It has been five years since the last version of the clinical practice guidelines for the management of adult diffuse gliomas was published by the Asian Glioma Genome Atlas (AGGA). Significant progress and revisions have occurred in the diagnosis and treatment of adult diffuse gliomas in recent years. In response to these updates, the joint guideline committee of the Chinese Glioma Cooperative Group (CGCG), the Society for Neuro-Oncology of China (SNO-China), and the Chinese Brain Cancer Association (CBCA) has revised the clinical practice guidelines. This updated guideline emphasizes molecular and pathological diagnostics, as well as the primary treatment modalities of surgery, radiotherapy, chemotherapy, and targeted therapy. Additionally, we have incorporated findings from recent clinical trials of new therapies to align with cutting-edge treatment strategies. This guideline is designed to serve as a practical resource for all professionals involved in managing adult diffuse glioma patients, while also providing valuable information for insurance companies and other institutions responsible for regulating cancer care costs in China and beyond.

Abstract Purpose To build a model that utilizes clinical and blood parameters to predict the recurrence or progression of pituitary tumors after surgery. Methods A training group (67,70%) and a validation group (29,30%) were formed from 96 individuals with recurrent pituitary tumors. The training group was screened for blood parameters and a blood-related risk score (BRS) was established. Clinical-related prognostic factors were also assessed through Cox regression analysis, which was used alongside the BRS to construct a clinical prognostic model. In the validation group to assess the stability and accuracy of the BRS and the clinical prognostic model. Additionally, a clinical and blood-based nomogram was developed. Result The preoperative blood parameters K+, cholinesterase (CHE), and 5-nucleotidase (NT5E) were found to be correlated with progression-free survival (PFS). The area under the curve (AUC) for the BRS was 0.788 (95% CI: 0.657-0.919) in the training group and 0.852 (95% CI: 0.706-0.997) in the validation group. For 1-, 3-, and 5-year intervals in the validation set, the clinical model's AUC was 0.718, 0.852, and 0.864, respectively. While in the test group, the AUCs were 0.600, 0.889, and 0.660. The nomogram had C indices of 0.732 and 0.704 in the training and validation groups, respectively, and its calibration curves and clinical decision curves (DCA) indicated good calibrations and clinical utility. ConclusionThis is a new non-invasive tool that provides a tool for predicting prognosis and risk stratification.

In 2022, the American Heart Association/American Stroke Association (AHA/ASA) issued Guidelines for Diagnosis and Treatment of Spontaneous Cerebral Hemorrhage (2022). This evidence-based guidelines provide treatment recommendations of cerebral hemorrhage. In particular, the guidelines emphasize the concepts of cerebral small-vessel disease, treatment of anticoagulant-related cerebral hemorrhage, and early rehabilitation at home. The authors interprets this guideline based on relevant research progress.

目的 探讨术前栓塞联合显微手术切除治疗后颅窝大型实性血管母细胞瘤(HB)的可行性和效果,并分析可能影响患者术后并发症发生的因素.方法 回顾性分析2012年6月至2022年1月郑州大学第一附属医院神经外科收治的21例大型HB(最大直径＞30 mm)患者[占同期收治后颅窝HB患者的8.8％(21/238)]的临床资料.5例(23.8％)合并Von Hippel-Lindau(VHL)病.肿瘤位于小脑半球9例(42.9％);小脑脑桥角区4例(19.0％);第四脑室顶及小脑上、下蚓部,枕骨大孔区8例(38.1％).病灶累及脑干4例(19.0％),肿瘤多发2例(9.5％).所有患者均采用血管内栓塞供血动脉以及显微手术切除肿瘤治疗.评估术后并发症的发生率,入院及末次随访时的改良Rankin量表评分(mRS),并探讨可能影响HB患者术后并发症发生的因素.结果 21例患者均完成术前肿瘤供血动脉栓塞,栓塞程度为60％～80％.所有患者的肿瘤均获全切除.共7例(33.3％)患者发生术后并发症,包括颅内出血1例,呼吸功能障碍2例,后组脑神经功能障碍2例,面瘫1例,偏侧肢体无力1例,脑积水1例,肺部感染3例,颅内感染1例,脑脊液漏1例,皮下积液1例,平衡障碍加重1例.单因素分析结果显示,仅肿瘤侵袭脑干为影响HB患者术后并发症发生的危险因素(P=0.006),而患者的性别、年龄、病程、病变大小或质地、术前有无脑积水、术前mRS与术后并发症的发生无明显相关(均P＞0.05).术后2例患者死亡(1例术后因再出血死亡,1例死于呼吸系统并发症),其余19例获得随访,随访时间为6～114个月,中位时间为22个月.末次随访mRS:0分9例,1分5例,2分4例,3分1例.随访期间,肿瘤复发2例,均为合并VHL病的患者;新发额叶胶质瘤1例,脑积水2例.结论 对于后颅窝大型实性HB,术前肿瘤供血动脉栓塞联合显微手术切除肿瘤多可获得良好的效果;肿瘤累及脑干者术后并发症的发生率较高.

2022年美国临床肿瘤协会(ASCO)、神经肿瘤学会(SNO)和美国放射治疗及肿瘤学会(ASTRO)发布了《ASCO/SNO/ASTRO脑转移瘤治疗指南》。该指南依据相关领域的循证医学证据，对脑转移瘤主要治疗方案给出了综合性治疗建议，具有很强的实践性。本文对该指南进行解读，以供参考。

Purpose The aim of this study was to investigate the epidemiological characteristics and associated risk factors of recurrent lower-grade glioma [LGG] (WHO grades II and III) according to the 2016 updated WHO classification paradigm and finally develop a model for predicting early mortality (succumb within a year after reoperation) in recurrent LGG patients. Methods Data were obtained from consecutive patients who underwent surgery for primary LGG and reoperation for tumor recurrence. The end point “early mortality” was defined as death within 1 year after the reoperation. Predictive factors, including basic clinical characteristics and laboratory data, were retrospectively collected. Results A final nomogram was generated for surgically treated recurrent LGG. Factors that increased the probability of early mortality included older age ( P = 0.042), D-dimer> 0.187 ( P = 0.007), RDW > 13.4 ( P = 0.048), PLR > 100.749 ( P = 0.014), NLR > 1.815 ( P = 0.047), 1p19q intact ( P = 0.019), IDH1-R132H Mutant (P = 0.048), Fib≤2.80 ( P = 0.018), lack of Stupp concurrent chemoradiotherapy ( P = 0.041), and an initial symptom of epilepsy ( P = 0.047). The calibration curve between the prediction from this model and the actual observations showed good agreement. Conclusion: A nomogram that predicts individualized probabilities of early mortality for surgically treated recurrent LGG patients could be a practical clinical tool for counseling patients regarding treatment decisions and optimizing therapeutic approaches. Free online software implementing this nomogram is provided at https://warrenwrl.shinyapps.io/RecurrenceGliomaEarlyM/

ObjectiveTo construct and validate a radiomics nomogram for preoperative prediction of survival stratification in glioblastoma (GBM) patients with standard treatment according to radiomics features extracted from multiparameter magnetic resonance imaging (MRI), which could facilitate clinical decision-making. MethodsA total of 125 eligible GBM patients (53 in the short and 72 in the long survival group, separated by an overall survival of 12 months) were randomly divided into a training cohort (n = 87) and a validation cohort (n = 38). Radiomics features were extracted from the MRI of each patient. The T-test and the least absolute shrinkage and selection operator algorithm (LASSO) were used for feature selection. Next, three feature classifier models were established based on the selected features and evaluated by the area under curve (AUC). A radiomics score (Radscore) was then constructed by these features for each patient. Combined with clinical features, a radiomics nomogram was constructed with independent risk factors selected by the logistic regression model. The performance of the nomogram was assessed by AUC, calibration, discrimination, and clinical usefulness. ResultsThere were 5,216 radiomics features extracted from each patient, and 5,060 of them were stable features judged by the intraclass correlation coefficients (ICCs). 21 features were included in the construction of the radiomics score. Of three feature classifier models, support vector machines (SVM) had the best classification effect. The radiomics nomogram was constructed in the training cohort and exhibited promising calibration and discrimination with AUCs of 0.877 and 0.919 in the training and validation cohorts, respectively. The favorable decision curve analysis (DCA) indicated the clinical usefulness of the radiomics nomogram. ConclusionsThe presented radiomics nomogram, as a non-invasive tool, achieved satisfactory preoperative prediction of the individualized survival stratification of GBM patients.

背景:越来越多新兴的修补材料用于颅骨缺损的修补,何种修补材料是最佳选择尚无明确定论.目的:初步探讨三维数字化塑形聚醚醚酮、钛网两种颅骨修补材料在颅骨修补中的应用性比较.方法:回顾性分析2017年1月至2020年9月在郑州大学第一附属医院神经外科接受颅骨修补174例患者的临床资料,男126例,女48例,平均年龄(43.9±12.0)岁,其中选择聚醚醚酮修补材料者95例,选择钛网修补材料者79例.获取术中资料、术后并发症及随访结果情况(包括癫痫发作、需手术处理的血肿、感染、皮下积液、脑脊液漏、修补材料松动或凹陷、植入物外露等及主观感受),比较两组是否存在差异.试验方案符合郑州大学第一附属医院伦理委员会要求.结果与结论:①174例患者术后随访时间为2-37个月,平均(17.2±12.4)个月;②聚醚醚酮组与钛网组的术后总并发症发生率分别为20%, 26%,组间比较差异无显著性意义(P > 0.05);③术后随访过程中,两组患者癫痫、血肿发生、手术部位感染、皮下积液、脑脊液漏、修补材料松动或凹陷发生情况比较差异无显著性意义(P > 0.05),头部双侧对称性比例比较差异无显著性意义(P > 0.05),聚醚醚酮组患者的修补材料外露、震动感和冷热感体验发生比例低于钛网组(P < 0.05);④结果表明,两组修补材料均具有良好的生物亲和性,聚醚醚酮修补材料术后发生的材料外露、震动感和冷热感觉体验要少于钛网修复材料.

Objective:To explore the risk factors and treatment strategies of intraoperative cerebrospinal fluid (CSF) leakage during transnasosphenoidal neuroendoscopic surgery for pituitary adenomas.Methods:A retrospective analysis was conducted on the clinical data of 676 patients with pituitary adenomas who were registered in the National Brain Tumor Registry Platform of China (https: //) and treated with transnasosphenoidal endoscopic surgery at the Department of Neurosurgery, the First Affiliated Hospital of Zhengzhou University from January 2019 to July 2020. According to the presence or absence of intraoperative CSF leakage and its severity degree, the patients were divided into grades 0-3 CSF leakage, and different skull base reconstruction techniques were adopted. CSF leakage grades 1 to 3 were defined as intraoperative CSF leakage group (117 cases), and grade 0 was defined as no intraoperative CSF leakage group (559 cases). The clinical characteristics of the two groups of patients were compared, and multivariate logistic regression analysis was used to determine the influencing factors of intraoperative CSF leakage.Results:Skull base reconstruction was completed in all 676 patients. Intraoperative CSF leakage occurred in 117 cases (17.3%) which included 56 cases of CSF leakage grade 1, 38 cases of grade 2, and 23 cases of grade 3. Postoperative CSF leakage occurred in 5 cases, none of the patients showed the symptoms of CSF leakage when they were discharged. The follow-up time of 676 patients was 8.1±2.4 months (6-12 months), and there were no complications such as intracranial infection or CSF leakage during the follow-up period. Compared with the group without intraoperative CSF leakage, the intraoperative CSF leakage group had higher proportions of patients with secondary surgery, abnormal preoperative visual acuity, Knosp grade 3 and 4, Hardy-Wilson grade C, D and E, and stiff tumor, and the difference was statistically significant (all P<0.05). The results of multivariate logistic regression analysis showed that secondary surgery ( OR=3.05, 95% CI: 1.70-5.44, P<0.001), Hardy-Wilson classification [C grade ( OR=7.16, 95% CI: 4.02-13.10, P<0.001), grades D and E ( OR=11.41, 95% CI: 5.68-23.55, P<0.001)], tumor texture ( OR=2.13, 95% CI: 1.21-3.70, P=0.008) were all influencing factors of intraoperative CSF leakage during transnasosphenoidal neuroendoscopic resection of pituitary adenomas. Conclusions:Patients with secondary surgery, higher Hardy-Wilson grades, and stiff tumors have a higher risk of intraoperative CSF leakage during transnasosphenoidal neuroendoscopic surgery for pituitary adenomas. Skull base reconstruction techniques based on the grading of intraoperative CSF leakage are relatively safe and effective.

欧洲神经肿瘤学会(European Association of Neuro-oncology,EANO)在回顾大量文献的基础上发布了 2020版《成人弥漫性胶质瘤的诊断和治疗指南》[1](简称《指南》).该《指南》结合了 2016年WHO中枢神经系统肿瘤分类标准(2016 WHO CNS)中的组织-分子病理诊断标准[2]、中枢神经系统肿瘤分类分子信息及实践方法联盟——非WHO官方组织(cIMPACT-NOW)推荐意见[3]和临床试验进展,对成人弥漫性胶质瘤的筛查、术前诊断、组织-分子病理学诊断、治疗及随访部分进行了修订.该次修订使得胶质瘤诊疗常规发生了重大变化,为胶质瘤的诊断和治疗提供了重要的参考.《指南》强调整个诊疗计划中应遵循多学科综合治疗模式,尤其要重视神经功能康复训练.另外,许多罕见胶质瘤病种还缺乏临床数据和治疗建议,《指南》还需在今后的临床和基础研究中不断验证和完善.

目的 观察脑胶质瘤患者的TGF-β1、Smad7、VEGF水平,并分析其临床意义.方法 选取2020年9月-2020年10月在我院接受治疗的脑胶质瘤患者为研究对象.同时选取同期在我院治疗的良性脑胶质瘤作为对照.观察两组患者血清TGF-β1、Smad7、VEGF水平,比较不同临床病理特征脑胶质瘤患者TGF-β1、Smad7、VEGF水平的差异,分析影响脑胶质瘤患者TGF-β1、Smad7、VEGF表达情况的因素.结果 脑胶质瘤患者的TGF-β1、Smad7、VEGF阳性表达率均高于良性肿瘤组,差异有统计学意义(χ2值=105.195、86.445、106.404,P<0.001);有淋巴结转移、分化程度为中低分化、TNM分期为Ⅲ期+Ⅳ期的脑胶质瘤患者的TGF-β1、Smad7、VEGF阳性表达率较高,不同年龄、性别患者的TGF-β1、Smad7、VEGF阳性表达率无差别;将单因素分析有意义的因素作为自变量,将TGF-β1、Smad7、VEGF阳性率作为因变量进行回归分析,结果显示,淋巴转移和TNM分期是影响胶质瘤患者TGF-β1、Smad7、VEGF阳性表达的因素.结论 脑胶质瘤患者的TGF-β1、Smad7、VEGF阳性表达率较高,且受患者淋巴结转移情况和TNM分期的影响.

目的 分析腱糖蛋白C(TNC)在脑胶质瘤中的表达及临床意义.方法 回顾性分析中国脑胶质瘤基因组图谱(CGGA)数据库中胶质瘤患者转录组数据和临床资料,采用SPSS 22.0统计软件分析TNC在胶质瘤组织中的表达特点,分析TN C表达水平与患者临床特征及预后的关系.结果 TN C在胶质瘤组织中表达水平高于正常对照脑组织(P<0.05);TNC表达水平在胶质瘤组织中随世界卫生组织(WHO)病理分级增高而升高(P<0.05).TNC在异柠檬酸脱氢酶(IDH)基因野生型、年龄>42岁、O6-甲基鸟嘌呤DNA甲基转移酶(MGMT)基因启动子非甲基化患者的脑胶质瘤组织中高表达(P<0.05).TNC高表达组患者总生存期均短于TNC低表达组患者(P<0.05).多因素Cox回归分析结果显示,病理分级、术后化疗、1p/19q染色体共缺失和TNC表达水平是脑胶质瘤患者生存期的独立影响因素(P<0.05).结论 TN C在脑胶质瘤中的表达水平与脑胶质瘤的恶性程度相关,可作为脑胶质瘤的诊断标志物及预后预测因子.

-BACKGROUND: Carbamazepine (CBZ) is the first-line therapy for trigeminal neuralgia (TN), and microvascular decompression (MVD) is considered to be an effective surgical treatment for TN. However, the effect of preoperative CBZ treatment on MVD outcome is not clear. -METHODS: From 2013 to 2019, 63 patients with classical TN underwent MVD at the First Affiliated Hospital of Zhengzhou University, China. Data were collected through telephone follow-up and electronic medical records in April 2020. Short-term surgical outcome and long-term follow-up data were estimated by univariate and multivariate analysis. -RESULTS: Multivariate analysis indicated that preoperative CBZ treatment was not a significant predictor for short-term outcomes of MVD (P 0.05). Multivariate analysis for the long-term outcome of MVD indicated that preoperative CBZ treatment could predict postoperative recurrence of TN (P < 0.05). -CONCLUSIONS: For patients with classical TN, a longer preoperative medication history of CBZ treatment had no significant effect on short-term outcome of MVD, but CBZ treatment was associated with a poor long-term outcome following MVD.

Purpose: Early identification of early mortality for glioblastoma (GBM) patients based on laboratory findings at the time of diagnosis could improve the overall survival. The study aimed to explore preoperative factors associated with higher risk of early death (within 1 year after surgery) for isocitrate dehydrogenase (IDH) -wild-type (wt) GBM patients. Patients and Methods: We conducted a retrospective analysis of 194 IDH-wt GBM patients who underwent standard treatment. The probability of dying within 1 year after gross total resection (GTR) was defined as the end point "early mortality". Retrospective collection of predictive factors including clinical characteristics and laboratory data at diagnosis. Results: Median follow-up time after GTR was 16 months (3-41 months). Forty-two patients died within 1 year after surgery (1-year mortality rate: 21.6%). All potential predictive factors were assessed on univariate analyses, which revealed the following factors as associated with higher risk of early death: older age (P = 0.013), occurrence of non-seizures symptoms (P = 0.042), special tumor positions (P = 0.046), higher neutrophil-to-lymphocyte ratio (NLR) (P = 0.015), higher red blood cell distribution width (RDW) (P = 0.019), higher lactate dehydrogenase (LDH) (P = 0.005), and higher fibrinogen (FIB) (P = 0.044). In a multivariate analysis, tumor location (P = 0.012), NLR (P = 0.032) and LDH (P = 0.002) were independent predictors of early mortality. The C-index of the nomogram was 0.795. The calibration curve showed good agreement between prediction by nomogram and actual observation. Conclusion: Tumor location, preoperative elevated NLR and serum LDH level were independent predictors for 1-year mortality after GTR. We indicate that increased preoperative NLR or LDH may guide patients to review head magnetic resonance imaging (MRI) more frequently and regularly to monitor tumor progression.

Objective:To explore the clinical efficacy and intraoperative neuroprotection strategies of individualized selection of surgical approach and microsurgery for jugular foramen schwannoma (JFS) based on the modified Samii classification.Methods:The clinical and imaging data of 28 patients with JFS admitted to the Department of Neurosurgery, the First Affiliated Hospital of Zhengzhou University from January 2015 to December 2019 were retrospectively analyzed. Before surgery, the tumors were classified into types A to D according to the modified Samii classification, and the surgical approach was individualized; 6 cases of type A tumors were treated with the suboccipital retrosigmoid approach, 2 cases of type B1 with the suboccipital transjugular process approach, 5 cases of type B2 with suboccipital retrosigmoid combined with transjugular process approach, 3 cases of type B3 with transjugular process and lateral cervical approach, 4 cases of type C with lateral cervical approach, and 8 cases of type D with suboccipital retrosigmoid approach combined with transjugular process and lateral cervical approach. All patients were followed up at 3, 6, and 12 months after the operation. Head MRI was performed to assess the degree of tumor resection, the House-Brackmann (H-B) grade was used to assess the severity of facial nerve palsy, and the patient′s modified Rankin Scale score (mRS) was assessed 12 months after surgery.Results:All 28 patients successfully underwent the operation. Total tumor resection was performed in 25 cases and subtotal resection in 3 cases. The perioperative cranial nerve complications mainly included 8 cases of aggravated palsy of the posterior cranial nerve and 2 cases of aggravated facial nerve palsy. There was no intracranial hematoma, second operation or death cases. The follow-up time of 28 patients was 35±9 months (12-70) months. At 12 months post operation, 16 cases had a score of 0 to 1, 9 cases were scored 2 and 3 cases were scored 3. At the last follow-up, 3 patients with subtotal tumor resection showed no tumor progression; 25 patients with total tumor resection did not develop tumor recurrence; posterior cranial nerve palsy remained in 5 patients, and there were 3 cases of facial nerve palsy with H-B grade above Ⅲ.Conclusion:Based on the modified Samii classification and individualized selection of surgical approach, following the concept of minimally invasive skull base surgery, microsurgical treatment of JFS can achieve satisfactory clinical results.

2013年7月至2019年8月郑州大学第一附属医院神经外科收治7例小脑发育不良性节细胞瘤患者，结合文献分析该疾病的临床特点、诊治和预后。7例患者的临床表现主要为颅高压症状和小脑症状；MRI表现为病灶在T1加权成像、T2加权成像上呈黑白相间的条纹影("虎纹"征)；2例患者行磁共振波谱检查，显示N-乙酰天冬氨酸、胆碱水平降低。7例患者均行手术切除肿瘤。全切除1例，次全切除3例，部分切除3例。术前相关症状均于术后明显改善，且无一例出现手术相关并发症。随访时间为12～105个月，影像学随访结果显示无一例复发。

Purpose: The purpose of our study is to explore the diagnostic value of the single and combined hematological maker for the classification and isocitrate dehydrogenase (IDH)-1/2 mutations (IDH) molecular subtypes of high-grade gliomas (HGGs). Methods: A total of 354 newly diagnosed HGGs patients were included in this study. Firstly, we compared the levels of hematology indicators in the classification and molecular subtypes of HGGs. Next, the correlation between the levels of hematology indicators with basic clinical features was analyzed. Finally, the diagnostic value of the single and combined hematology indicator for identifying the classification and molecular subtypes from HGGs was performed. Results: The level of fibrinogen (FIB) was higher in higher grade gliomas and glioblastoma multiforme IDH wild type (GBM IDH-wt). Nutrition-related indicators such as serum albumin (ALB), albumin/globulin ratio (AGR), and prognostic nutrition index (PNI) were negatively correlated with age, whereas FIB was positively associated with age. Compared with women, men with GBM had significantly higher AGR and lower serum globulin (GLOB). We found that the best single and combined indicator for identifying GBM and GBM IDH-wt from HGGs were FIB [0.595 (0.519-0.672) and 0.615 (0.546-0.684)] and age+FIB [0.712 (0.642-0.783) and 0.726 (0.662-0.791)], respectively. Conclusions: Preoperative hematological indicators have high diagnostic value for GBM and GBM IDH-wt from HGGs, especially FIB combined age.

OBJECTIVES:The aim of this study was to establish and validate a radiomics nomogram for predicting meningiomas consistency, which could facilitate individualized operation schemes-making.METHODS:A total of 172 patients was enrolled in the study (train cohort: 120 cases, test cohort: 52 cases). Tumor consistency was classified as soft or firm according to Zada's consistency grading system. Radiomics features were extracted from multiparametric MRI. Variance selection and LASSO regression were used for feature selection. Then, radiomics models were constructed by five classifiers, and the area under curve (AUC) was used to evaluate the performance of each classifiers. A radiomics nomogram was developed using the best classifier. The performance of this nomogram was assessed by AUC, calibration and discrimination.RESULTS:A total of 3840 radiomics features were extracted from each patient, of which 3719 radiomics features were stable features. 28 features were selected to construct the radiomics nomogram. Logistic regression classifier had the highest prediction efficacy. Radiomics nomogram was constructed using logistic regression in the train cohort. The nomogram showed a good sensitivity and specificity with AUCs of 0.861 and 0.960 in train and test cohorts, respectively. Moreover, the calibration graph of the nomogram showed a favorable calibration in both train and test cohorts.CONCLUSIONS:The presented radiomics nomogram, as a non-invasive prediction tool, could predict meningiomas consistency preoperatively with favorable accuracy, and facilitated the determination of individualized operation schemes.

This study attempts to explore the radiomics-based features of multi-parametric magnetic resonance imaging (MRI) and construct a machine-learning model to predict the blood supply in vestibular schwannoma preoperatively. By retrospectively collecting the preoperative MRI data of patients with vestibular schwannoma, patients were divided into poor and rich blood supply groups according to the intraoperative recording. Patients were divided into training and test cohorts (2:1), randomly. Stable features were retained by intra-group correlation coefficients (ICCs). Four feature selection methods and four classification methods were evaluated to construct favorable radiomics classifiers. The mean area under the curve (AUC) obtained in the test set for different combinations of feature selecting methods and classifiers was calculated separately to compare the performance of the models. Obtain and compare the best combination results with the performance of differentiation through visual observation in clinical diagnosis. 191 patients were included in this study. 3918 stable features were extracted from each patient. Least absolute shrinkage and selection operator (LASSO) and logistic regression model was selected as the optimal combinations after comparing the AUC calculated by models, which predicted the blood supply of vestibular schwannoma by K-Fold cross-validation method with a mean AUC = 0.88 and F1-score = 0.83. Radiomics machine-learning classifiers can accurately predict the blood supply of vestibular schwannoma by preoperative MRI data.