|Table of Contents|

The value of multi-parameter magnetic resonance imaging radiomics in distinguishing high-grade gliomas from single brain metastases

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

Issue:
2024 22
Page:
4338-4344
Research Field:
Publishing date:

Info

Title:
The value of multi-parameter magnetic resonance imaging radiomics in distinguishing high-grade gliomas from single brain metastases
Author(s):
WANG Jing1; ZONG Huiqian1; ZHANG Ya2; WEI Hongyang1; WANG Jiayi3
1.Medical Imaging Department,Second Hospital of Hebei Medical University,Hebei Shijiazhuang 050000，China;2.Medical Equipment Department,Hebei Medical University,Hebei Shijiazhuang 050000，China;3.CT Magnetic Resonance Room,the Fourth Hospital of Hebei Medical University,Hebei Shijiazhuang 050000，China.
Keywords:
glioma; metastatic tumor; radiomics; machine learning; tumor region
PACS:
R739.41
DOI:
10.3969/j.issn.1672-4992.2024.22.020
Abstract:
Objective:To distinguish high-grade gliomas from single brain metastases using multi-parameter magnetic resonance imaging (MRI) imaging.Methods:Traditional MRI sequences and apparent diffusion coefficient (ADC) images of 103 patients with high-grade glioma or single brain metastases confirmed by pathological biopsy were retrospectively collected.Volumes of interest (VOI) is manually delineated,includingthe tumor core region，the peripheral edema region and the entire tumor region.Using Pyradiomics package in Python to extract radiomics features.Then t-test and least absolute shrinkage and selection operator (LASSO) method are selected for feature screening and dimensionality reductio.Logistic regression (LR),random forest (RF),support vector machines (SVM) and K-nearest neighbors (KNN) were used to establish the model and compare the effect of distinguishing these brain tumors.Results:No significant differences were observed in terms of gender and age among patients with high-grade glioma and single brain metastasis.The highest diagnostic efficiency was obtained based on tumor core region differentiation,and the highest area under curve (AUC) was 0.924.In the multi-sequence combination model,the ALL_TCR_LR combination exhibited the highest AUC value of 0.924 on the test set,which was chosen as the optimal classifier combination.Conclusion:The multi-sequence radiomics based on the tumor core region can realize the identification of high-grade glioma and single brain metastases using LR machine learning classifier,which provides a great help for clinical decision-making and practice.

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］ BISEROVA K,JAKOVLEVS A,ULJANOVS R,et al.Cancer stem cells:Significance in origin,pathogenesis and treatment of glioblastoma［J］.Cells，2021，10(3):621.
［3］ BOIRE A,BRASTIANOS PK,GARZIA L,et al.Brain metastasis［J］.Nat Rev Cancer，2020，20(1):4-11.
［4］ 林泽,左敏静.影像组学在肺癌脑转移诊断中的研究进展［J］.现代肿瘤医学,2024,32(02):383-386. LIN Z,ZUO MJ.Research progress of imaging in the diagnosis of brain metastases in lung cancer ［J］.Modern Oncology,2024,32(02):383-386.
［5］ DU Q,LIN Y,ZHANG W,et al.Bioinformatics analysis of LMAN1 expression,clinical characteristics,and its effects on cell proliferation and invasion in glioma［J］.Brain Res,2022,1789:147952.
［6］ BANDER ED,JONES SH,PISAPIA D,et al.Tubular brain tumor biopsy improves diagnostic yield for subcortical lesions［J］.J Neurooncol,2019,141(1):121-129.
［7］ MAXIMILIEN R,AYMERIC A,MATTHIEU P,et al.Complications after frame-based stereotactic brain biopsy:a systematic review［J］.Neurosurg Rev,2020,44:301-307.
［8］ BENZAKOUN J,ROBERT C,LERGAND L,et al.Anatomical and functional MR imaging to define tumoral boundaries and characterize lesions in neuro-oncology［J］.Cancer Radiother,2020,24(5):453-462.
［9］肖建平,马玉超,王洁,等.中国肿瘤整合诊疗指南—脑转移瘤［J］.癌症,2023,42(06):304-318. XIAO JP,MA YC,WANG J,et al.Chinese guidelines for integrated diagnosis and treatment of tumor—Brain metastases ［J］.Cancer,2023,42(06):304-318.
［10］ YAN JL,LI C,BOONZAIER NR,et al.Multimodal MRI characteristics of the glioblastoma infiltration beyond contrast enhancement［J］.Ther Adv Neurol Disord,2019,12:1756286419844664.
［11］ 黄海霞,陈建,代绕,等.磁共振增强FLAIR序列在脑部转移瘤评估中的应用［J］.江苏大学学报(医学版),2023,33(06):528-533. HUANG HX,CHEN J,DAI R,et al.Application of FLAIR sequence enhanced magnetic resonance in the evaluation of brain metastases ［J］.Journal of Jiangsu University (Med Edition),2023,33(06):528-533.
［12］ AHIR BK,ENGELHARD HH,LAKKA SS.Tumor development and angiogenesis in adult brain tumor:Glioblastoma［J］.Mol Neurobiol,2020,57(5):2461-2478.
［13］ BARIS MM,CELIK AO,GEZER NS,et al.Role of mass effect,tumor volume and peritumoral edema volume in the differential diagnosis of primary brain tumor and metastasis［J］.Clin Neurol Neurosurg,2016,148:67-71.
［14］ CARAVAN I,CIORTEA CA,CONTIS A,et al.Diagnostic value of apparent diffusion coefficient in differentiating between high-grade gliomas and brain metastases［J］.Acta Radiol,2018,59(5):599-605.
［15］ 张楠,陈锋.磁共振弥散加权成像在脑转移瘤鉴别诊断中的准确率［J］.实用医技杂志,2023,30(08):560-564. ZHANG N,CHEN F.Accuracy of diffusion-weighted magnetic resonance imaging in differential diagnosis of brain metastases ［J］.Journal of Practical Medical Technology,2023,30(08):560-564.
［16］ MAYERHOEFER ME,MATERKA A,LANGS G,et al.Introduction to radiomics［J］.J Nucl Med,2020,61(4):488-495.
［17］ KOCHER M,RUGE MI,GALLDIKS N,et al.Applications of radiomics and machine learning for radiotherapy of malignant brain tumors［J］.Strahlenther Onkol,2020,196(10):856-867.
［18］ LAMBIN P,LEI GENNER R,DEIST TM,et al.Radiomics:the bridge between medical imaging and personalized medicine［J］.Nat Rev Clin Oncol,2017,14(12):749-762.
［19］ AVANZO M,WEI L,STANCANELLO J,et al.Machine and deep learning methods for radiomics［J］.Med Phys,2020,47(5):e185-e202.
［20］ BUCH K,KUNO H,QURESHI MM,et al.Quantitative variations in texture analysis features dependent on MRI scanning parameters:A phantom model［J］.J Appl Clin Med Phys,2018,19(6):253-264.
［21］ KOCAK B,YUZKAN S,MUTLU S,et al.Influence of image preprocessing on the segmentation-based reproducibility of radiomic features:in vivo experiments on discretization and resampling parameters［J］.Diagn Interv Radiol,2024,30(3):152-162.
［22］ 周琦,李娜,王娟,等.评估不同特征筛选及分类组学方法在定量识别乳腺结节超声影像特征的价值［J］.中国超声医学杂志,2023,39(10):1113-1116. ZHOU Q,LI N,WANG J,et al.To evaluate the value of different feature screening and taxonomic methods in the quantitative identification of ultrasound features of breast nodules ［J］.Chinese Journal of Ultrasound Medicine,2023,39(10):1113-1116.
［23］ CHARTRAND G,CHENG PM,VORONTSOV E,et al.Deep learning:A primer for radiologists［J］.Radiographics,2017,37(7):2113-2131.
［24］ WU J,LIANG F,WEI R,et al.A multiparametric MR-based RadioFusionOmics model with robust capabilities of differentiating glioblastoma multiforme from solitary brain metastasis［J］.Cancers (Basel),2021,13(22):5793.
［25］ PARK JE,KICKINGEREDER P,KIM HS.Radiomics and deep learning from research to clinical workflow:Neuro-oncologic imaging［J］.Korean J Radiol,2020,21(10):1126-1137.
［26］侯娟,刘文亚.肿瘤瘤周的影像组学研究进展［J］.磁共振成像,2024,15(03):230-234. HOU J,LIU WY.Advances in peritumoral imaging of tumor ［J］.Magnetic Resonance Imaging,2024,15(03):230-234.
［27］ SARKARIA JN,HH LS,PARNEY IF,et al.Is the blood-brain barrier really disrupted in all glioblastomas? A critical assessment of existing clinical data［J］.Neuro Oncol,2018,20(2):184-191.
［28］ PRIYA S,LIU Y,WARD C,et al.Machine learning based differentiation of glioblastoma from brain metastasis using MRI derived radiomics［J］.Sci Rep,2021,11(1):10478.
［29］ ABDOLMOHAMMADI J,FAEGHI F,AREFAN D,et al.The role of single voxel MR spectroscopy,T2 relaxation time and apparent diffusion coefficient in determining the cellularity of brain tumors by MATLAB software［J］.Asian Pac J Cancer Prev,2018,19:2891-2895.
［30］ LI Y,LIU Y,LIANG Y,et al.Radiomics can differentiate high-grade glioma from brain metastasis:a systematic review and meta-analysis［J］.Eur Radiol,2022,32(11):8039-8051.
［31］ DONG F,LI Q,JIIANG B,et al.Differentiation of supratentorial single brain metastasis and glioblastoma by using peri-enhancing oedema region-derived radiomic features and multiple classifiers［J］.Eur Radiol,2020,30(5):3015-3022.
［32］ ARTZI M,BRESSLER I,BEN BASHAT D.Differentiation between glioblastoma,brain metastasis and subtypes using radiomics analysis［J］.J Magn Reson Imaging,2019,50(2):519-528.
［33］ LOTAN E,JAIN R,RAZAVIAN N,et al.State of the art:Machine learning applications in glioma imaging［J］.AJR Am J Roentgenol,2019,212(1):26-37.

Memo

Memo:
河北省卫生健康委科研基金项目（编号：20230518）
Last Update: 1900-01-01