Neuroradiology最新文献

{"title":"Endovascular therapy vs. conventional medical treatment for symptomatic intracranial atherosclerotic stenosis: an updated meta-analysis of randomized controlled trials.","authors":"Husam Abu Suilik, Mohammed Baker, Ahmed Naeem, AlMothana Manasrah, Mohamed Elnady, Bashar M Al Zoubi, Mohamed Abouzid, Mohamed Abuelazm","doi":"10.1007/s00234-025-03736-5","DOIUrl":"https://doi.org/10.1007/s00234-025-03736-5","url":null,"abstract":"<p><strong>Background: </strong>Symptomatic intracranial atherosclerotic stenosis is a common cause of ischemic stroke, with high recurrence rates despite medical management. The present study investigated the short-term and long-term outcomes of endovascular therapy (ET) versus conventional medical therapy (CMT) in intracranial atherosclerotic stenosis (sICAS) management.</p><p><strong>Methods: </strong>We conducted a systematic review and meta-analysis. Searches were performed in PubMed (MEDLINE), Cochrane Central Register of Controlled Trials (CENTRAL), Web of Science (WOS), SCOPUS, and Embase. Odds ratios (ORs) with 95% confidence intervals (CIs) were calculated. PROSPERO ID: (CRD42024601551).</p><p><strong>Results: </strong>Five RCTs involving 1,531 patients were included, with 743 in the ET + CMT group and 748 in the CMT group. ET was associated with increased odds of short-term mortality or stroke (OR, 3.19; 95% CI [1.96, 5.19], P < 0.01), including higher risks of mortality (OR, 4.35; 95% CI [1.23, 15.35], P = 0.02), ischemic stroke (OR, 2.26; 95% CI [1.34, 3.82], P < 0.01), and hemorrhagic stroke (OR, 10.74; 95% CI [2.52, 45.90], P < 0.01), but no difference between both groups in transient ischemic attack (OR, 0.87; 95% CI [0.32, 2.34], P = 0.78). For long-term outcomes, no significant differences were observed. However, ET significantly increased long-term hemorrhagic stroke risk (OR, 5.14; 95% CI [1.48, 17.77], P < 0.01).</p><p><strong>Conclusion: </strong>In patients with ischemic stroke due to sICAS, ET plus CMT has increased the risk of all-cause mortality, ischemic stroke, and hemorrhagic stroke compared to CMT alone. Hence, current evidence does not support adjuvant ET for patients with sICAS.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144963253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reproducible meningioma grading across multi-center MRI protocols via hybrid radiomic and deep learning features.","authors":"Mohamed J Saadh, Rafid Jihad Albadr, Dharmesh Sur, Anupam Yadav, R Roopashree, Gargi Sangwan, T Krithiga, Zafar Aminov, Waam Mohammed Taher, Mariem Alwan, Mahmood Jasem Jawad, Ali M Ali Al-Nuaimi, Bagher Farhood","doi":"10.1007/s00234-025-03725-8","DOIUrl":"https://doi.org/10.1007/s00234-025-03725-8","url":null,"abstract":"<p><strong>Objective: </strong>This study aimed to create a reliable method for preoperative grading of meningiomas by combining radiomic features and deep learning-based features extracted using a 3D autoencoder. The goal was to utilize the strengths of both handcrafted radiomic features and deep learning features to improve accuracy and reproducibility across different MRI protocols.</p><p><strong>Materials and methods: </strong>The study included 3,523 patients with histologically confirmed meningiomas, consisting of 1,900 low-grade (Grade I) and 1,623 high-grade (Grades II and III) cases. Radiomic features were extracted from T1-contrast-enhanced and T2-weighted MRI scans using the Standardized Environment for Radiomics Analysis (SERA). Deep learning features were obtained from the bottleneck layer of a 3D autoencoder integrated with attention mechanisms. Feature selection was performed using Principal Component Analysis (PCA) and Analysis of Variance (ANOVA). Classification was done using machine learning models like XGBoost, CatBoost, and stacking ensembles. Reproducibility was evaluated using the Intraclass Correlation Coefficient (ICC), and batch effects were harmonized with the ComBat method. Performance was assessed based on accuracy, sensitivity, and the area under the receiver operating characteristic curve (AUC).</p><p><strong>Results: </strong>For T1-contrast-enhanced images, combining radiomic and deep learning features provided the highest AUC of 95.85% and accuracy of 95.18%, outperforming models using either feature type alone. T2-weighted images showed slightly lower performance, with the best AUC of 94.12% and accuracy of 93.14%. Deep learning features performed better than radiomic features alone, demonstrating their strength in capturing complex spatial patterns. The end-to-end 3D autoencoder with T1-contrast images achieved an AUC of 92.15%, accuracy of 91.14%, and sensitivity of 92.48%, surpassing T2-weighted imaging models. Reproducibility analysis showed high reliability (ICC > 0.75) for 127 out of 215 features, ensuring consistent performance across multi-center datasets.</p><p><strong>Conclusions: </strong>The proposed framework effectively integrates radiomic and deep learning features to provide a robust, non-invasive, and reproducible approach for meningioma grading. Future research should validate this framework in real-world clinical settings and explore adding clinical parameters to enhance its prognostic value.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144874370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multicentric prospective study on computed tomography-guided periradicular infiltration and facet joint infiltration.","authors":"Daniel Cantré, Lars Gerigk, Simon David Sprengel, Christian Plathow, Iris Burkholder, Marc-André Weber, Anna Schedler, Christoph Rehnitz","doi":"10.1007/s00234-025-03741-8","DOIUrl":"https://doi.org/10.1007/s00234-025-03741-8","url":null,"abstract":"<p><strong>Purpose: </strong>Evaluation of the success of periradicular infiltration and facet joint infiltration in a multicenter and prospective approach.</p><p><strong>Materials and methods: </strong>114 patients undergoing therapeutic nerve root or facet joint infiltration for radicular and/or facet joint symptoms between the first lumbar and the first sacral segments were prospectively and consecutively enrolled across nine participating study centers in Germany. These centers provide CT-guided pain procedures continuously over a period of 96 months. Assessment was carried out by means of a systematic patient survey including pain questionnaires. The severity of the pain and the impairment caused by pain were assessed using 11-point Numerical Rating Scales.</p><p><strong>Results: </strong>CT-guided periradicular infiltration and facet joint infiltration significantly reduced pain levels and substantially reduced pain frequency at all time points and up to three months after the last intervention. All pain related characteristics (i.e. actual pain, average pain level, maximum pain level) were significantly (95% confidence intervals (CI) ranging between - 1.0 and - 5.0) reduced at all time points when compared to the baseline. Besides the pure pain levels, the presented data also provide detailed insights into the complex associated issues the patient collective is facing including impairment in everyday life, fitness for work and leisure time activities. These parameters were also substantially improved (95% CI between - 0.0 and - 5.0) at all time points indicating a comprehensive patient benefit. Self-reported patient satisfaction, recommendation of the procedure and personal success were rated high (62-100%). The rate of patients on sick leave dropped from 23.7 to 1.9%. Accordingly, patients reported a high rate of satisfaction with the procedures. There was a high technical and clinical success rate with no major complications.</p><p><strong>Conclusion: </strong>CT-guided pain therapy on the lumbar spine is effective and safe with a comprehensive benefit for patients, including not only pain levels in the narrow meaning but also regarding everyday life, fitness for work and leisure time activities at all investigated time points including 3 months follow-up.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144859405","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MRI evaluation of hyperostosis frontalis interna: differentiation and diagnostic insights.","authors":"Anish Bhandari, Samuel N Rogers, Srinivasan Vedantham, Richard Joseph Wruble, Unni Udayasankar, Hasan Ozgur, Raza Mushtaq","doi":"10.1007/s00234-025-03708-9","DOIUrl":"https://doi.org/10.1007/s00234-025-03708-9","url":null,"abstract":"<p><strong>Introduction: </strong>To delineate the MRI characteristics of Hyperostosis Frontalis Interna (HFI) and evaluate its imaging features to aid in accurate diagnosis and differentiation from other pathologies, particularly metastatic disease.</p><p><strong>Methods: </strong>A retrospective analysis of 74 patients with HFI was conducted. MRI sequences, including pre-contrast T1-weighted, post-contrast T1-weighted, and T2-weighted fat-saturation imaging, were evaluated. Quantitative and qualitative assessments of HFI signal intensity and enhancement patterns were performed. The Hershkovitz classification categorized the extent of HFI.</p><p><strong>Results: </strong>Pre-contrast T1-weighted imaging showed varied signal intensities, with hypointense regions more common in advanced HFI stages. Hypointense HFI was associated with a lower likelihood (OR: 0.303, CI: 0.113-0.808) and heterogeneous distribution was associated with a higher likelihood (OR: 5.128, CI: 1.982-13.265) of higher Hershkovitz classification (P = 0.0008). Post-contrast T1-weighted imaging revealed that 31% of subjects demonstrated enhancement, with focal geographic enhancement associated with lower CT attenuation values (P = 0.0138), indicating higher fat content. T2-weighted fat-saturation imaging supported the correlation between hypointense signals on pre-contrast T1 imaging and lower T2 signal intensities (P = 0.0022). No significant differences were found in enhancement patterns between different MRI sequences (P > 0.1326).</p><p><strong>Conclusions: </strong>HFI demonstrates varying appearances on pre- and post-contrast MRI sequences, crucial for differentiating benign HFI from metastatic lesions. Understanding these imaging characteristics can enhance diagnostic accuracy, reduce the risk of misdiagnosis, and improve patient management. Future studies should focus on larger, more diverse populations and explore advanced MRI techniques to further understand HFI.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144855929","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Tumor location, genomic alterations, and radiomic features as predictors of survival in glioblastoma: a Multi-Modal analysis.","authors":"Kavita Kundal, K Venkateswara Rao, Sandeep Kumar Dhanda, Neeraj Kumar, Rahul Kumar","doi":"10.1007/s00234-025-03742-7","DOIUrl":"https://doi.org/10.1007/s00234-025-03742-7","url":null,"abstract":"<p><strong>Purpose: </strong>This study aims to identify the impact of tumor location on the survival of glioblastoma (GBM) patients and the associated genetic alterations, using MRI scans from The Cancer Imaging Archive (TCIA) and genomic data from The Cancer Genome Atlas (TCGA). It also seeks to uncover non-invasive radiomic markers related to poor survival outcome for improved prognosis and treatment planning.</p><p><strong>Methods: </strong>We analysed pre-operative MRI scans and genomic data from 123 GBM patients (TCIA and TCGA). Tumor locations were determined using our in-house tool, \"tumorVQ\", followed by Kaplan-Meier survival analysis based on tumor position. Genomic analysis included somatic mutations, copy number variations, fusion genes, and differential gene expression to identify factors linked to poor survival. We extracted radiomic features from T1ce MRI scans using pyRadiomics to analyse their relationship with survival outcomes.</p><p><strong>Results: </strong>Kaplan-Meier analysis showed worse survival for tumors in the parietal lobe compared to other lobes, especially frontal lobe tumors. Genomic analysis revealed high prevalence of PTEN mutations, and exclusive fusion genes FGFR3-TACC3 and EGFR-SEPT14 in parietal lobe tumors. Differential gene expression showed upregulation of PITX2, HOXB13, and DTHD1, linked to tumor progression, while ALOX15 downregulation increased relapse risk. Copy number alterations, like LINC00290 deletions, were associated with aggressive parietal lobe tumors. Radiomic features, lower GLDM DependanceEntropy (LLL) and higher FirstOrder Mean (HLL), were strongly linked to increase risk.</p><p><strong>Conclusion: </strong>This study highlights poor survival outcomes in GBM patients with parietal lobe tumors. Key genetic alterations, such as PTEN mutations and fusion genes, drive tumor progression and chemoresistance in parietal lobe tumors. The association between radiomic features and survival indicates their potential as non-invasive prognostic biomarkers, which could aid in personalized treatment and improved patient management.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144822097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of brainstem hematoma volume evaluation techniques with a novel quantitative approach.","authors":"Xiangdong Wan, Yan Chen, Xueke Zhen, Ziqian Yan, Ziyi Liu, Tianxu Pang, Erwei Zhang, Zhenzeng Fan, Lijun Yang","doi":"10.1007/s00234-025-03729-4","DOIUrl":"https://doi.org/10.1007/s00234-025-03729-4","url":null,"abstract":"<p><p>This study systematically compares various methods for calculating brainstem hematoma volume, and introduces a novel estimation method based on the maximum cross-sectional area. First, we assessed the accuracy of the Tada formula and 3D Slicer software for quantifying brainstem hematomas of different sizes and morphologies. The results revealed significant differences among methods, with the traditional Tada formula frequently overestimating hematoma volumes. We therefore propose an improved algorithm that substantially increases both the accuracy and reliability of hematoma volume assessment. Experimental results demonstrate that this new method provides greater precision and consistency when measuring the volume of irregular hematomas. These findings not only contribute to improved diagnosis and treatment of brainstem hemorrhage but also provide valuable support for future research and practical applications.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144822093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficacy and safety of p48 flow diverters in the treatment of intracranial aneurysms: A systematic review and Meta-Analysis.","authors":"Bardia Hajikarimloo, Ibrahim Mohammadzadeh, Salem M Tos, Mohammad Amin Habibi, Rana Hashemi, Arman Hasanzade, Azin Ebrahimi, Kimia Didehvar, Mahdi Hooshmand, Sara Bana","doi":"10.1007/s00234-025-03737-4","DOIUrl":"https://doi.org/10.1007/s00234-025-03737-4","url":null,"abstract":"<p><strong>Background: </strong>The p48 movable wire (MW) flow modulation devices are a group of novel low-profile flow diverters (FDs) that have recently been introduced for the management of small intracranial aneurysms (IAs). This study evaluates the current literature regarding the efficacy and safety of p48 in treating IAs.</p><p><strong>Methods: </strong>A literature search was conducted using the PubMed, Embase, Scopus, and Web of Science databases. Studies evaluating the role of p48 FDs in IAs were included.</p><p><strong>Results: </strong>Twelve studies encompassing 312 individuals with 330 IAs were included. The meta-analysis revealed a pooled complete occlusion rate of 58% (95% CI: 40%-75%), a favorable outcome rate of 96% (95% CI: 86%-100%), and a morbidity rate of 1% (95% CI: 0%-3%). Regarding the complications, our findings showed a pooled intraprocedural rate of 7% (95% CI: 1%-16%), a postprocedural rate of 9% (95% CI: 6%-13%), an ischemic complication rate of 8% (95% CI: 5%-12%), a hemorrhagic complication rate of 3% (95% CI: 1%-5%), and an in-stent stenosis rate of 1% (95% CI: 0%-3%). The subgroup analysis comparing p48 MW and p48 MW with a hydrophilic coating (HPC) did not demonstrate significant differences between groups in outcomes and complications, except for hemorrhagic complications, which were higher in p48 MW than in p48 MW HPC devices (p48: 3% vs. p48 HPC: 0%, P = 0.04).</p><p><strong>Conclusion: </strong>The p48 FDs represent novel therapeutic options in the management of IAs, associated with promising outcomes and low complication rates.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144817217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ultrasound assessment of peripheral nerve size in Guillain-Barré syndrome: A systematic review and Meta-Analysis.","authors":"Omar Alomari, Bassel Alrabadi, Tarek A Hussein, Sanaa Shtayat, Rania A Hussein, Reem Alnahdi, Ragad Tawalbeh, Mahmoud Sayed Ahmed, Anas Elgenidy","doi":"10.1007/s00234-025-03728-5","DOIUrl":"https://doi.org/10.1007/s00234-025-03728-5","url":null,"abstract":"<p><strong>Purpose: </strong>Guillain-Barré Syndrome (GBS) is an autoimmune disorder causing acute inflammatory polyneuropathy, resulting in muscle weakness. Timely diagnosis is critical to prevent complications such as respiratory failure and long-term disability. Ultrasound imaging of peripheral nerves, specifically assessing nerve cross-sectional area (CSA), has been suggested as a diagnostic tool for GBS. This systematic review aims to evaluate the utility of nerve ultrasound in diagnosing and monitoring GBS.</p><p><strong>Methods: </strong>A systematic review was conducted following PRISMA guidelines, searching databases including PubMed, Scopus, Web of Science, and Cochrane Library up to December 2024. Studies that used ultrasound to assess peripheral nerve size in GBS patients compared to healthy controls or other neuropathy patients were included. Statistical analysis was conducted using Review Manager 5.4 software.</p><p><strong>Results: </strong>Out of 848 studies, 25 met the inclusion criteria, with 12 included in the meta-analysis. A total of 528 patients with GBS were included. Ultrasound revealed significant increases in the CSA of cervical, peroneal, median, ulnar, and tibial nerves in GBS patients. Specifically, cervical nerve enlargement (MD: 1.45, P = 0.0008) and peroneal nerve enlargement (Mean Difference (MD): 2.09, P < 0.00001) were notable. Subgroup analysis revealed significant enlargement of the ulnar and tibial nerves across different anatomical regions.</p><p><strong>Conclusion: </strong>Ultrasound imaging of peripheral nerves, particularly changes in CSA, provides valuable diagnostic insight for GBS, may be helpful in early recognition and intervention. Further studies are needed to establish consistent CSA patterns and improve diagnostic accuracy across various GBS subtypes.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144804483","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine learning diagnostic model for amyotrophic lateral sclerosis analysis using MRI-derived features.","authors":"Pablo Gil Chong, Miguel Mazon, Leonor Cerdá-Alberich, Maria Beser Robles, José Miguel Carot, Juan Francisco Vázquez-Costa, Luis Martí-Bonmatí","doi":"10.1007/s00234-025-03732-9","DOIUrl":"https://doi.org/10.1007/s00234-025-03732-9","url":null,"abstract":"<p><strong>Purpose: </strong>Amyotrophic Lateral Sclerosis is a devastating motor neuron disease characterized by its diagnostic difficulty. Currently, no reliable biomarkers exist in the diagnosis process. In this scenario, our purpose is the application of machine learning algorithms to imaging MRI-derived variables for the development of diagnostic models that facilitate and shorten the process.</p><p><strong>Methods: </strong>A dataset of 211 patients (114 ALS, 45 mimic, 22 genetic carriers and 30 control) with MRI-derived features of volumetry, cortical thickness and local iron (via T2* mapping, and visual assessment of susceptibility imaging). A binary classification task approach has been taken to classify patients with and without ALS. A sequential modeling methodology, understood from an iterative improvement perspective, has been followed, analyzing each group's performance separately to adequately improve modelling. Feature filtering techniques, dimensionality reduction techniques (PCA, kernel PCA), oversampling techniques (SMOTE, ADASYN) and classification techniques (logistic regression, LASSO, Ridge, ElasticNet, Support Vector Classifier, K-neighbors, random forest) were included. Three subsets of available data have been used for each proposed architecture: a subset containing automatic retrieval MRI-derived data, a subset containing the variables from the visual analysis of the susceptibility imaging and a subset containing all features.</p><p><strong>Results: </strong>The best results have been attained with all the available data through a voting classifier composed of five different classifiers: accuracy = 0.896, AUC = 0.929, sensitivity = 0.886, specificity = 0.929.</p><p><strong>Conclusion: </strong>These results confirm the potential of ML techniques applied to imaging variables of volumetry, cortical thickness, and local iron for the development of diagnostic model as a clinical tool for decision-making support.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144799764","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Acute stroke risk prediction model based on dual-energy CTA-derived carotid plaque, perivascular adipose tissue characteristics, and serum lipid parameters: a dual-center study.","authors":"He Zhang, Xu Xu, Juan Long, Chenzi Wang, Xiaohan Liu, Wenbei Xu, Xiaonan Sun, Peipei Dou, Dexing Zhou, Wei Cao, Kai Xu, Yankai Meng","doi":"10.1007/s00234-025-03723-w","DOIUrl":"https://doi.org/10.1007/s00234-025-03723-w","url":null,"abstract":"<p><strong>Background: </strong>Acute stroke is a major global cause of mortality and disability. Accurate prediction of stroke risk is crucial for effective clinical management. This study aimed to develop a multidimensional prediction model for acute stroke using carotid plaque characteristics, lumen parameters, perivascular adipose tissue (PVAT) quantitative metrics derived from dual-energy computed tomography angiography (DE-CTA), and serum lipid biomarkers.</p><p><strong>Methods: </strong>This retrospective dual-center study enrolled 212 patients who underwent DE-CTA and MRI between January 2023 and October 2024, comprising a training cohort (137 patients) and an external validation cohort (75 patients). Quantitative parameters including carotid plaque features (composition and intraplaque parameters), lumen metrics, PVAT quantitative indices, and serum lipid levels were collected. Patients with ipsilateral acute anterior circulation infarcts identified on MRI were classified as symptomatic (STA), and those without infarcts as asymptomatic (ATA). Variables were selected via univariate analysis and LASSO regression to construct a multivariate logistic regression model. Model performance was evaluated by ROC analysis, confusion matrix, calibration curves, and clinical decision curves, followed by external validation.</p><p><strong>Results: </strong>External validation of the final model showed an area under the ROC curve (AUC) of 0.810, with a sensitivity of 80.8% and specificity of 65.3%, indicating robust predictive performance and good clinical applicability.</p><p><strong>Conclusions: </strong>The multidimensional predictive model integrating DE-CTA-derived carotid plaque features, PVAT metrics, and serum lipid parameters effectively predicts acute stroke risk, providing a reliable quantitative tool for early screening and clinical intervention.</p>","PeriodicalId":19422,"journal":{"name":"Neuroradiology","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144794986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}