Research progress of deep learning and radiomics in meningioma

Share this content in WeChat

• Review •

YANG Huimin LI Wenxin LIU Yanmei YU Wenjing WANG Qianqian JIANG Xingyue LIU Xinjiang

Cite this article as: YANG H M, LI W X, LIU Y M, et al. Research progress of deep learning and radiomics in meningioma[J]. Chin J Magn Reson Imaging, 2023, 14(6): 124-128. DOI:10.12015/issn.1674-8034.2023.06.022.

Abstract

[Abstract] Meningioma is one of the most common primary central nervous system tumours, treatment modalities vary between different grades and subtypes of meningioma, so early diagnosis, grading, and typing of meningiomas are critical to the development of a comprehensive and individualized treatment plan. Radiomics and deep learning (DL) are now popular research methods, and are well established for the classification and differential diagnosis of meningiomas. Both have the characteristics of fast and accurate, fully automated learning, non-invasive and objective, which can provide more accurate diagnosis, treatment and prognosis prediction of the disease. In this paper, we will summarise and analyse the research progress of imaging histology and DL in meningioma in terms of preoperative grading and staging, differential diagnosis, prognosis of recurrence and prediction of genetic phenotype, and summarise the achievements and limitations of existing studies as well as future improvement measures and development directions, to promote the application of imaging omics and DL in the diagnosis and treatment of meningioma.

[Keywords] meningioma；deep learning；radiomics；grading；differential diagnosis；prognostic prediction；magnetic resonance imaging

Contributor Information

YANG Huimin¹ LI Wenxin¹ LIU Yanmei¹ YU Wenjing¹ WANG Qianqian¹ JIANG Xingyue¹ LIU Xinjiang^{1,
2*}

¹ Department of Radiology, Affiliated Hospital of Binzhou Medical College, Binzhou 256603, China

² Department of Radiology, Shanghai Pudong Hospital (Pudong Hospital of Fudan University), Shanghai 201399, China

Corresponding author: Liu XJ, E-mail: lxj6513@163.com

Conflicts of interest None.

Publication Information

ACKNOWLEDGMENTS Special Project for Clinical Research in Health Industry of Shanghai Municipal Health and Health Commission (No. 202140266); Health Science and Technology Project of Pudong New Area Health Commission (No. PW2020A-35).

Received 2023-01-02

Accepted 2023-05-23

DOI: 10.12015/issn.1674-8034.2023.06.022

Text

References

[1]

OSTROM Q T, GITTLEMAN H, FULOP J, et al. CBTRUS statistical report: primary brain and central nervous system tumors diagnosed in the United States in 2008-2012[J/OL]. Neuro Oncol, 2015, 17(Suppl 4): iv1-iv62 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/26511214/. DOI: 10.1093/neuonc/nov189.

[2]

HERSCOVICI Z, RAPPAPORT Z, SULKES J, et al. Natural history of conservatively treated meningiomas[J]. Neurology, 2004, 63(6): 1133-1134. DOI: 10.1212/01.wnl.0000138569.45818.50.

[3]

GOLDBRUNNER R, STAVRINOU P, JENKINSON M D, et al. EANO guideline on the diagnosis and management of meningiomas[J]. Neuro Oncol, 2021, 23(11): 1821-1834. DOI: 10.1093/neuonc/noab150.

[4]

NEROMYLIOTIS E, KALAMATIANOS T, PASCHALIS A, et al. Machine learning in meningioma MRI: past to present. A narrative review[J]. J Magn Reson Imaging, 2022, 55(1): 48-60. DOI: 10.1002/jmri.27378.

[5]

RUDIE J D, RAUSCHECKER A M, BRYAN R N, et al. Emerging applications of artificial intelligence in neuro-oncology[J]. Radiology, 2019, 290(3): 607-618. DOI: 10.1148/radiol.2018181928.

[6]

ACS B, RANTALAINEN M, HARTMAN J. Artificial intelligence as the next step towards precision pathology[J]. J Intern Med, 2020, 288(1): 62-81. DOI: 10.1111/joim.13030.

[7]

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. DOI: 10.1016/j.ejca.2011.11.036.

[8]

LI J, LIU G Y, FAN F X, et al. Research progress of deep learning and radiomics in glioma[J]. Chin J Magn Reson Imaging, 2022, 13(4): 158-161. DOI: 10.12015/issn.1674-8034.2022.04.035

[9]

潘波敏, 叶成坤, 范光伟, 等. MRI纹理分析对术前脑膜瘤分级鉴别的临床价值[J]. 临床神经外科杂志, 2020, 17(1): 47-51. DOI: 10.3969/j.issn.1672-7770.2020.01.011.PAN B M, YE C K, FAN G W, et al. Clinical value of preoperative texture analysis in differentiation of meningioma[J]. J Clin Neurosurg, 2020, 17(1): 47-51. DOI: 10.3969/j.issn.1672-7770.2020.01.011.[ DOI: ]

[10]

YU X Y, GENG C J, FENG Y B, et al. Clinical value of MRI texture analysis for preoperative grading of meningiomas based on conventional MRI images[J]. Chin J Radiol, 2018, 52(5): 356-362. DOI: 10.3760/cma.j.issn.1005-1201.2018.05.007.

[11]

NG F, GANESHAN B, KOZARSKI R, et al. Assessment of primary colorectal cancer heterogeneity by using whole-tumor texture analysis: contrast-enhanced CT texture as a biomarker of 5-year survival[J]. Radiology, 2013, 266(1): 177-184. DOI: 10.1148/radiol.12120254.

[12]

GANESHAN B, MILES K A, YOUNG R C, et al. Hepatic entropy and uniformity: additional parameters that can potentially increase the effectiveness of contrast enhancement during abdominal CT[J]. Clin Radiol, 2007, 62(8): 761-768. DOI: 10.1016/j.crad.2007.03.004.

[13]

ZHENG Q, LU Y, SUN X J, et al. The value of conventional MRI texture analysis in differential diagnosis of benign and malignant meningiomas[J]. J Pract Radiol, 2020, 36(8): 1192-1195. DOI: 10.3969/j.issn.1002-1671.2020.08.004

[14]

LI X X, MIAO Y W, GUO Y, et al. Grading diagnosis of meningiomas with histogram analysis of MRI based on whole tumor volume measurement[J]. Chin J Med Imaging Techno, 2018, 34(8): 1143-1147. DOI: 10.13929/j.1003-3289.201712114.

[15]

YANG C X, YUAN M, ZHANG J L, et al. Preoperatively predict pathological grading of meningiomas using radiomics model based on transverse and sagittal enhanced T1WI images: a preliminary study[J]. Chin J Magn Reson Imaging, 2022, 13(2): 6-9. DOI: 10.12015/issn.1674-8034.2022.02.002

[16]

CHEN H L, LI S Q, ZHANG Y M, et al. Deep learning-based automatic segmentation of meningioma from multiparametric MRI for preoperative meningioma differentiation using radiomic features: a multicentre study[J]. Eur Radiol, 2022, 32(10): 7248-7259. DOI: 10.1007/s00330-022-08749-9.

[17]

CHU H R, LIN X Q, HE J, et al. Value of MRI radiomics based on enhanced T1WI images in prediction of meningiomas grade[J]. Acad Radiol, 2021, 28(5): 687-693. DOI: 10.1016/j.acra.2020.03.034.

[18]

HU J P, ZHAO Y J, LI M C, et al. Machine learning-based radiomics analysis in predicting the meningioma grade using multiparametric MRI[J/OL]. Eur J Radiol, 2020, 131: 109251 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/32916409/. DOI: 10.1016/j.ejrad.2020.109251.

[19]

KE C, CHEN H L, LV X F, et al. Differentiation between benign and nonbenign meningiomas by using texture analysis from multiparametric MRI[J]. J Magn Reson Imaging, 2020, 51(6): 1810-1820. DOI: 10.1002/jmri.26976.

[20]

HAN Y X, WANG T Z, WU P, et al. Meningiomas: Preoperative predictive histopathological grading based on radiomics of MRI[J/OL]. Magn Reson Imaging, 2021, 77: 36-43 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/33220449/. DOI: 10.1016/j.mri.2020.11.009.

[21]

DUAN C F, LI N, LI Y, et al. Comparison of different radiomic models based on enhanced T1-weighted images to predict the meningioma grade[J/OL]. Clin Radiol, 2022, 77(4): e302-e307 [2023-01-01]. https://www.clinicalradiologyonline.net/article/S0009-9260(22)00047-2/fulltext. DOI: 10.1016/j.crad.2022.01.039.

[22]

BANZATO T, CAUSIN F, DELLA PUPPA A, et al. Accuracy of deep learning to differentiate the histopathological grading of meningiomas on MR images: a preliminary study[J]. J Magn Reson Imaging, 2019, 50(4): 1152-1159. DOI: 10.1002/jmri.26723.

[23]

ZHU Y B, MAN C T, GONG L X, et al. A deep learning radiomics model for preoperative grading in meningioma[J/OL]. Eur J Radiol, 2019, 116: 128-134 [2023-01-01]. https://www.ejradiology.com/article/S0720-048X(19)30156-1/fulltext. DOI: 10.1016/j.ejrad.2019.04.022.

[24]

WINTER F, FURTNER J, PLEYEL A, et al. How to predict the consistency and vascularity of meningiomas by MRI: an institutional experience[J]. Neurol Res, 2021, 43(8): 693-699. DOI: 10.1080/01616412.2021.1922171.

[25]

PARK Y W, OH J, YOU S C, et al. Radiomics and machine learning may accurately predict the grade and histological subtype in meningiomas using conventional and diffusion tensor imaging[J]. Eur Radiol, 2019, 29(8): 4068-4076. DOI: 10.1007/s00330-018-5830-3.

[26]

HAN T, LIU X W, XU Z D, et al. T2WI and contrast enhanced T1WI radiomics models for distinguishing fibroblastic and non-fibroblastic meningioma[J]. Chin J Med Imaging Technol, 2022, 38(12): 1791-1796. DOI: 10.13929/j.issn.1003-3289.2022.12.007

[27]

NIU L, ZHOU X M, DUAN C F, et al. Differentiation researches on the meningioma subtypes by radiomics from contrast-enhanced magnetic resonance imaging: a preliminary study[J/OL]. World Neurosurg, 2019, 126: e646-e652 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/30831287/. DOI: 10.1016/j.wneu.2019.02.109.

[28]

BODALAL Z, TREBESCHI S, NGUYEN-KIM T D L, et al. Radiogenomics: bridging imaging and genomics[J]. Abdom Radiol (NY), 2019, 44(6): 1960-1984. DOI: 10.1007/s00261-019-02028-w.

[29]

LI X X, LU Y P, XIONG J, et al. Presurgical differentiation between malignant haemangiopericytoma and angiomatous meningioma by a radiomics approach based on texture analysis[J]. J Neuroradiol, 2019, 46(5): 281-287. DOI: 10.1016/j.neurad.2019.05.013.

[30]

FU S L, REN Y D, LI X R, et al. The value of magnetic resonance imaging in differentiating grade Ⅱ solitary fibrous tumor/hemangiopericytoma from angiomatous meningioma[J]. Chin J Magn Reson Imaging, 2022, 13(1): 15-20. DOI: 10.12015/issn.1674-8034.2022.01.004

[31]

DONG J Y, YU M M, MIAO Y W, et al. Differential diagnosis of solitary fibrous tumor/hemangiopericytoma and angiomatous meningioma using three-dimensional magnetic resonance imaging texture feature model[J/OL]. Biomed Res Int, 2020, 2020: 5042356 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/33344637/. DOI: 10.1155/2020/5042356.

[32]

WANG B L, ZHAO W, DING S, et al. Study on the value of MRI texture analysis in the differential diagnosis of solitary fibroma (SFT) and hemangiomatous meningioma (AM)[J]. Chin J CT MRI, 2022, 20(3): 14-17, 20. DOI: 10.3969/j.issn.1672-5131.2022.03.005.

[33]

CHEN Z Y, YE N R, JIANG N, et al. Deep learning model for intracranial hemangiopericytoma and meningioma classification[J/OL]. Front Oncol, 2022, 12: 839567 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/35311127/. DOI: 10.3389/fonc.2022.839567.

[34]

SAIGAL G, PISANI L, ALLAKHVERDIEVA E, et al. Utility of microhemorrhage as a diagnostic tool in distinguishing vestibular schwannomas from other cerebellopontine angle (CPA) tumors[J]. Indian J Otolaryngol Head Neck Surg, 2021, 73(3): 321-326. DOI: 10.1007/s12070-021-02372-8.

[35]

JEONG H, LEE D H, SHIN J E, et al. Direction-changing spontaneous nystagmus in cerebellopontine angle tumour[J/OL]. J Clin Neurosci, 2022, 95: 118-122 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/34929634/. DOI: 10.1016/j.jocn.2021.12.002.

[36]

MOHAMAD J, SIMGEN A. Akustikusneurinome[J]. Der Radiol, 2020, 60(11): 1018-1025. DOI: 10.1007/s00117-020-00751-w.

[37]

ZHENG Y X, XU Y, FAN G W, et al. Differential diagnosis of texture analysis in vestibular schwannoma and cerebellopontine angle meningioma[J]. J Reg Anat Oper Surg, 2019, 28(5): 379-382. DOI: 10.11659/jjssx.12E018115

[38]

JU W P, LIANG J, WANG X L, et al. Application value of gray level co-occurrence matrix in differentiating vestibular schwannoma from cerebellopontine angle meningioma[J]. Chin J Magn Reson Imaging, 2022, 13(4): 103-106. DOI: 10.12015/issn.1674-8034.2022.04.019.

[39]

MAKI S, FURUYA T, HORIKOSHI T, et al. A deep convolutional neural network with performance comparable to radiologists for differentiating between spinal schwannoma and meningioma[J]. Spine, 2019, 45(10): 694-700. DOI: 10.1097/brs.0000000000003353.

[40]

ABUDUREXITI M W L J, YIZIM P R H Y J, ABDUJILIL A B D K Y M, et al. Clinical features of atypical meningiomas and research progress for risk factors of postoperative recurrence[J]. J Clin Neurosurg, 2022, 19(3)356-360. DOI: 10.3969/j.issn.1672-7770.2022.03.024

[41]

ZHANG Y, CHEN J H, CHEN T Y, et al. Radiomics approach for prediction of recurrence in skull base meningiomas[J]. Neuroradiology, 2019, 61(12): 1355-1364. DOI: 10.1007/s00234-019-02259-0.

[42]

MORIN O, CHEN W C, NASSIRI F, et al. Integrated models incorporating radiologic and radiomic features predict meningioma grade, local failure, and overall survival[J/OL]. Neurooncol Adv, 2019, 1(1): vdz011 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/31608329/. DOI: 10.1093/noajnl/vdz011.

[43]

HSIEH H P, WU D Y, HUNG K C, et al. Machine learning for prediction of recurrence in parasagittal and parafalcine meningiomas: combined clinical and MRI texture features[J/OL]. J Pers Med, 2022, 12(4): 522 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/35455638/. DOI: 10.3390/jpm12040522.

[44]

ZHANG J, YAO K, LIU P P, et al. A radiomics model for preoperative prediction of brain invasion in meningioma non-invasively based on MRI: a multicentre study[J/OL]. EBioMedicine, 2020, 58: 102933 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/32739863/. DOI: 10.1016/j.ebiom.2020.102933.

[45]

SUN K, ZHANG J, LIU Z Y, et al. A deep learning radiomics analysis for identifying sinus invasion in patients with meningioma before operation using tumor and peritumoral regions[J/OL]. Eur J Radiol, 2022, 149: 110187 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/35183900/. DOI: 10.1016/j.ejrad.2022.110187.

[46]

WANG W J, TU Y, WANG S S, et al. Role of HER-2 activity in the regulation of malignant meningioma cell proliferation and motility[J]. Mol Med Rep, 2015, 12(3): 3575-3582. DOI: 10.3892/mmr.2015.3805.

[47]

KAYASELÇUK F, ZORLUDEMIR S, BAL N, et al. The expression of survivin and Ki-67 in meningiomas: correlation with grade and clinical outcome[J]. J Neurooncol, 2004, 67(1/2): 209-214. DOI: 10.1023/b:neon.0000021823.05163.2c.

[48]

JIAO J T, HUANG J, CHENG C, et al. Expression characteristic and prognostic value of survivin in meningioma[J]. J Clin Neurosurg, 2018, 15(4): 241-245. DOI: 10.3969/j.issn.1672-7770.2018.04.001

[49]

ZHAO Y J, XU J F, CHEN B R, et al. Efficient prediction of ki-67 proliferation index in meningiomas on MRI: from traditional radiological findings to a machine learning approach[J/OL]. Cancers (Basel), 2022, 14(15): 3637 [2023-01-01]. https://pubmed.ncbi.nlm.nih.gov/35892896/. DOI: 10.3390/cancers14153637.

[50]

KHANNA O, FATHI KAZEROONI A, FARRELL C J, et al. Machine learning using multiparametric magnetic resonance imaging radiomic feature analysis to predict ki-67 in World Health Organization grade I meningiomas[J]. Neurosurgery, 2021, 89(5): 928-936. DOI: 10.1093/neuros/nyab307.

[51]

PAVELIN S, BECIC K, FOREMPOHER G, et al. Expression of ki-67 and p53 in meningiomas[J]. Neoplasma, 2013, 60(5): 480-485. DOI: 10.4149/neo_2013_062.

[52]

PEĆINA-ŠLAUS N, KAFKA A, VLADUŠIĆ T, et al. Loss of p53 expression is accompanied by upregulation of beta-catenin in meningiomas: a concomitant reciprocal expression[J]. Int J Exp Pathol, 2016, 97(2): 159-169. DOI: 10.1111/iep.12186.

[53]

OUYANG Z Q, LI Q, SUN X J, et al. Predicting p53 gene phenotype in meningioma based on radiomics analysis of enhanced MRI T1-weighted imaging[J]. Radiol Pract, 2021, 36(6): 693-699. DOI: 10.13609/j.cnki.1000-0313.2021.06.001.

[54]

OUYANG Z Q, LU Y, WEN L, et al. Contrast enhanced T1WI-based radiomics for preoperatively predicting expression status of ki-67 proliferation index in meningioma[J]. Chin J Med Imaging, 2021, 29(10): 980-986, 988. DOI: 10.3969/j.issn.1005-5185.2021.10.005.

PREV Advances in imaging research of vertebral artery hypoplasia and its relationship with posterior circulation ischemic stroke

NEXT Research progress of MRI radiomics in lung cancer

LINK

Tel & Fax: +8610-67113815 E-mail: editor@cjmri.cn