基于CnViT的胶质瘤IDH1突变状态智能预测方法

doi:10.6040/j.issn.1672-3961.0.2022.122

山东大学学报 (工学版) ›› 2023, Vol. 53 ›› Issue (2): 127-134.doi: 10.6040/j.issn.1672-3961.0.2022.122

基于CnViT的胶质瘤IDH1突变状态智能预测方法

徐芊芊¹,许倩²,徐华畅¹,赵钰琳¹,徐凯²,朱红^1*

1.徐州医科大学医学信息与工程学院, 江苏徐州 221000;2.徐州医科大学附属医院影像科, 江苏徐州 221000

收稿日期:2022-04-03 出版日期:2023-04-22 发布日期:2023-04-21
作者简介:徐芊芊(1997— ),女,江苏徐州人,硕士研究生,主要研究方向为智能医学图像处理. E-mail: 301910911594@stu.xzhmu.edu.cn. *通信作者简介:朱红(1970— ),女,江苏徐州人,教授,博士,主要研究方向为人工智能. E-mail: zhuhong@xzhmu.edu.cn
基金资助:
江苏省卫生健康委医学科研项目(Z2020032);徐州市卫生健康委员会青年医学科技创新项目(XWKYHT20210586)

Intelligent prediction method of IDH1 mutation status of glioma based on CnViT

XU Qianqian¹, XU Qian², XU Huachang¹, ZHAO Yulin¹, XU Kai², ZHU Hong^1*

1. School of Medical Information and Engineering, Xuzhou Medical University, Xuzhou 221000, Jiangsu, China;
2. RadiologyDepartment, the Affiliated Hospital of Xuzhou Medical University, Xuzhou 221000, Jiangsu, China

Received:2022-04-03 Online:2023-04-22 Published:2023-04-21

摘要/Abstract

摘要： 为了提高胶质瘤影像数据利用率,实现胶质瘤-异柠檬酸脱氢酶1(isocitrate dehydrogenase1, IDH1)突变状态术前无创预测,提出一种基于影像组学与粗糙集属性约简算法的伪标签标注算法,为无标签胶质瘤影像做伪标签标注;提出一种基于卷积神经网络和Vision Transformer的分类模型,并在模型中加入基于胶质瘤位置信息的先验知识,用于胶质瘤IDH1突变状态预测。伪标签标注算法实现了胶质瘤影像数据扩增,基于卷积神经网络和Vision Transformer的分类模型在胶质瘤IDH1突变状态预测中的准确率为93.27%。试验结果表明,提出的方法能够有效提高胶质瘤影像利用率和胶质瘤IDH1突变状态智能诊断准确率,可实现术前无创预测,从而辅助医生诊断和制定治疗方案。

关键词: 胶质瘤IDH1, 影像组学, 伪标签, Vision Transformer, 先验知识

中图分类号:

TP18

徐芊芊,许倩,徐华畅,赵钰琳,徐凯,朱红. 基于CnViT的胶质瘤IDH1突变状态智能预测方法[J]. 山东大学学报 (工学版), 2023, 53(2): 127-134.

XU Qianqian, XU Qian, XU Huachang, ZHAO Yulin, XU Kai, ZHU Hong. Intelligent prediction method of IDH1 mutation status of glioma based on CnViT[J]. Journal of Shandong University(Engineering Science), 2023, 53(2): 127-134.

参考文献 20

[1]	University of California San Francisco. Brain tumor center[EB/OL].(2019-01-01)[2021-05-25].https://braintumorcenter.ucsf.edu/condition.
[2]	马杰,刘芳.异柠檬酸脱氢酶1突变在胶质瘤免疫治疗中的研究进展[J]. 癌症进展, 2022, 20(2): 109-112. MA Jie, LIU Fang. Research progress of isocitrate dehydrogenase 1 mutation in glioma immunotherapy[J]. Cancer Progression, 2022, 20(2): 109-112.
[3]	LOUIS D N, PERRY A, REIFENBERGER G, et al. The 2016 World Health Organization classification of tumors of the central nervous system: a summary[J]. Acta Neuropathologica, 2016, 131(6): 803-820.
[4]	李锐, 马林. IDH基因突变与胶质瘤相关性的研究进展[J]. 中国医学影像学杂志, 2020, 28(2): 142-145. LI Rui, MA Lin. Research progress on the correlation between IDH gene mutation and glioma[J]. Chinese Journal of Medical Imaging, 2020, 28(2): 142-145.
[5]	WANG Shuo, SHI Jingyun, YE Zhaoxiang, et al. Predicting EGFR mutation status in lung adenocarcinoma on computed tomography image using deep learning[J]. European Respiratory Journal, 2019, 53(3): 1800986.
[6]	YOGANANDA C G B, SHAH B R, VEJDANI-JAHROMI M,et al.A novel fully automated MRI-based deep-learning method for classification of IDH mutation status in brain gliomas[J]. Neuro-Oncology, 2020, 22(3):402-411.
[7]	夏水伟, 周永进, 陈春妙,等. 基于MRI增强T1WI影像组学预测模型鉴别高级别胶质瘤IDH1突变型与野生型的价值[J]. 温州医科大学学报, 2021, 51(10): 800-805. XIA Shuiwei, ZHOU Yongjin, CHEN Chunmiao, et al. The value of MRI-enhanced T1WI radiomics prediction model in identifying IDH1 mutant and wild type in high-grade glioma[J]. Journal of Wenzhou Medical University, 2021, 51(10): 800-805.
[8]	TAHA B, LI T H, BOLEY D, et al. Detection of isocitrate dehydrogenase mutated glioblastomas through anomaly detection analytics[J]. Neurosurgery, 2021, 89(2): 323-328.
[9]	CHOI Y S, BAE S, CHANG J H, et al. Fully automated hybrid approach to predict the IDH mutation status of gliomas via deep learning and radiomics[J].Neuro-Oncology, 2021,23(2):304-313.
[10]	QI Songtao, YU Lei, LI Hezhen, et al. Isocitrate dehydrogenase mutation is associated with tumor location and magnetic resonance imaging characteristics in astrocytic neoplasms[J].Oncology Letters, 2014, 7(6): 1895-1902.
[11]	SONODA Y, SHIBAHARA I, KAWAGUCHI T, et al. Association between molecular alterations and tumor location and MRI characteristics in anaplastic gliomas[J].Brain Tumor Pathology, 2015, 32(2): 99-104.
[12]	PAWLAK Z, GRZYMALA-BUSSE J, SLOWINSKI R, et al. Rough sets[J]. Communications of the ACM, 1995, 38(11): 88-95.
[13]	LAMBIN P, RIOS-BELAZQUEZ E, LEIJENAAR R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. European Journal of Cancer, 2012,48(4): 441-446.
[14]	胡云涛,黄小华, 刘念,等. 影像组学在原发性肝癌中的研究进展[J]. 国际医学放射学杂志, 2021,44(1): 76-80. HU Yuntao, HUANG Xiaohua, LIU Nian,et al. Research progress of radiomics in primary liver cancer[J]. International Journal of Medical Radiology, 2021,44(1): 76-80.
[15]	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C] //Neural Information Processing Systems. California, USA:MIT Press, 2017:6000-6010.
[16]	DOSOVITSKIY A, BEYER L, KOLESNIKOV A, et al. An image is worth 16SymboltB@16 words: transformers for image recognition at scale[C] //International Conference on Learning Representations. Vienna, Austria:[s.n] , 2021.
[17]	ZHANG Lifei, FRIED D V, FAVE X J, et al. IBEX:an open infrastructure software platform to facilitate collaborative work in radiomics[J]. Medical Physics, 2015, 42(3): 1341-1353.
[18]	刘光宇,黄懿,曹禹,等. 基于灰度共生矩阵的图像纹理特征提取研究[J]. 科技风, 2021(12): 61-64. LIU Guangyu, HUANG Yi, CAO Yu, et al. Research on image texture feature extraction based on grey level co-occurrence matrix[J]. Technology Wind, 2021(12):61-64.
[19]	王铭,田为中,张继,等.基于TIRM序列的游程矩阵纹理特征联合ADC值预测乳腺癌Ki-67表达水平[J]. 放射学实践, 2021,36(12): 1520-1525. WANG Ming, TIAN Weizhong, ZHANG Ji, et al. Prediction of Ki-67 expression level in breast cancer based on run-length matrix texture feature combined with ADC value based on TIRM sequence[J]. Radiology Practice, 2021, 36(12):1520-1525.
[20]	CHOI K S, CHOI S H, JEONG B.Prediction of IDH genotype in gliomas with dynamic susceptibility contrast perfusion MR imaging using an explainable recurrent neural network[J]. Neuro-Oncology, 2019, 21(9):1197-1209.

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于CnViT的胶质瘤IDH1突变状态智能预测方法

Intelligent prediction method of IDH1 mutation status of glioma based on CnViT

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献 20

相关文章 2

多维度评价

本文评价

推荐阅读 10

[1]	刘子一,崔超然,孟凡安,林培光. 基于批归一化统计量的无源多领域自适应方法[J]. 山东大学学报 (工学版), 2023, 53(2): 102-108.
[2]	杨霄,袭肖明,李维翠,杨璐. 基于层次化双重注意力网络的乳腺多模态图像分类[J]. 山东大学学报 (工学版), 2022, 52(3): 34-41.