基于宏观与微观影像学特征融合的胶质瘤基因状态与分级预测研究

doi:10.3969/j.issn.1672-6731.2025.03.002

中国现代神经疾病杂志 ›› 2025, Vol. 25 ›› Issue (3): 165-174. doi: 10.3969/j.issn.1672-6731.2025.03.002

2 基于宏观与微观影像学特征融合的胶质瘤基因状态与分级预测研究

李臻¹, 宋鹏斐², 朱锐泽¹, 江山¹, 曹诗文³, 余锦华⁴, 史之峰¹^,*()

1. 201107 上海，复旦大学附属华山医院神经外科(李臻，朱锐泽，江山，史之峰)
2. 200438 上海，复旦大学信息科学与工程学院生物医学工程系 2023 级(宋鹏斐)
3. 200438 上海，复旦大学信息科学与工程学院生物医学工程系 2021 级(曹诗文)
4. 200438 上海，复旦大学信息科学与工程学院生物医学工程系, 生物医学工程系(余锦华)

收稿日期:2025-02-13 出版日期:2025-03-25 发布日期:2025-04-21
通讯作者: 史之峰
作者简介:
李臻与宋鹏斐对本文有同等贡献

LI Zhen and SONG Peng-fei contributed equally to the article
基金资助:
上海市卫生健康委员会优秀项目(20234Z0009); 国家重点研发计划项目(2022YFF1202804); 国家自然科学基金资助项目(82373018); 国家自然科学基金资助项目(82072020); 上海市科委医学创新研究项目(23Y11906200)

Prediction of genetic status and grading in glioma based on fusion of macro - and micro-imaging features

Zhen LI¹, Peng-fei SONG², Rui-ze ZHU¹, Shan JIANG¹, Shi-wen CAO³, Jin-hua YU⁴, Zhi-feng SHI¹^,*()

1. Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai 201107, China
2. Grade 2023 of Department of Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai 200438, China
3. Grade 2021 of Department of Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai 200438, China
4. Department of Biomedical Engineering, School of Information Science and Technology, Fudan University, Shanghai 200438, China

Received:2025-02-13 Online:2025-03-25 Published:2025-04-21
Contact: Zhi-feng SHI
Supported by:
Excellent Project of Shanghai Municipal Health Commission(20234Z0009); National Key Research and Development Program of China(2022YFF1202804); The National Natural Science Foundation of China(82373018); The National Natural Science Foundation of China(82072020); Medical Innovation Research Project of Shanghai Science and Technology Commission(23Y11906200)

摘要/Abstract

摘要：

目的: 建立基于MRI与全视野数字切片(WSI)特征融合的双层特征蒸馏的多实例学习(DLFD-MIL)模型，实现对成人型弥漫性胶质瘤IDH1突变、1p/19q共缺失及世界卫生组织(WHO)分级的高精准性预测。方法: 选择2021年1月至2024年6月复旦大学附属华山医院收治的212例成人型弥漫性胶质瘤患者及美国癌症基因组图谱计划42例成人型弥漫性胶质瘤病例，联合分析术前T₂-FLAIR影像与术后WSI数据。构建DLFD-MIL模型，采用伪包生成策略解决WSI弱监督学习中的实例标签缺失问题，Concat融合方式实现多模态融合；绘制受试者工作特征曲线，以曲线下面积比较单模态与多模态特征融合对胶质瘤基因状态和WHO分级的预测效能。结果: 在IDH1突变预测任务中，多模态特征融合模型的曲线下面积大于单模态WSI模型(Z = 2.752，P = 0.006)和单模态T₂-FLAIR模型(Z = 5.662，P = 0.000)；在1p/19q共缺失预测任务中，多模态特征融合模型的曲线下面积与单模态WSI模型(Z = - 0.245，P = 0.806)和单模态T₂-FLAIR模型(Z = 0.781，P = 0.435)差异均无统计学意义；在WHO分级预测任务中，多模态特征融合模型的曲线下面积大于单模态T₂-FLAIR模型(Z = 4.830，P = 0.000)，而与单模态WSI模型差异无统计学意义(Z = 1.739，P = 0.082)。结论: 基于宏观与微观影像学特征融合模型可以提高胶质瘤IDH1基因分型和WHO分级的预测精度，为临床制定个性化治疗方案提供可靠的人工智能决策支持工具。

关键词: 神经胶质瘤, 磁共振成像, 病理学, 基因, 肿瘤分级, 深度学习, ROC曲线

Abstract:

Objective: To develop a dual-layer feature distillation multiple instance learning (DLFD- MIL) model integrating MRI and whole slide image (WSI) features for precise prediction of IDH1 mutation, 1p/19q codeletion, and World Health Organization (WHO) grading in adult-type diffuse gliomas. Methods: A retrospective cohort of 212 adult-type diffuse gliomas patients from Huashan Hospital, Fudan University (January 2021 to June 2024) and 42 cases from The Cancer Genome Atlas (TCGA) were included. Preoperative T₂-FLAIR and postoperative WSI data were jointly analyzed. The DLFD-MIL model addressed the lack of instance - level labels in weakly supervised WSI learning via a pseudo - bag generation strategy. Multimodal feature fusion was achieved through Concat. Diagnostic performance for molecular subtyping and WHO grading was evaluated by comparing area under the curve (AUC) of receiver operating characteristic (ROC) curve between single - mode (WSI or MRI) and multi - mode. Results: In the IDH1 mutation prediction task, AUC of the multi - mode feature fusion model surpassed single - mode WSI model (Z = 2.752, P = 0.006) and single-mode T₂ -FLAIR model (Z = 5.662, P = 0.000). In the 1p/19q codeletion prediction task, no statistically significant differences in AUC were observed between the multi-mode feature fusion model and either single-mode WSI model (Z = - 0.245, P = 0.806) or T₂-FLAIR model (Z = 0.781, P = 0.435). In the WHO grading prediction task, the multi - mode feature fusion model showed no significant differences in AUC compared to single - mode WSI model (Z = 1.739, P = 0.082), however its AUC was significantly higher than single -mode T₂ -FLAIR model (Z = 4.830, P = 0.000). Conclusions: Multi-mode fusion of macro - and micro - imaging features improves prediction accuracy for IDH1 genotyping and WHO grading in gliomas, providing a reliable artificial intelligence (AI) decision - support tool for personalized clinical management.

Key words: Glioma, Magnetic resonance imaging, Pathology, Genes, Neoplasm grading, Deep learning, ROC curve

李臻, 宋鹏斐, 朱锐泽, 江山, 曹诗文, 余锦华, 史之峰. 基于宏观与微观影像学特征融合的胶质瘤基因状态与分级预测研究[J]. 中国现代神经疾病杂志, 2025, 25(3): 165-174.

Zhen LI, Peng-fei SONG, Rui-ze ZHU, Shan JIANG, Shi-wen CAO, Jin-hua YU, Zhi-feng SHI. Prediction of genetic status and grading in glioma based on fusion of macro - and micro-imaging features[J]. Chinese Journal of Contemporary Neurology and Neurosurgery, 2025, 25(3): 165-174.

/ 收藏文章 0 / 推荐 / 导出引用

链接本文: https://journal11.magtechjournal.com/cjcnn/CN/10.3969/j.issn.1672-6731.2025.03.002

https://journal11.magtechjournal.com/cjcnn/CN/Y2025/V25/I3/165

图/表 9

图 1 基于AB-MIL的WSI伪包特征提取模型 WSI，全视野数字切片；ResNet，深度残差网络；b1 ~ bn，注意力权重；AB-MIL，基于注意力机制的多实例学习

Figure 1 AB-MIL-based pseudo-bag feature extraction model for WSI.

图 2 基于双层AB-MIL的WSI特征蒸馏流程 WSI，全视野数字切片；ResNet，深度残差网络；AB-MIL，基于注意力机制的多实例学习；y¹ ~ yⁿ，伪包标签继承父包标签，与Y相同；ŷ，第二层AB-MIL输出的全局特征预测结果；Y，真实病理诊断标签

Figure 2 Dual-layer AB-MIL-based WSI feature distillation pipeline.

图 3 宏观与微观多模态特征融合预测基因状态和WHO分级的整体框架 3D U - Net，三维U - Net网络；WSI，全视野数字切片；ResNet，深度残差网络；AB-MIL，基于注意力机制的多实例学习；N，特征维度；IDH1 - W，IDH1野生型；IDH1 - M，IDH1突变型；1p19q-Y，1p/19q共缺失；1p19q-N，1p/19q无共缺失；HGG，高级别胶质瘤；LGG，低级别胶质瘤

Figure 3 Integrated framework for predicting genetic status and WHO grading through macro-and micro-scopic feature fusion.

表 1 不同诊断模型对IDH1突变状态预测效能的比较（例）

Table 1. Comparison of predictive performance of different diagnostic models for IDH1 mutation status (case)

诊断试验	金标准		合计	诊断试验	金标准		合计	诊断试验	金标准		合计
诊断试验	突变型	野生型	合计	诊断试验	突变型	野生型	合计	诊断试验	突变型	野生型	合计
单模态T₂-FLAIR				单模态 WSI				多模态特征融合
预测突变型	11	1	12	预测突变型	36	11	47	预测突变型	39	8	47
预测野生型	29	43	72	预测野生型	4	33	37	预测野生型	1	36	37
合计	40	44	84	合计	40	44	84	合计	40	44	84

表 2 不同诊断模型对1p/19q共缺失状态预测效能的比较（例）

Table 2. Comparison of predictive performance of different diagnostic models for 1p/19q codeletion status (case)

诊断试验	金标准		合计	诊断试验	金标准		合计	诊断试验	金标准		合计
诊断试验	共缺失	无共缺失	合计	诊断试验	共缺失	无共缺失	合计	诊断试验	共缺失	无共缺失	合计
单模态T₂-FLAIR				单模态 WSI				多模态特征融合
预测共缺失	8	8	16	预测共缺失	11	11	22	预测共缺失	15	25	40
预测无共缺失	11	57	68	预测无共缺失	8	54	62	预测无共缺失	4	40	44
合计	19	65	84	合计	19	65	84	合计	19	65	84

表 3 不同诊断模型对WHO分级预测效能的比较（例）

Table 3. Comparison of predictive performance of different diagnostic models for WHO grading (case)

诊断试验	金标准		合计	诊断试验	金标准		合计	诊断试验	金标准		合计
诊断试验	高级别	低级别	合计	诊断试验	高级别	低级别	合计	诊断试验	高级别	低级别	合计
单模态T₂-FLAIR				单模态 WSI				多模态特征融合
预测高级别	16	2	18	预测高级别	35	5	40	预测高级别	38	4	42
预测低级别	30	36	66	预测低级别	11	33	44	预测低级别	8	34	42
合计	46	38	84	合计	46	38	84	合计	46	38	84

图 4 基于宏观与微观影像学特征融合预测基因状态和WHO分级的ROC曲线 4a IDH1突变状态预测 4b 1p/19q共缺失状态预测 4c WHO分级预测 AUC，曲线下面积；WSI，全视野数字切片

Figure 4 ROC curves for predicting genetic status and WHO grading based on macro - and micro - imaging features fusion IDH1 mutation status prediction (Panel 4a). 1p/19q codeletion status prediction (Panel 4b). WHO grading prediction (Panel 4c).

表 4 多模态特征融合模型与单模态模型预测效能的比较

Table 4. Comparison of predictive performance between multi-mode feature fusion model and single-mode model

组间两两比	IDH1突变
组间两两比	Z值	P值
多模态特征融合∶单模态WSI	2.752	0.006
多模态特征融合∶单模态T₂-FLAIR	5.662	0.000
单模态WSI∶单模态T₂-FLAIR	4.064	0.000

组间两两比	1p/19q共缺失
组间两两比	Z值	P值
多模态特征融合∶单模态WSI	-0.245	0.806
多模态特征融合∶单模态T₂-FLAIR	0.781	0.435
单模态WSI∶单模态T₂-FLAIR	0.712	0.476

组间两两比	WHO分级
组间两两比	Z值	P值
多模态特征融合∶单模态WSI	1.739	0.082
多模态特征融合∶单模态T₂-FLAIR	4.830	0.000
单模态WSI∶单模态T₂-FLAIR	3.819	0.000

图 5 基于宏观与微观影像学特征融合预测基因状态和WHO分级的决策曲线分析图 5a IDH1突变状态预测 5b 1p/19q共缺失状态预测 5c WHO分级预测 WSI，全视野数字切片；treat all，全治疗决策；treat none，全不治疗决策

Figure 5 DCA for predicting genetic status and WHO grading based on macro - and micro - imaging features fusion IDH1 mutation status prediction (Panel 5a). 1p/19q codeletion status prediction (Panel 5b). WHO grading prediction (Panel 5c).

参考文献 32

1	Price M , Ballard C , Benedetti J , Neff C , Cioffi G , Waite KA , Kruchko C , Barnholtz-Sloan JS , Ostrom QT . CBTRUS statistical report: primary brain and other central nervous system tumors diagnosed in the United States in 2017-2021. Neuro Oncol, 2024, 26 (Supplement_6): ⅵ1- ⅵ85. doi: 10.1093/neuonc/noae145
2	Schaff LR , Mellinghoff IK . Glioblastoma and other primary brain malignancies in adults: a review. JAMA, 2023, 329: 574- 587. doi: 10.1001/jama.2023.0023
3	Louis DN , Perry A , Wesseling P , Brat DJ , Cree IA , Figarella-Branger D , Hawkins C , Ng HK , Pfister SM , Reifenberger G , Soffietti R , von Deimling A , Ellison DW . The 2021 WHO Classification of Tumors of the Central Nervous System: a summary. Neuro Oncol, 2021, 23: 1231- 1251. doi: 10.1093/neuonc/noab106
4	Horbinski C , Berger T , Packer RJ , Wen PY . Clinical implications of the 2021 edition of the WHO classification of central nervous system tumours. Nat Rev Neurol, 2022, 18: 515- 529. doi: 10.1038/s41582-022-00679-w
5	Weller M , van den Bent M , Preusser M , Le Rhun E , Tonn JC , Minniti G , Bendszus M , Balana C , Chinot O , Dirven L , French P , Hegi ME , Jakola AS , Platten M , Roth P , Rudà R , Short S , Smits M , Taphoorn MJB , von Deimling A , Westphal M , Soffietti R , Reifenberger G , Wick W . EANO guidelines on the diagnosis and treatment of diffuse gliomas of adulthood. Nat Rev Clin Oncol, 2021, 18: 170- 186. doi: 10.1038/s41571-020-00447-z
6	Makino K , Nakamura H , Hide T , Yano S , Kuroda J , Takahashi Y , Iyama K , Kuratsu J . Usefulness of immunohistochemical expression analysis of metabolic - related molecules in differentiating between intracranial neoplastic and non - neoplastic lesions. Brain Tumor Pathol, 2013, 30: 144- 150. doi: 10.1007/s10014-012-0120-2
7	Brandes AA , Tosoni A , Franceschi E , Sotti G , Frezza G , Amistà P , Morandi L , Spagnolli F , Ermani M . Recurrence pattern after temozolomide concomitant with and adjuvant to radiotherapy in newly diagnosed patients with glioblastoma: correlation with MGMT promoter methylation status. J Clin Oncol, 2009, 27: 1275- 1279. doi: 10.1200/JCO.2008.19.4969
8	Hu ZY , Wei W , Hu WZ , Ma MH , Li Y , Wu XS , Yin H , Xi YB . Prediction of IDH mutations in glioma based on MRI multiparametric image fusion and DenseNet network. Ci Gong Zhen Cheng Xiang, 2023, 14: 10- 17.
	胡振远, 魏炜, 胡文鐘, 马梦航, 李艳, 吴旭莎, 印弘, 席一斌. 基于磁共振多参数图像融合及DenseNet网络的脑胶质瘤IDH突变预测研究. 磁共振成像, 2023, 14: 10- 17.
9	Liu ZP , Jiang JX , Wu QW , Zhou Y , Bian XF , Zhu YX . Prediction of glioma grading based on multi - sequence MRI radiomics and deep transfer learning features. Nanjing Yi Ke Da Xue Xue Bao (Zi Ran Ke Xue Ban), 2024, 44: 372- 379. doi: 10.7655/NYDXBNSN230893
	刘志鹏, 降建新, 吴琪炜, 周炎, 卞雪峰, 朱银杏. 基于多序列MRI影像组学与深度迁移学习特征的脑胶质瘤分级预测研究. 南京医科大学学报(自然科学版), 2024, 44: 372- 379. doi: 10.7655/NYDXBNSN230893
10	Xue H , Han Z , Li H , Li X , Jia D , Qi M , Zhang H , Zhang K , Gong J , Wang H , Feng Z , Ni S , Han B , Li G . Application of intraoperative rapid molecular diagnosis in precision surgery for glioma: mimic the world health organization CNS5 integrated diagnosis. Neurosurgery, 2023, 92: 762- 771. doi: 10.1227/neu.0000000000002260
11	Zhang H, Meng Y, Zhao Y, Qiao Y, Yang X, Coupland SE, Zheng Y. DTFD - MIL: double - tier feature distillation multiple instance learning for histopathology whole slide image classification[C]//2022 IEEE/CVF conference on computer vision and pattern recognition (CVPR), New Orleans: IEEE, 2022: 18780-18790.
12	Ilse M , Tomczak JM , Welling M . Attention -based deep multiple instance learning. Proc Mach Learn Res, 2018, 80: 2127- 2136.
13	Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A. Learning deep features for discriminative localization[C]//2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas: IEEE, 2016: 2921-2929.
14	Hou L , Samaras D , Kurc TM , Gao Y , Davis JE , Saltz JH . Patch- based convolutional neural network for whole slide tissue image classification. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit, 2016, 2424- 2433.
15	Xu G, Song Z, Sun Z, Ku C, Yang Z, Liu C, Wang S, Ma J, Xu W. CAMEL: aweakly supervised learning framework for histopathology image segmentation[C]//2019 IEEE/CVF international conference on computer vision (ICCV), Seoul: IEEE, 2019: 10681-10690.
16	Campanella G , Hanna MG , Geneslaw L , Miraflor A , Werneck Krauss Silva V , Busam KJ , Brogi E , Reuter VE , Klimstra DS , Fuchs TJ . Clinical - grade computational pathology using weakly supervised deep learning on whole slide images. Nat Med, 2019, 25: 1301- 1309. doi: 10.1038/s41591-019-0508-1
17	Kanavati F , Toyokawa G , Momosaki S , Rambeau M , Kozuma Y , Shoji F , Yamazaki K , Takeo S , Iizuka O , Tsuneki M . Weakly - supervised learning for lung carcinoma classification using deep learning. Sci Rep, 2020, 10: 9297. doi: 10.1038/s41598-020-66333-x
18	Sharma Y , Shrivastava A , Ehsan L , Moskaluk CA , Syed S , Brown DE . Cluster - to-conquer: a framework for end-to-end multi-instance learning for whole slide image classification. Proc Mach Learn Res, 2021, 143: 682- 698.
19	Shao Z , Bian H , Chen Y , Wang Y , Zhang J , Ji X , Zhang Y . TransMIL: transformer based correlated multiple instance learning for whole slide image classification. Adv Neural Inform Process Syst, 2021, 34: 2136- 2147.
20	Li B , Li Y , Eliceiri KW . Dual -stream multiple instance learning network for whole slide image classification with self-supervised contrastive learning. Conf Comput Vis Pattern Recognit Workshops, 2021, 14318- 14328.
21	Hsu WW , Guo JM , Pei L , Chiang LA , Li YF , Hsiao JC , Colen R , Liu P . A weakly supervised deep learning - based method for glioma subtype classification using WSI and mpMRIs. Sci Rep, 2022, 12: 6111. doi: 10.1038/s41598-022-09985-1
22	Despotovic V , Kim SY , Hau AC , Kakoichankava A , Klamminger GG , Borgmann FBK , Frauenknecht KBM , Mittelbronn M , Nazarov PV . Glioma subtype classification from histopathological images using in - domain and out - of - domain transfer learning: an experimental study. Heliyon, 2024, 10: e27515. doi: 10.1016/j.heliyon.2024.e27515
23	Chen Y , Yang Z , Zhao J , Adamson J , Sheng Y , Yin FF , Wang C . A radiomics - incorporated deep ensemble learning model for multi-parametric MRI-based glioma segmentation. Phys Med Biol, 2023, ID37586382.
24	Xie X , Shen C , Zhang X , Wu G , Yang B , Qi Z , Tang Q , Wang Y , Ding H , Shi Z , Yu J . Rapid intraoperative multi - molecular diagnosis of glioma with ultrasound radio frequency signals and deep learning. EBioMedicine, 2023, 98: 104899. doi: 10.1016/j.ebiom.2023.104899
25	Alongi P , Arnone A , Vultaggio V , Fraternali A , Versari A , Casali C , Arnone G , DiMeco F , Vetrano IG . Artificial intelligence analysis using MRI and PET imaging in gliomas: a narrative review. Cancers (Basel), 2024, 16: 407. doi: 10.3390/cancers16020407
26	Paprottka KJ , Kleiner S , Preibisch C , Kofler F , Schmidt-Graf F , Delbridge C , Bernhardt D , Combs SE , Gempt J , Meyer B , Zimmer C , Menze BH , Yakushev I , Kirschke JS , Wiestler B . Fully automated analysis combining. Eur J Nucl Med Mol Imaging, 2021, 48: 4445- 4455. doi: 10.1007/s00259-021-05427-8
27	Yuan Y , Li G , Mei S , Hu M , Chu YH , Hsu YC , Li C , Song J , Hu J , Feng D , Xie F , Guan Y , Yue Q , Liu M , Mao Y . Deep mutual learning on hybrid amino acid PET predicts H3K27M mutations in midline gliomas. NPJ Precis Oncol, 2024, 8: 274. doi: 10.1038/s41698-024-00760-1
28	Zadeh A, Chen M, Poria S, Cambria E, Morency LP. Tensor fusion network for multimodal sentiment analysis[C]//Palmer M, Hwa R, Riedel S. Proceedings of the 2017 conference on empirical methods in natural language processing, Copenhagen: Association for Computational, 2017: 1103-1114.
29	Xing X , Chen Z , Hou Y , Yuan Y . Gradient modulated contrastive distillation of low - rank multi - modal knowledge for disease diagnosis. Med Image Anal, 2023, 88: 102874. doi: 10.1016/j.media.2023.102874
30	Xing X , Zhu M , Chen Z , Yuan Y . Comprehensive learning and adaptive teaching: distilling multi - modal knowledge for pathological glioma grading. Med Image Anal, 2024, 91: 102990. doi: 10.1016/j.media.2023.102990
31	Huang P , Li D , Jiao Z , Wei D , Cao B , Mo Z , Wang Q , Zhang H , Shen D . Common feature learning for brain tumor MRI synthesis by context - aware generative adversarial network. Med Image Anal, 2022, 79: 102472. doi: 10.1016/j.media.2022.102472
32	Wang J , Wang X , Zhang P , Xie S , Fu S , Li Y , Han H . Correction of uneven illumination in color microscopic image based on fully convolutional network. Opt Express, 2021, 29: 28503- 28520. doi: 10.1364/OE.433064

编辑推荐 0

Metrics

阅读次数

全文

HTML			PDF

最新录用	在线预览	正式出版	最新录用	在线预览	正式出版
0	0	3	0	0	25

来源	本网站	其他网站

次数	23	5
比例	82%	18%

摘要

最新录用	在线预览	正式出版

0	0	78

来源	本网站	其他网站

次数	38	40
比例	49%	51%

[1]	杨学军, 师炜, 张恺. 2024年中国脑胶质瘤诊断与治疗发展与创新[J]. 中国现代神经疾病杂志, 2025, 25(3): 161-164.
[2]	程星, 王治超, 李华宁, 王协锋, 尤永平. 基于多参数MRI脑-肿瘤界面影像组学模型预测脑膜瘤侵犯程度的应用研究[J]. 中国现代神经疾病杂志, 2025, 25(3): 175-186.
[3]	韩哲, 李刚, 薛皓. 分子诊断在胶质瘤手术中的应用初探[J]. 中国现代神经疾病杂志, 2025, 25(3): 187-192.
[4]	吴东东, 束旭俊, 赵恺, 丛小均, 周星宇, 夏鹰, 孙国臣. 智能化水分离技术在岛叶胶质瘤手术壳核外侧面分离中的应用[J]. 中国现代神经疾病杂志, 2025, 25(3): 193-198.
[5]	姚书敬, 王洋, 杨瑞鑫, 余珊, 王玉宝, 白红民. 唤醒开颅手术在脑功能区复发胶质瘤治疗中的初步研究[J]. 中国现代神经疾病杂志, 2025, 25(3): 207-214.
[6]	郑丹枫, 李春瑶, 刘向一, 郭文阳, 孟庆阳, 钟延丰, 张英爽. 具有杆状体结构的肌肉病临床病理学特征分析与鉴别诊断[J]. 中国现代神经疾病杂志, 2025, 25(3): 247-258.
[7]	俱京涛, 陈昕, 刘佳宾, 胡永生, 王雷明, 陈楠. MRI阴性的局灶性皮质发育不良临床特征分析[J]. 中国现代神经疾病杂志, 2025, 25(3): 259-264.
[8]	吴红梅, 季涛云, 张继新. Rasmussen脑炎发病机制及治疗进展[J]. 中国现代神经疾病杂志, 2025, 25(3): 265-270.
[9]	孙翌朔, 张伟. 多组学技术辅助胶质瘤治疗的研究进展[J]. 中国现代神经疾病杂志, 2025, 25(2): 136-143.
[10]	臧玉峰. 脑影像引导的精准定位经颅磁刺激神经调控治疗进展[J]. 中国现代神经疾病杂志, 2025, 25(2): 152-154.
[11]	郭松, 张弘灏, 李建宇, 杨岸超. 特发性震颤神经调控治疗进展[J]. 中国现代神经疾病杂志, 2025, 25(1): 24-32.
[12]	杨学军. 儿童胶质瘤诊断与治疗要点及进展[J]. 中国现代神经疾病杂志, 2024, 24(9): 695-700.
[13]	盖菁菁, 孔晨晨, 赵传, 张俊平. 儿童型低级别胶质瘤药物化疗及靶向治疗进展[J]. 中国现代神经疾病杂志, 2024, 24(9): 706-711.
[14]	丁兴华, 祝迎锋, 张超, 祝翊倩, 张荣. 基于扩散加权成像的儿童后颅窝常见肿瘤诊断与鉴别诊断[J]. 中国现代神经疾病杂志, 2024, 24(9): 723-731.
[15]	陈新, 童文娟. 儿童药物难治性癫痫视频脑电图及影像学特征分析[J]. 中国现代神经疾病杂志, 2024, 24(9): 744-750.

选择文件类型/文献管理软件名称

选择包含的内容

2 基于宏观与微观影像学特征融合的胶质瘤基因状态与分级预测研究

Prediction of genetic status and grading in glioma based on fusion of macro - and micro-imaging features

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 32

相关文章 15

编辑推荐 0

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

2 基于宏观与微观影像学特征融合的胶质瘤基因状态与分级预测研究

Prediction of genetic status and grading in glioma based on fusion of macro - and micro-imaging features

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 32

相关文章 15

编辑推荐 0

Metrics

本文评价