|Table of Contents|

Application value of MRI peritumoral radiomics features in differentiation between high-grade glioblastoma and single brain metastasis

Journal Of Modern Oncology[ISSN:1672-4992/CN:61-1415/R]

Issue:
2023 06
Page:
1103-1107
Research Field:
Publishing date:

Info

Title:
Application value of MRI peritumoral radiomics features in differentiation between high-grade glioblastoma and single brain metastasis
Author(s):
YUAN Yuan; LI Zhenkai; DU Hongdi; SHEN Hailin
Department of Radiology,Suzhou Kowloon Hospital Affiliated to Shanghai Jiaotong University School of Medicine,Jiangsu Suzhou 215021,China.
Keywords:
radiomics; peritumoral edema; high-grade glioma; single brain metastasis
PACS:
R739.41
DOI:
10.3969/j.issn.1672-4992.2023.06.023
Abstract:
Objective：To investigate the feasibility of MRI peritumoral radiomics analysis in distinguishing high-grade glioblastoma from single brain metastasis.Methods:A total of 67 patients with 39 high-grade gliomas and 28 single brain metastasis confirmed with surgically pathologic proof were retrospectively reviewed.All patients underwent pre-operative MRI，including T2-weighted sequence.The volume of interest of the T2WI sequential tumor was manually divided by 3D-slicer software,and the radiomic features of peritumoral edema (5 mm and 10 mm)were extracted by the radiomic plug-in of 3D-slicer software.Minimum-maximum normalization and optimal feature selection were used to reduce the dimensioning of radiomic features.Finally,R language software was used to establish Logistic regression models,and K-fold cross validation was used to verify the stability of the models.Receiver operating characteristic (ROC) curve was drawn to evaluate the diagnostic effectiveness of the models.Results:Based on the conventional pre-operative MRI,the sensitivity,specificity and area under the curve (AUC) of the 5 mm peritumoral radiomic model in distinguishing high-grade glioblastoma from single brain metastasis were 0.692,0.946 and 0.91,respectively.The sensitivity,specificity and area AUC of the 10 mm peritumoral radiomic model were 0.872,0.893 and 0.93,respectively.K-fold cross validation was used to verify the stability of the models.The mean AUC of the 5 mm and 10 mm peritumoral radiomic models were 0.80 and 0.75 respectively,suggesting that the models have higher diagnostic performance.Conclusion:The use of MRI peritumoral radiomic model can effectively improve the pre-operative diagnostic efficiency of differentiating high-grade glioma and single brain metastasis.

References:

［1］ LOUIS DN,PERRY A,WESSELING P,et al.The 2021 WHO classification of tumors of the central nervous system:a summary［J］.Neuro Oncol，2021，23(8):1231-1251.
［2］ NABORS LB,PORTNOW J,AHLUWALIA M,et al.Central nervous system cancers,version 3.2020,NCCN clinical practice guidelines in oncology［J］.J Natl Compr Canc Netw，2020，18(11):1537-1570.
［3］ CHAND P,AMIT S,GUPTA R,et al.Errors,limitations,and pitfalls in the diagnosis of central and peripheral nervous system lesions in intraoperative cytology and frozen sections［J］.J Cytol Indian Acad Cytol，2016，33:93.
［4］ 张利文,方梦捷,臧亚丽,等.影像组学的发展与应用［J］.中华放射学杂志,2017,51(001):75-77. ZHANG LW,FANG MJ,ZANG YL,et al.Development and application of radiomics［J］.Chinese Journal of Radiology,2017,51(001):75-77.
［5］ STRUGAR J,ROTHBART D,HARRINGTON W,et al.Vascular permeability factor in brain metastases:correlation with vasogenic brain edema and tumor angiogenesis［J］.Journal of Neurosurgery,1994,81(4):560-566.
［6］ LAMBIN P,LEIJENAAR RTH,DEIST TM,et al.Radiomics:the bridge between medical imaging and personalized medicine［J］.Nat Rev Clin Oncol，2017，14(12):749-762.
［7］ GILLIES RJ,KINAHAN PE,HRICAK H.Radiomics:Images are more than pictures,they are data［J］.Radiology，2015，278:563-577.
［8］ LAW M,CHA S,KNOPP EA,et al.High-grade gliomas and solitary metastases:Differentiation by using perfusion and pro-ton spectroscopic MR imaging［J］.Radiology，2002，222:715-721.
［9］ HYUNGJIN K,MIN PC,MYUNGHEE L,et al.Impact of reconstruction algorithms on CT radiomic features of pulmonary tumors:analysis of intra- and inter-reader variability and inter-reconstruction algorithm variability［J］.Plos One,2016,11(10):e0164924.
［10］ HUYNH E,COROLLER TP,NARAYAN V,et al.CT-based radiomic analysis of stereotactic body radiation therapy patients with lung cancer［J］.Radiotherapy & Oncology,2016，2:258-266.
［11］ 刘哲,刘小彤,尹畅畅,等.T2WI机器学习在鉴别高级别胶质瘤和脑单发转移瘤中的应用［J］.西安交通大学学报(医学版),2019,040(005):794-799. LIU Z,LIU XT,YIN CC,et al.Application of T2WI machine learning in the identification of high-grade gliomas and brain solitary metastases［J］.Journal of Xi'an Jiaotong University(Medical Sciences),2019,040(005):794-799.
［12］ 尹浩霖,李冬宝,蒋宇,等.高通量纹理分析鉴别脑内单发转移瘤和高级别胶质瘤［J］.中华肿瘤杂志,2018,40(11):841-846. YIN HL,LI DB,JIANG Y,et al.High-throughput texture analysis in the distinction of single metastatic brain tumors from high-grade gliomas［J］.Chinese Journal of Oncology,2018,40(11):841-846.
［13］ CSUTAK C,TEFAN PA,LENGHEL LM,et al.Differentiating high-grade gliomas from brain metastases at magnetic resonance:The role of texture analysis of the peritumoral zone［J］.Brain Sci，2020，10(9):638.
［14］ MRGINEAN L,TEFAN PA,LEBOVICI A,et al.CT in the differentiation of gliomas from brain metastases:The radiomics analysis of the peritumoral zone［J］.Brain Sci，2022，12(1):109.
［15］ 王敏红,冯湛.瘤周水肿常规MRI纹理分析鉴别脑胶质母细胞瘤和单发转移瘤的价值［J］.中华放射学杂志,2018,52(10):756-760. WANG MH,FENG Z.The value of conventional MRI texture analysis of peritumoral edema in differentiating glioblastoma from solitary metastatic tumor［J］.Chinese Journal of Radiology,2018,52(10):756-760.

Memo

Memo:
-
Last Update: 1900-01-01