MRI影像组学在胶质瘤术前分级预测中的研究进展

doi:10.3969/j.issn.1000-8535.2024.03.002

摘要/Abstract

摘要： 胶质瘤是颅内最常见的原发性恶性肿瘤,其分级对患者治疗方式的选择和预后至关重要。尽管目前组织病理学仍是其最为可靠的分级手段,但需通过有创性手术以获取组织样本,存在一定的风险。相较之下,磁共振成像（MRI）作为一种非侵入性影像诊断工具,在胶质瘤分级中发挥着不可或缺的作用。然而,传统MRI评估受限于医师个体主观性强和可重复性差的问题,一定程度上影响了准确的分级结果。近年来,影像组学技术的崭露头角为解决上述难题开辟了新视角,通过高通量提取影像数据特征捕捉并量化肿瘤的影像学表现,避免因主观因素而导致的不确定性,协助医师更准确地评估肿瘤的恶性程度。本文对近五年来MRI影像组学在胶质瘤术前分级预测方面的相关研究进行了简要综述,旨在为相关领域研究者提供有益的参考和借鉴,以推动MRI影像组学在临床实践中的应用。

关键词: 胶质瘤, 术前分级, 磁共振成像, 影像组学

Abstract: Glioma is the most common primary malignant brain tumor,and its grading is crucial for treatment decisions and prognosis．Currently,histopathology remains the gold standard for grading,but it requires invasive procedures and carries inherent risks．In contrast,magnetic resonance imaging（MRI）,a non-invasive diagnostic tool,plays an indispensable role in glioma grading．However,traditional MRI assessment is hampered by interobserver subjectivity and limited repeatability,which compromise grading accuracy．In recent years,radiomics,a burgeoning field,has offered a promising solution to address these challenges．By extracting high-dimensional imaging data features,radiomics enables the quantification of tumor radiological characteristics and elimination of subjectivity-related discrepancies．This technology assists clinicians in more precisely assessing the malignancy of gliomas．This article summarizes relevant studies in the past five years on the application of MRI radiomics in preoperative glioma grading,aiming to provide valuable insights and guidance to researchers in the field and promote the clinician implementation of MRI radiomics．

Key words: glioma, preoperative grading, magnetic resonance imaging, radiomics

梁芳蓉, 杨蕊梦. MRI影像组学在胶质瘤术前分级预测中的研究进展[J]. 广州医药, 2024, 55(3): 221-230.

LIANG Fangrong, YANG Ruimeng. Advancement in MRI radiomics for preoperative glioma grading prediction[J]. Guangzhou Medical Journal, 2024, 55(3): 221-230.

参考文献

[1] LOUIS D N,PERRY A,WESSELING P,et al.The 2021 WHO classification of tumors of the central nervous system:A summary[J].Neuro-oncology,2021,23(8):1231-1251.
[2] A GHOTME K,E BARRETO G,ECHEVERRIA V,et al.Gliomas:New perspectives in diagnosis,treatment and prognosis[J].Curr Top Med Chem,2017,17(12):1438-1447.
[3] HAJ-HOSSEINI N,RICHTER J C,MILOS P,et al.5-ALA fluorescence and laser Doppler flowmetry for guidance in a stereotactic brain tumor biopsy[J].Biomed Opt Express,2018,9(5):2284-2296.
[4] ANEJA S,CHANG E,OMURO A.Applications of artificial intelligence in neuro-oncology[J].Curr Opin Neurol,2019,32(6):850-856.
[5] LOHMANN P,GALLDIKS N,KOCHER M,et al.Radiomics in neuro-oncology:basics,workflow,and applications[J].Methods,2021(188):112-121.
[6] JACKSON R J,FULLER G N,ABI-SAID D,et al.Limitations of stereotactic biopsy in the initial management of gliomas[J].Neuro-oncology,2001,3(3):193-200.
[7] VLAARDINGERBROEK M T,den BOER J A.Magnetic resonance imaging:Theory and practice[M].Berlin,Heidelberg:Springer Berlin Heidelberg,1996.
[8] 钱春红,沈海林,房志伟,等.不同病理级别脑胶质瘤的MRI表现[J].现代医用影像学,2019,28(8):1728-1730.
[9] AERTS H J,VELAZQUEZ E R,LEIJENAAR R T,et al.Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach[J].Nat Commun,2014(5):4006.
[10] WU J,THA K K,XING L,et al.Radiomics and radiogenomics for precision radiotherapy[J].Journal of radiation research,2018,59(suppl_1):i25-i31.
[11] GILLIES R J,KINAHAN P E,HRICAK H.Radiomics:Images are more than pictures,they are data[J].J Radiat Res,2016,278(2):563-577.
[12] LAMBIN P,LEIJENAAR R T,DEIST T M,et al.Radiomics:The bridge between medical imaging and personalized medicine[J].Nat Rev Clin Oncol,2017,14(12):749-762.
[13] LAMBIN P,RIOS-VELAZQUEZ E,LEIJENAAR R,et al.Radiomics:Extracting more information from medical images using advanced feature analysis[J].Eur J Cancer,2012,48(4):441-446.
[14] KUMAR V,GU Y,BASU S,et al.Radiomics:The process and the challenges[J].Magn Reson Imag,2012,30(9):1234-1248.
[15] 于永成,姜雨萌,方玲玲.基于胶质瘤图像的原始数据集构建及应用[J].计算机系统应用,2023,32(1):368-375.
[16] JIANG Y,CHEN C,XIE J,et al.Radiomics signature of computed tomography imaging for prediction of survival and chemotherapeutic benefits in gastric cancer[J].EBioMedicine,2018(36):171-182.
[17] LIU Z,MENG X,ZHANG H,et al.Predicting distant metastasis and chemotherapy benefit in locally advanced rectal cancer[J].Nat Commun,2020,11(1):4308.
[18] PARMAR C,GROSSMANN P,RIETVELD D,et al.Radiomic machine-learning classifiers for prognostic biomarkers of head and neck cancer[J].Front Oncol,2015(5):272.
[19] MAYERHOEFER M E,MATERKA A,LANGS G,et al.Introduction to radiomics[J]. J Nucl Med,2020,61(4):488-495.
[20] WEN P Y,KESARI S.Malignant gliomas in adults[J].N Engl J Med,2008,359(5):492-507.
[21] CHA S.Neuroimaging in neuro-oncology[J].Neurotherapeutics,2009,6(3):465-477.
[22] KICKINGEREDER P,BURTH S,WICK A,et al.Radiomic profiling of glioblastoma:Identifying an imaging predictor of patient survival with improved performance over established clinical and radiologic risk models[J].Radiology,2016,280(3):880-889.
[23] ZHOU H,VALLIÈRES M,BAI H X,et al.MRI features predict survival and molecular markers in diffuse lower-grade gliomas[J].Neuro-oncology,2017,19(6):862-870.
[24] GAO M,HUANG S,PAN X,et al.Machine learning-based radiomics predicting tumor grades and expression of multiple pathologic biomarkers in gliomas[J].Front Oncol,2020(10):1676.
[25] ZHOU H,XU R,MEI H,et al.Application of enhanced T1WI of MRI radiomics in glioma grading[J].Int J Clin Pract,2022(2022):3252574.
[26] ZHANG H,ZHANG B,PAN W,et al.Preoperative contrast-enhanced MRI in differentiating glioblastoma from low-grade gliomas in the cancer imaging archive database:A proof-of-concept study[J].Front Oncol,2022(11):761359.
[27] DITMER A,ZHANG B,SHUJAAT T,et al.Diagnostic accuracy of MRI texture analysis for grading gliomas[J].J Neurooncol,2018,140(3):583-589.
[28] 赵博涵,王训恒,厉力华.基于T1加权磁共振影像组学的脑胶质瘤分级[J].杭州电子科技大学学报(自然科学版),2023,43(2):61-66.
[29] TOVI M.MR imaging in cerebral gliomas analysis of tumour tissue components[J].Acta Radiol Suppl,1993(384):1-24.
[30] AL-ZURFI A N,MEZIANE F,ASPIN R.A computer-aided diagnosis system for glioma grading using three dimensional texture analysis and machine learning in MRI brain tumour[C]//2019 3rd International Conference on Bio-engineering for Smart Technologies(BioSMART).Paris,France.IEEE,2019:1-5.
[31] TRIPATHI P C,BAG S.A computer-aided grading of glioma tumor using deep residual networks fusion[J].Comput Meth Programs Biomed,2022(215):106597.
[32] XU J,LAI M,LI S,et al.Noninvasive prediction of histological grading in pediatric low-grade gliomas using preoperative T2-FLAIR radiomics features[J].World Neurosurg,2023(177):e34-e43.
[33] SU C,CHEN X,LIU C,et al.T2-FLAIR,DWI and DKI radiomics satisfactorily predicts histological grade and Ki-67 proliferation index in gliomas[J].Am J Transl Res,2021,13(8):9182-9194.
[34] 张微,牛蕾,马敏阁,等.DCE-MRI在高、低级别脑胶质瘤及脑膜瘤中的鉴别诊断[J].磁共振成像,2015,6(8):566-570.
[35] MANNELLI L,NOUGARET S,VARGAS H A,et al.Advances in diffusion-weighted imaging[J].Radiol Clin North Am,2015,53(3):569-581.
[36] KUSUNOKI M,KIKUCHI K,TOGAO O,et al.Differentiation of high-grade from low-grade diffuse gliomas using diffusion-weighted imaging:A comparative study of mono-,Bi-,and stretched-exponential diffusion models[J].Neuroradiology,2020,62(7):815-823.
[37] ZHANG L,MIN Z,TANG M,et al.The utility of diffusion MRI with quantitative ADC measurements for differentiating high-grade from low-grade cerebral gliomas:Evidence from a meta-analysis[J].J Neurol Sci,2017(373):9-15.
[38] GIHR G A,HORVATH-RIZEA D,HEKELER E,et al.Histogram analysis of diffusion weighted imaging in low-grade gliomas:In vivo characterization of tumor architecture and corresponding neuropathology[J].Front Oncol,2020(10):206.
[39] SOLIMAN R K,ESSA A A,ELHAKEEM A A,et al.Texture analysis of apparent diffusion coefficient(ADC)map for glioma grading:Analysis of whole tumoral and peri-tumoral tissue[J].Diagn Interv Imag,2021,102(5):287-295.
[40] WANG S,MENG M,ZHANG X,et al.Texture analysis of diffusion weighted imaging for the evaluation of glioma heterogeneity based on different regions of interest[J].Oncol Lett,2018,15(5):7297-7304.
[41] 孙功能,朱虎,邱伟,等.磁共振弥散张量成像定量参数在胶质瘤分级诊断中的应用研究[J].医学影像学杂志,2019,29(4):528-531.
[42] 潘虹,陈燕萍,易云平.DTI在颅脑胶质瘤术前分级中的应用[J].中国中西医结合影像学杂志,2020,18(1):26-29.
[43] NUCCI C,GARACI F,ALTOBELLI S,et al.Diffusional kurtosis imaging of white matter degeneration in glaucoma[J].J Clin Med,2020,9(10):3122.
[44] 韩彤,郭军,刘力,等.动态对比增强磁共振灌注成像在脑肿瘤诊断中的应用价值[J].中国现代神经疾病杂志,2006,6(3):211-219.
[45] HYLTON N.Dynamic contrast-enhanced magnetic resonance imaging as an imaging biomarker[J].J Clin Oncol,2006,24(20):3293-3298.
[46] XIE T,CHEN X,FANG J,et al.Textural features of dynamic contrast‐enhanced MRI derived model‐free and model‐based parameter maps in glioma grading[J].J Magn Reson Imag,2018,47(4):1099-1111.
[47] ZHAO P F,XIE S H,QIAO P F,et al.Role of texture analysis and dynamic contrast-enhanced magnetic resonance imaging quantitative parameters based on different regions of interest in glioma grading[J].Asian J Surg,2021,44(8):1089-1090.
[48] ANZALONE N,CASTELLANO A,CADIOLI M,et al.Brain gliomas:Multicenter standardized assessment of dynamic contrast-enhanced and dynamic susceptibility contrast MR images[J].Radiology,2018,287(3):933-943.
[49] JEONG J,WANG L,JI B,et al.Machine-learning based classification of glioblastoma using delta-radiomic features derived from dynamic susceptibility contrast enhanced magnetic resonance images:Introduction[J].Quant Imaging Med Surg,2019,9(7):1201-1213.
[50] SAKATA A,OKADA T,YAMAMOTO A,et al.Grading glial tumors with amide proton transfer MR imaging:Different analytical approaches[J].J Neurooncol,2015,122(2):339-348.
[51] 秦倩,高翾,张岚,等.基于3D APTw 影像组学模型预测脑胶质瘤 IDH 突变状态及 WHO 分级的研究[J].中国临床新医学,2023,16(4):336-341.
[52] BRYNOLFSSON P,NILSSON D,HENRIKSSON R,et al.ADC texture:An imaging biomarker for high‐grade glioma?[J].Med Phys,2014,41(10):101903.
[53] NAKAMOTO T,TAKAHASHI W,HAGA A,et al.Prediction of malignant glioma grades using contrast-enhanced T1-weighted and T2-weighted magnetic resonance images based on a radiomic analysis[J].Sci Rep,2019,9(1):19411.
[54] ZHAO S S,FENG X L,HU Y C,et al.Better efficacy in differentiating WHO grade II from III oligodendrogliomas with machine-learning than radiologist’s reading from conventional T1 contrast-enhanced and fluid attenuated inversion recovery images[J].BMC Neurol,2020,20(1):48.
[55] CHO H H,LEE S H,KIM J,et al.Classification of the glioma grading using radiomics analysis[J].PeerJ,2018(6):e5982.
[56] CHENG J,LIU J,YUE H,et al.Prediction of glioma grade using intratumoral and peritumoral radiomic features from multiparametric MRI images[J].IEEE/ACM Trans Comput Biol Bioinform,2022,19(2):1084-1095.
[57] SU C,JIANG J,ZHANG S,et al.Radiomics based on multicontrast MRI can precisely differentiate among glioma subtypes and predict tumour-proliferative behaviour[J].Eur Radiol,2019,29(4):1986-1996.
[58] WANG Q,LI Q,MI R,et al.Radiomics nomogram building from multiparametric MRI to predict grade in patients with glioma:A cohort study[J].J Magn Reson Imaging,2019,49(3):825-833.
[59] TAKAHASHI S,TAKAHASHI W,TANAKA S,et al.Radiomics analysis for glioma malignancy evaluation using diffusion kurtosis and tensor imaging[J].Int J Radiat Oncol Biol Phys,2019,105(4):784-791.
[60] LIU J,LI C,CHEN Y,et al.Diagnostic performance of multiparametric MRI in the evaluation of treatment response in glioma patients at 3T[J].J Magn Reson Imaging,2020,51(4):1154-1161.
[61] VAMVAKAS A,WILLIAMS S C,THEODOROU K,et al.Imaging biomarker analysis of advanced multiparametric MRI for glioma grading[J].Phys Med,2019(60):188-198.
[62] LIN K,CIDAN W,QI Y,et al.Glioma grading prediction using multiparametric magnetic resonance imaging‐based radiomics combined with proton magnetic resonance spectroscopy and diffusion tensor imaging[J].Med Phys,2022,49(7):4419-4429.
[63] AHAMMED MUNEER K V,RAJENDRAN VR,PAUL JOSEPH K.Glioma tumor grade identification using artificial intelligent techniques[J].J Med Syst,2019,43(5):113.
[64] JIANG L,ZHOU L,AI Z,et al.Machine learning based on diffusion kurtosis imaging histogram parameters for glioma grading[J].J Clin Med,2022,11(9):2310.
[65] COMELLI A,BIGNARDI S,STEFANO A,et al.Development of a new fully three-dimensional methodology for tumours delineation in functional images[J].Comput Biol Med,2020(120):103701.
[66] ZHUGE Y,NING H,MATHEN P,et al.Automated glioma grading on conventional MRI images using deep convolutional neural networks[J].Med Phys,2020,47(7):3044-3053.
[67] GUTTA S,ACHARYA J,SHIROISHI M S,et al.Improved glioma grading using deep convolutional neural networks[J].AJNR Am J Neuroradiol,2021,42(2):233-239.
[68] PENG J,WANG Y.Medical image segmentation with limited supervision:A review of deep network models[J].IEEE Access,2021(9):36827-36851.
[69] SIDDIQUE N,PAHEDING S,ELKIN C P,et al.U-net and its variants for medical image segmentation:a review of theory and applications[J].IEEE Access,2021(9):82031-82057.
[70] CHAMBERS J M,HASTIE T J.Statistical models[M]//Chambers J M,Hastie T J,Eds.Statistical Models in S:Routledge,2017:13-44.
[71] GUO J,REN J,SHEN J,et al.Do the combination of multiparametric MRI-based radiomics and selected blood inflammatory markers predict the grade and proliferation in glioma patients?[J].Diagn Interv Radiol,2021,27(3):440-449.
[72] BREIMAN L.Random forests[J].Mach Learn,2001(45):5-32.
[73] ZHOU Z H.Machine Learning[M].Singapore:Springer Singapore,2021.
[74] ALPAYDIN E.Introduction to machine learning[M].Massachusetts:The MIT Press,2020.
[75] SENGUPTA A,RAMANIHARAN A K,GUPTA R K,et al.Glioma grading using a machine‐learning framework based on optimized features obtained from T1 perfusion MRI and volumes of tumor components[J].J Magn Reson Imaging,2019,50(4):1295-1306.
[76] ZHANG Z,XIAO J,WU S,et al.Deep convolutional radiomic features on diffusion tensor images for classification of glioma grades[J].J Digit Imaging,2020,33(4):826-837.
[77] SUDRE C H,PANOVSKA-GRIFFITHS J,SANVERDI E,et al.Machine learning assisted DSC-MRI radiomics as a tool for glioma classification by grade and mutation status[J]. BMC Med Inform Decis Mak,2020,20(1):149.
[78] UBALDI L,SAPONARO S,GIULIANO A,et al.Deriving quantitative information from multiparametric MRI via Radiomics:evaluation of the robustness and predictive value of radiomic features in the discrimination of low-grade versus high-grade gliomas with machine learning[J].Phys Med,2023(107):102538.
[79] HOSMER DW JR,LEMESHOW S,STURDIVANT RX.Applied Logistic Regression[M].New Jersey:Wiley,2013.
[80] CORTES C,VAPNIK V.Support-vector networks[J].Mach Learn,1995,20(3):273-297.
[81] CHEN Q,WANG L,WANG L,et al.Glioma grade prediction using wavelet scattering-based radiomics[J].IEEE Access,2020(8):106564-106575.
[82] YU X,WU Y,BAI Y,et al.A lightweight 3D UNet model for glioma grading[J].Phys Med Biol,2022,67(15).
[83] NING Z,LUO J,XIAO Q,et al.Multi-modal magnetic resonance imaging-based grading analysis for gliomas by integrating radiomics and deep features[J].Ann Transl Med,2021,9(4):298.
[84] XIAO T,HUA W,LI C,et al.Glioma grading prediction by exploring radiomics and deep learning features[C]//Proceedings of the Third International Symposium on Image Computing and Digital Medicine.August 24 - 26,2019,Xi’an,China.ACM,2019:208-213.
[85] YANG Y,YAN L F,ZHANG X,et al.Glioma grading on conventional MR images:A deep learning study with transfer learning[J].Front Neurosci,2018(12):804.
[86] ALI MB,GU IYH,JAKOLA AS.Multi-stream convolutional autoencoder and 2D generative adversarial network for glioma classification[C]//Computer Analysis of Images and Patterns:18th International Conference,CAIP 2019,Salerno,Italy,September 3-5,2019,Proceedings,Part I.ACM,2019:234-245.
[87] LI X,XIONG H,LI X,et al.Interpretable deep learning:interpretation,interpretability,trustworthiness,and beyond[J].Knowl Inf Syst,2022,64(12):3197-3234.