Prevalence of basilar artery variants: a systematic review with meta-analysis of radiological studies

基底动脉变异的患病率：一项基于影像学研究的系统评价和荟萃分析

To provide a comprehensive meta-analytic synthesis of the morphological variability of the basilar artery (BA) - specifically fenestrations, persistent trigeminal arteries (PTA), and aberrant posterior inferior cerebellar artery (PICA) origin - and to elucidate their clinical implications for neuroradiological and neurosurgical procedures. Although BA variations are relatively infrequent, their precise identification is a clinical necessity for procedural safety. Awareness of these variants is vital for navigating complex vascular geometries and managing the potential risk of associated aneurysms during endovascular interventions.

对基底动脉（BA）的形态变异性——具体包括开窗畸形、持续性三叉动脉（PTA）和小脑下后动脉（PICA）起始异常——进行全面的荟萃分析综合研究，并阐明其对神经放射学和神经外科手术的临床意义。尽管基底动脉变异相对少见，但准确识别这些变异是保障手术安全的临床必要条件。了解这些变异对于处理复杂的血管形态以及在血管内介入治疗期间应对相关动脉瘤的潜在风险至关重要。

REF: Triantafyllou G, Paschopoulos I, Papadopoulos-Manolarakis P, et al. Prevalence of basilar artery variants: a systematic review with meta-analysis of radiological studies. Neuroradiology. Published online April 29, 2026. doi:10.1007/s00234-026-04008-6 PMID: 42053591

Radiomics-based artificial intelligence models in brain tumors: A systematic review and meta-analysis of diagnostic performance

基于影像组学的脑肿瘤人工智能模型：诊断性能的系统评价与荟萃分析

Radiomics-based artificial intelligence (AI) models have emerged as promising tools for brain tumor diagnosis, grading, and classification by extracting quantitative features from imaging data. Yet, clinical translation remains limited due to variability in model design, validation, and interpretability. To systematically evaluate the diagnostic performance—defined as the ability of radiomics-based AI models to correctly classify or distinguish brain tumors, measured by sensitivity, specificity, accuracy, and area under the curve (AUC)—and to identify the impact of model type, imaging modality, and tumor subtype on predictive accuracy. Radiomics-based AI models demonstrate strong diagnostic performance in the diagnosis, grading, and classification of brain tumors, particularly when using deep learning and multimodal imaging. However, limited validation and inconsistent reporting practices remain barriers. Standardized pipelines, explainable algorithms, and multicenter prospective studies are needed to advance clinical implementation.

基于影像组学的人工智能（AI）模型已成为通过从影像数据中提取定量特征进行脑肿瘤诊断、分级和分类的有前景的工具。然而，由于模型设计、验证和可解释性的差异，其临床转化仍然有限。为了系统评估诊断性能——定义为基于影像组学的人工智能模型正确分类或区分脑肿瘤的能力，通过灵敏度、特异度、准确度和曲线下面积（AUC）来衡量——并确定模型类型、成像方式和肿瘤亚型对预测准确性的影响。基于影像组学的人工智能模型在脑肿瘤的诊断、分级和分类中表现出较强的诊断性能，特别是在使用深度学习和多模态成像时。然而，有限的验证和不一致的报告做法仍然是障碍。需要标准化的流程、可解释的算法和多中心前瞻性研究来推动临床应用。

REF: Reyes JS, Almeida T, Bouras A, et al. Radiomics-based artificial intelligence models in brain tumors: A systematic review and meta-analysis of diagnostic performance. Neuroradiology. Published online April 27, 2026. doi:10.1007/s00234-026-03983-0 PMID: 42043503

Amide proton transfer and arterial spin labeling for non-invasive molecular stratification of glioma: a multi-dataset imaging biomarker study

酰胺质子转移和动脉自旋标记用于胶质瘤的非侵入性分子分层：一项多数据集影像生物标志物研究

To evaluate amide proton transfer chemical exchange saturation transfer magnetization transfer ratio asymmetry (MTRasym) and arterial spin labeling cerebral blood flow (CBF), two advanced MRI-based maps, for predicting glioma isocitrate dehydrogenase (IDH) mutation status, 1p/19q codeletion status, and grade using radiomics features; to assess cross-dataset/cross-vendor generalizability; and to examine whether combining MTRasym and CBF features improves prediction. MTRasym and CBF features show promise for glioma molecular stratification, and multimodal modeling improves predictions. Cross-vendor validation reveals modality-specific generalizability patterns.

利用影像组学特征，评估基于磁共振成像（MRI）的两种高级成像图，即酰胺质子转移化学交换饱和转移磁化传递比不对称性（MTRasym）和动脉自旋标记脑血流量（CBF），以预测胶质瘤异柠檬酸脱氢酶（IDH）突变状态、1p/19q共缺失状态和分级；评估跨数据集/跨设备厂商的可推广性；并研究结合MTRasym和CBF特征是否能改善预测效果。MTRasym和CBF特征在胶质瘤分子分层方面显示出应用前景，多模态建模可改善预测效果。跨设备厂商验证揭示了特定模态的可推广性模式。

REF: Essed R, Wamelink IJ, Petr J, et al. Amide proton transfer and arterial spin labeling for non-invasive molecular stratification of glioma: a multi-dataset imaging biomarker study. Neuroradiology. Published online April 23, 2026. doi:10.1007/s00234-026-04006-8 PMID: 42024277

Integrated quantitative susceptibility mapping and radiomics for multiple system atrophy subtypes classification

整合定量磁敏感图和影像组学用于多系统萎缩亚型分类

To explore the diagnostic potential of combining quantitative susceptibility mapping (QSM) and radiomics in distinguishing between multiple system atrophy with predominant cerebellar ataxia (MSA-C) and predominant parkinsonism (MSA-P). The integration of QSM and radiomics improves the differentiation between the two MSA subtypes. The hybrid model of PUT demonstrated superior classification performance. This combined approach showed potential as an imaging biomarker for improving diagnostic capabilities of MSA subtypes.

探讨结合定量磁敏感图（QSM）和影像组学在区分以小脑性共济失调为主的多系统萎缩（MSA - C）和以帕金森综合征为主的多系统萎缩（MSA - P）方面的诊断潜力。QSM和影像组学的结合提高了对两种MSA亚型的鉴别能力。壳核（PUT）的混合模型表现出更优的分类性能。这种联合方法有望作为一种影像学生物标志物，提高MSA亚型的诊断能力。

REF: Mao X, Zhang D, Bai J, Liu Y, Yu J, Jia Z. Integrated quantitative susceptibility mapping and radiomics for multiple system atrophy subtypes classification. Neuroradiology. Published online April 23, 2026. doi:10.1007/s00234-026-04007-7 PMID: 42024277

Pathological signatures of white matter lesions in multiple sclerosis versus stroke: a synthetic MRI study

多发性硬化症与中风中白质病变的病理特征：一项合成磁共振成像研究

To evaluate whether quantitative synthetic MRI (SyMRI) parameters can differentiate non-specific white matter lesions (nsWMLs) in patients with multiple sclerosis (MS) and ischemic stroke, and to assess differences in normal-appearing white matter (NAWM) between these groups. SyMRI captures both lesion-specific and diffuse NAWM differences between MS and stroke. Age strongly influences quantitative white matter measures, and adjusting for age reveals subtle NAWM pathology in MS. SyMRI may support differential diagnosis in patients with ambiguous white matter lesions.

评估定量合成磁共振成像（SyMRI）参数能否区分多发性硬化症（MS）患者和缺血性中风患者的非特异性白质病变（nsWMLs），并评估这些患者组之间正常表现白质（NAWM）的差异。SyMRI可捕捉MS和中风患者之间病变特异性和弥漫性NAWM的差异。年龄对定量白质测量有显著影响，对年龄进行校正后可揭示MS患者中细微的NAWM病理改变。SyMRI可能有助于对存在不明确白质病变的患者进行鉴别诊断。

REF: Katsarogiannis E, Wikström J, Virhammar J, Berntsson SG, Landtblom AM. Pathological signatures of white matter lesions in multiple sclerosis versus stroke: a synthetic MRI study. Neuroradiology. Published online April 22, 2026. doi:10.1007/s00234-026-04002-y PMID: 42017989

MRI Differentiation of Anaplastic Ependymoma and Medulloblastoma with Fourth Ventricular Outlet Extension in Children

儿童间变性室管膜瘤与累及第四脑室出口的髓母细胞瘤的磁共振成像鉴别

Medulloblastoma and anaplastic ependymoma (AE) are common malignant pediatric posterior fossa tumors with differing outcomes. While tumor extension through the fourth ventricular outlets (TETFVO) is common in AEs, it also occurs in some medulloblastomas, which complicates diagnosis. This study aimed to improve pretreatment differentiation between medulloblastomas with TETFVO and AEs for better treatment planning and outcome prediction. Compared with AEs, medulloblastomas with TETFVO show lower ADCmin, less brainstem or vascular encasement, less caudal extensions, and the tumor central vein sign. These distinct features can aid in treatment planning and outcome prediction.

髓母细胞瘤和间变性室管膜瘤（AE）是常见的儿童后颅窝恶性肿瘤，预后不同。虽然肿瘤经第四脑室出口延伸（TETFVO）在间变性室管膜瘤中很常见，但在一些髓母细胞瘤中也会出现，这使诊断变得复杂。本研究旨在提高对伴有TETFVO的髓母细胞瘤和间变性室管膜瘤的治疗前鉴别能力，以便更好地制定治疗方案和预测预后。与间变性室管膜瘤相比，伴有TETFVO的髓母细胞瘤表观扩散系数最小值（ADCmin）更低，脑干或血管包绕较少，尾端延伸较少，且有肿瘤中央静脉征。这些独特特征有助于治疗方案的制定和预后预测。

REF: Wu HW, Wu CH, Lin SC, et al. MRI Differentiation of Anaplastic Ependymoma and Medulloblastoma with Fourth Ventricular Outlet Extension in Children. Neuroradiology. Published online April 20, 2026. doi:10.1007/s00234-026-04003-x PMID: 42002635

Higher cerebral metabolic rate of oxygen derived from dynamic susceptibility contrast MRI is an independent predictor of poor survival in IDH-wildtype glioblastoma

基于动态磁敏感对比磁共振成像得出的较高脑氧代谢率是异柠檬酸脱氢酶野生型胶质母细胞瘤患者生存不良的独立预测因素。

To evaluate the role of tumor oxygenation imaging parameters in predicting the overall survival (OS) of newly diagnosed isocitrate dehydrogenase (IDH)-wildtype glioblastoma patients. Higher 10th percentile of CMRO2 may predict dismal prognosis in IDH-wildtype glioblastoma patients independently of previously known clinical, molecular, and surgical prognostic factors.

评估肿瘤氧合成像参数在预测新诊断的异柠檬酸脱氢酶（IDH）野生型胶质母细胞瘤患者总生存期（OS）中的作用。脑氧代谢率（CMRO2）的第10百分位数较高可能独立于先前已知的临床、分子和手术预后因素，预测IDH野生型胶质母细胞瘤患者预后不良。

REF: Park YW, Choi K, Han K, et al. Higher cerebral metabolic rate of oxygen derived from dynamic susceptibility contrast MRI is an independent predictor of poor survival in IDH-wildtype glioblastoma. Neuroradiology. Published online April 20, 2026. doi:10.1007/s00234-026-03961-6 PMID: 42008029

A comprehensive framework for automated segmentation of perivascular spaces in brain MRI with the nnU-Net

基于nnU-Net的脑磁共振成像中血管周围间隙自动分割综合框架

Enlargement of perivascular spaces (PVS) is common in cerebral small vessel disease, Alzheimer’s disease, and Parkinson’s disease, reflecting impaired clearance pathways. While MRI provides a means to quantify perivascular spaces, manual annotation remains time-consuming and labour-intensive. Thus, there is a need for accurate automated MRI-based PVS segmentation methods. Our deep learning models provide a robust framework for automated PVS quantification across MRI modalities.

血管周围间隙（PVS）扩大在脑小血管病、阿尔茨海默病和帕金森病中很常见，反映了清除通路受损。虽然磁共振成像（MRI）提供了量化血管周围间隙的方法，但手动标注仍然耗时且费力。因此，需要基于MRI的准确自动PVS分割方法。我们的深度学习模型为跨MRI模态的自动PVS量化提供了一个强大的框架。

REF: Pham W, Jarema A, Rim D, et al. A comprehensive framework for automated segmentation of perivascular spaces in brain MRI with the nnU-Net. Neuroradiology. Published online April 17, 2026. doi:10.1007/s00234-026-03993-y PMID: 41995815

Neuroimaging-clinical phenotypes are associated with functional outcomes in acute ischemic stroke: a latent class analysis of multidimensional biomarkers

神经影像学 - 临床表型与急性缺血性卒中的功能结局相关：多维度生物标志物的潜类别分析

Functional recovery after acute ischemic stroke is highly heterogeneous. This study aimed to explore and characterize distinct clinical-neuroimaging phenotypes associated with outcomes in patients with anterior circulation large vessel occlusion (LVO) by integrating multidimensional clinical and neuroimaging biomarkers using latent class analysis (LCA). LCA-derived clinical-neuroimaging phenotypes define hypothesis-generating subgroups with distinct outcome risks, nominating the hyperglycemic subtype as potentially the most vulnerable.

急性缺血性卒中后的功能恢复具有高度异质性。本研究旨在通过潜在类别分析（LCA）整合多维度临床和神经影像学生物标志物，探索并描述与前循环大血管闭塞（LVO）患者预后相关的不同临床 - 神经影像学表型。LCA得出的临床 - 神经影像学表型定义了具有不同预后风险的假设性亚组，提示高血糖亚型可能是最脆弱的亚型。

REF: Cheng X, Tang H, Li J, et al. Neuroimaging-clinical phenotypes are associated with functional outcomes in acute ischemic stroke: a latent class analysis of multidimensional biomarkers. Neuroradiology. Published online April 16, 2026. doi:10.1007/s00234-026-04001-z PMID: 41986487