusion of low-quality exams, 490 patients were selected for analysis, but 46 carotids were excluded due to previous revascularization procedures. The remaining 934 carotid arteries were assessed. The agreement was substantial between Expert and Intermediate readers, ranging from κ=0.78 to κ=0.88, moderate between Intermediate and Beginner readers, ranging from κ=0.50 to κ=0.74, and between Expert and Beginner improved from substantial (κ=0.68) to almost optimal (κ=0.86) across blocks, indicating the effect of a learning curve. The inter-reader percent agreement was best for Plaque-RADS category 1-2-3 and poorest for 4. Intra-reader agreement was substantial for the Beginner (κ=0.77) and almost perfect for both the Intermediate and Expert readers (κ=0.88).</p><p><strong>Conclusions: </strong>In the CTA application of the Carotid Plaque-RADS, inter-reader agreement is substantial to near perfect among experienced and intermediate readers, with a notable learning curve for beginners. Intra-reader agreement is almost perfect in experienced and intermediate readers, indicating consistency of their grading, ensuring data reproducibility using Plaque-RADS.</p><p><strong>Abbreviations: </strong>RADS: Reporting and Data System; CTA: Computed Tomography Angiography; HU: Hounsfield Unit; IPH: Intra-plaque Hemorrhage; FC: Fibrous Cap; MWT: Maximum Wall Thickness; κ: Cohen's kappa; LRNC: Lipid-Rich Necrotic Core.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805122","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"In Plain Sight, a Radiology Workforce Crisis in the Making - Gap Between Job Growth and the Radiology Training Pipeline.","authors":"James Y Chen, Karen C Chen, Karen Buch, Mari Hagiwara, Frank J Lexa","doi":"10.3174/ajnr.A8764","DOIUrl":"https://doi.org/10.3174/ajnr.A8764","url":null,"abstract":"<p><strong>Background and purpose: </strong>This study aims to analyze the gap between the number of radiologist jobs listed in a single major US job posting center and the number of anticipated graduating general diagnostic radiology and neuroradiology trainees through the National Resident Matching Program as a primary source of radiologists to fulfill radiologist workforce needs.</p><p><strong>Materials and methods: </strong>Job listings between 2014-2023 from a single large US radiology job listing source were collected for the total number of unique annual job listings, divided between neuroradiology-only, some component of neuroradiology, and no component of neuroradiology. National Resident Matching Program data were collected for PGY-2 Diagnostic Radiology Residency and Neuroradiology Fellowship Match to estimate the number of general radiologists and neuroradiologists in the training pipeline graduating in the corresponding job listing year. The difference between the number of job listings and anticipated graduating trainees was calculated and extrapolated for the future.</p><p><strong>Results: </strong>Between 2014-2023, 31,825 jobs were listed in the ACR Career Center with 10,180 anticipated diagnostic radiology residency graduates during the same time period, for a ten-year cumulative deficit of 21,645 anticipated diagnostic radiology graduates. For neuroradiology-only jobs, the mismatch between job listings and anticipated fellowship trained neuroradiologists was 2,748 jobs to 1,933 graduates. For all jobs, the mismatch between anticipated radiology training graduates and job listings grew over this time-period.</p><p><strong>Conclusions: </strong>There is a growing mismatch between diagnostic radiology job listings on a major job listing board compared to the anticipated pipeline of general radiologists and neuroradiologists entering training through the NRMP Matching Program. This mismatch between the current growing need for radiologists and the training pipeline may help inform practice and training leaders seeking to mitigate the radiologist shortage.</p><p><strong>Abbreviations: </strong>NRMP = National Resident Matching Program; PGY-2 = Post-Graduate Year-2; ACR = American College of Radiology; PACS = Picture Archival and Communications System; ABR = American Board of Radiology; ACGME = Accreditation Council for Graduate Medical Education.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Effect of Prenatal Marijuana Exposure on White Matter Microstructure and Cortical Morphology During Late Childhood.","authors":"Hector Acosta-Rodriguez, Pratheek Bobba, Tal Zeevi, Laura R Ment, Seyedmehdi Payabvash","doi":"10.3174/ajnr.A8774","DOIUrl":"https://doi.org/10.3174/ajnr.A8774","url":null,"abstract":"<p><strong>Background and purpose: </strong>Marijuana consumption by pregnant women has been steadily increasing over the past decades. Even though many pregnant women perceive marijuana consumption as safe during pregnancy it has been previously linked to poor maternal and neonatal outcomes. The specific long lasting neurodevelopmental alterations caused by prenatal marijuana exposure in children are still underexplored. Thus, this study aims to determine the effect of prenatal marijuana exposure on brain neurodevelopment at late childhood.</p><p><strong>Materials and methods: </strong>This cross-sectional study investigated the relationship between prenatal marijuana exposure and neuroimaging markers of brain health. Data was obtained from the Adolescent Brain Cognitive Development study, a large, demographically diverse, multicenter cohort. The study included 1,085 children, 418 of whom were prenatally exposed to marijuana and 667 matched controls with no prenatal exposure, with a mean age of 9.9 (SD = 0.6) years in both groups.</p><p><strong>Results: </strong>We found that prenatal exposure to marijuana is associated with brain alterations in white matter tracts and cortical regions essential for goal directed behaviors, including motivation, cognitive skills for achieving specific objectives, and emotional processing. Direct group comparisons revealed significantly reduced white matter integrity in prenatally exposed children, with an overall reduction in lower fractional anisotropy and neurite density, and higher mean diffusivity and radial diffusivity. Furthermore, mixed linear model regressions revealed that prenatal marijuana exposure was significantly associated with decreased white matter microstructure, predominantly in the superior corticostriate tract and corticostriate projections via the external capsule to the superior parietal and frontal cortices and with reduced cortical surface area on the left hemisphere parahippocampal and right hemisphere postcentral gyrus.</p><p><strong>Conclusions: </strong>Overall, our findings suggest that prenatal exposure to marijuana may have long lasting alterations in children brain neurodevelopment. These alterations may impair critical skills needed as children grow into adolescence.</p><p><strong>Abbreviations: </strong>WM = white matter; DTI = Diffusion Tensor Imaging; FA = Fractional Anisotropy; MD = Mean Diffusivity;RD = Radial Diffusivity; ND = Neurite Density; sMRI = structural MRI; ABCD = Adolescent Brain Cognitive Development.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Severity Classification of Pediatric Spinal Cord Injuries Using Structural MRI Measures and Deep Learning: A Comprehensive Analysis Across All Vertebral Levels.","authors":"Zahra Sadeghi-Adl, Sara Naghizadehkashani, Devon Middleton, Laura Krisa, Mahdi Alizadeh, Adam E Flanders, Scott H Faro, Ze Wang, Feroze B Mohamed","doi":"10.3174/ajnr.A8770","DOIUrl":"https://doi.org/10.3174/ajnr.A8770","url":null,"abstract":"<p><strong>Background and purpose: </strong>Spinal cord injury (SCI) in the pediatric population presents a unique challenge in diagnosis and prognosis due to the complexity of performing clinical assessments on children. Accurate evaluation of structural changes in the spinal cord is essential for effective treatment planning. This study aims to evaluate structural characteristics in pediatric patients with SCI by comparing cross-sectional area (CSA), anterior-posterior (AP) width, and right-left (RL) width across all vertebral levels of the spinal cord between typically developing (TD) and participants with SCI. We employed deep learning techniques to utilize these measures for detecting SCI cases and determining their injury severity.</p><p><strong>Materials and methods: </strong>Sixty-one pediatric participants (ages 6-18), including 20 with chronic SCI and 41 TD, were enrolled and scanned using a 3T MRI scanner. All SCI participants underwent the International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI) test to assess their neurological function and determine their American Spinal Injury Association (ASIA) Impairment Scale (AIS) category. T2-weighted MRI scans were utilized to measure CSA, AP width, and RL widths along the entire cervical and thoracic cord. These measures were automatically extracted at every vertebral level of the spinal cord using the SCT toolbox. Deep convolutional neural networks (CNNs) were utilized to classify participants into SCI or TD groups and determine their AIS classification based on structural parameters and demographic factors such as age and height.</p><p><strong>Results: </strong>Significant differences (p<0.05) were found in CSA, AP width, and RL width between SCI and TD participants, indicating notable structural alterations due to SCI. The CNN-based models demonstrated high performance, achieving 96.59% accuracy in distinguishing SCI from TD participants. Furthermore, the models determined AIS category classification with 94.92% accuracy.</p><p><strong>Conclusions: </strong>The study demonstrates the effectiveness of integrating cross-sectional structural imaging measures with deep learning methods for classification and severity assessment of pediatric SCI. The deep learning approach outperforms traditional machine learning models in diagnostic accuracy, offering potential improvements in patient care in pediatric SCI management.</p><p><strong>Abbreviations: </strong><b>SCI</b> = Spinal Cord Injury, <b>TD</b> = Typically Developing, <b>CSA</b> = Cross-Sectional Area, <b>AP</b> = Anterior-Posterior, <b>RL</b> = Right-Left, <b>ASIA</b> = American Spinal Injury Association, <b>AIS</b> = American Spinal Injury Association, <b>CNN</b> = Convolutional Neural Network.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143805172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Repeatability and Reproducibility of Pseudocontinuous Arterial Spin-Labeling-Measured Brain Perfusion in Healthy Volunteers and Patients with Glioblastoma.","authors":"Limin Zhou, Durga Udayakumar, Yiming Wang, Marco C Pinho, Benjamin C Wagner, Michael Youssef, Joseph A Maldjian, Ananth J Madhuranthakam","doi":"10.3174/ajnr.A8551","DOIUrl":"10.3174/ajnr.A8551","url":null,"abstract":"<p><strong>Background and purpose: </strong>Arterial spin-labeling (ASL) MRI has gained recognition as a quantitative perfusion imaging method for managing patients with brain tumors. Limited studies have so far investigated the reproducibility of ASL-derived perfusion in these patients. This study aimed to evaluate intrasession repeatability and intersession reproducibility of perfusion measurements using 3D pseudocontinuous ASL (pCASL) with TSE Cartesian acquisition with spiral profile reordering (TSE-CASPR) in healthy volunteers (HV) and patients with glioblastoma (GBM) at 3T and to compare them against 3D pCASL with gradient and spin echo (GRASE).</p><p><strong>Materials and methods: </strong>This prospective study (NCT03922984) was approved by the institutional review board, and written informed consent was obtained from all subjects. HV underwent repeat pCASL evaluations 2-4 weeks apart between November 2021 and October 2022. Patients with GBM were recruited for longitudinal MRI from September 2019 to February 2023. Intrasession repeatability (HV and GBM) and intersession reproducibility (HV only) of pCASL were assessed using linear regression, Bland-Altman analyses, the intraclass correlation coefficient (ICC) with 95% CI, and within-subject coefficients of variation (wsCV).</p><p><strong>Results: </strong>Twenty HV (9 men; mean age, 25.1 [SD, 1.7] years; range, 23-30 years) and 21 patients with GBM (15 men; mean age, 59.8 [SD, 14.3] years; range, 28-81 years) were enrolled. In imaging sessions, 3D pCASL-measured perfusion with TSE-CASPR and GRASE, respectively, achieved high <i>R</i> ² values (0.88-0.95; 0.93-0.96), minimal biases (-0.46-0.81; -0.08-0.35 mL/100 g/min), high ICCs [95% CI], 0.96-0.98 [0.94-0.98]; 0.96-0.98 [0.92-0.99]), and low wsCV (6.64%-9.07%; 5.20%-8.16%) in HV (<i>n</i> = 20) and patients with GBM (<i>n</i> = 21). Across imaging sessions, 3D pCASL in HV (<i>n</i> = 20) achieved high <i>R</i> ² values (0.71; 0.82), minimal biases (-1.2; -0.90 mL/100 g/min), high ICC [95% CI] values (0.85 [0.81-0.89]; 0.90 [0.87-0.93]), and low wsCV values (13.82%; 9.98%).</p><p><strong>Conclusions: </strong>Our study demonstrated excellent intrasession repeatability of 3D pCASL-measured cerebral perfusion in HV and patients with GBM and good-to-excellent intersession reproducibility in HV. 3D pCASL with GRASE performed slightly better than 3D pCASL with TSE-CASPR in HV; however, in patients with GBM, 3D pCASL with TSE-CASPR showed better performance in tumor regions with a nearly 2-fold higher SNR. ASL-measured perfusion could serve as a noncontrast quantitative imaging biomarker to facilitate the management of patients with GBM.</p>","PeriodicalId":93863,"journal":{"name":"AJNR. American journal of neuroradiology","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142514458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}