Share：
Share this content in WeChat
X
[Chinese][PDF]4905
• Clinical Article •
The value of multi-sequence MRI-based radiomics in differential diagnosis of meningioma
LU Zhongyan  ZHANG Yong  LIU Xiangchu  JIANG Yuting  JIANG Jinquan 

Cite this article as LU Z Y, ZHANG Y, LIU X C, et al. The value of multi-sequence MRI-based radiomics in differential diagnosis of meningioma[J]. Chin J Magn Reson Imaging, 2024, 15(5): 47-54. DOI:10.12015/issn.1674-8034.2024.05.009.


[Abstract] Objective To evaluate the value of multi-sequence MRI features combined with routine signs in differentiating meningioma from other other intracranial meningeal tumors.Materials and Methods Clinical and preoperative MRI data of 360 patients confirmed by pathology in two centers were retrospectively analyzed. A total of 256 patients (145 meningiomas and 111 non-meningiomas) in center 1 were randomly divided into the training group (n=179) and the test group (n=77) at a ratio of 7∶3. A total of 104 patients in Center 2 served as the external validation group (53 meningiomas and 51 non-meningiomas). The tumor growth site, growth pattern, number and other 18 general clinical data and MRI routine signs were evaluated. Univariate and multivariate binary logistic regression analysis was used to screen the indicators related to differential diagnosis. After image standardization, 3D Slicer software was used to outline region of interest (ROI) and extract features on T2WI, diffusion-weighted imaging (DWI) and enhanced T1WI images. The feature screening was performed by using the method of 5-fold cross-validation and least absolute shrinkage and selection operator (LASSO). The training group and the test group were modeled by five classifiers: logistic regression (LR), support vector machine (SVM), K-nearest neighbor (KNN), light gradient boosting machine (LightGBM) and adaptive boosting (AdaBoost). MRI conventional model, radiomics intratumoral model, radiomics peritumoral model, radiomics fusion model, and full fusion model were established, and the models with the best performance were selected for external verification. The receiver operating characteristic (ROC) curve was plotted to evaluate the differential diagnostic performance of the model. The area under the curve (AUC) of the model was compared by DeLong test. Decision curve analysis (DCA) was used to assess the clinical value of the model.Results The effectiveness of the same model constructed by different classifiers was different. The overall efficiency of the SVM models was higher, and the AUC of the radiomics intratumoral SVM model in the test group was 0.889. In addition, the AUC of all SVM models in the training group and the test group was greater than 0.900. The efficacy of the radiomics intratumoral model and the radiomics peritumoral model were similar, both of which were higher than the MRI conventional model, while the efficacy of the radiomics fusion model was higher than that of the three, but the efficacy of the full fusion model was the best, and it also performed well in the external validation group, with an AUC of 0.925 and an accuracy of 88.5%. DCA showed that this model could bring clinical net benefits to patients within a wide range of thresholds.Conclusions Multi-sequence MRI-based radiomics model can be used to distinguish meningioma from other intracranial meningeal tumors before surgery, and combined with conventional signs can improve the effectiveness of the model. Different classifiers have influence on model efficiency, SVM model has high efficiency, robustness and good generalization ability.
[Keywords] meningioma；radiomics；magnetic resonance imaging；differential diagnosis；classifier

LU Zhongyan1   ZHANG Yong1*   LIU Xiangchu2   JIANG Yuting1   JIANG Jinquan1  

1 Department of Radiology, Deyang People's Hospital, Deyang 618000, China

2 Department of Radiology, Mianzhu People's Hospital, Mianzhu 618200, China

Corresponding author: ZHANG Y, E-mail: 759740128@qq.com

Conflicts of interest   None.

Received  2023-11-13
Accepted  2024-04-15
DOI: 10.12015/issn.1674-8034.2024.05.009
Cite this article as LU Z Y, ZHANG Y, LIU X C, et al. The value of multi-sequence MRI-based radiomics in differential diagnosis of meningioma[J]. Chin J Magn Reson Imaging, 2024, 15(5): 47-54. DOI:10.12015/issn.1674-8034.2024.05.009.

[1]
UGGA L, SPADARELLA G, PINTO L, et al. Meningioma radiomics: At the nexus of imaging, pathology and biomolecular characterization[J/OL]. Cancers (Basel), 2022, 14(11): 2605 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9179263/. DOI: 10.3390/cancers14112605.
[2]
GALLDIKS N, ANGENSTEIN F, WERNER J M, et al. Use of advanced neuroimaging and artificial intelligence in meningiomas[J/OL]. Brain Pathol, 2022, 32(2): e13015 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8877736/. DOI: 10.1111/bpa.13015.
[3]
LOKEN E K, HUANG R Y. Advanced meningioma imaging[J]. Neurosurg Clin N Am, 2023, 34(3): 335-345. DOI: 10.1016/j.nec.2023.02.015.
[4]
GU H, ZHANG X, DI RUSSO P, et al. The current state of radiomics for meningiomas: promises and challenges[J/OL]. Front Oncol, 2020, 10: 567736 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7653049/. DOI: 10.3389/fonc.2020.567736.
[5]
JO S W, KIM E S, YOON D Y, et al. Changes in radiomic and radiologic features in meningiomas after radiation therapy[J/OL]. BMC Med Imaging, 2023, 23(1): 164 [2023-11-16]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10588231/. DOI: 10.1186/s12880-023-01116-0.
[6]
MUSIGMANN M, AKKURT B H, KRÄHLING H, et al. Assessing preoperative risk of STR in skull meningiomas using MR radiomics and machine learning[J/OL]. Sci Rep, 2022, 12(1): 14043 [2023-11-16]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9388514/. DOI: 10.1038/s41598-022-18458-4.
[7]
PARK C J, CHOI S H, EOM J, et al. An interpretable radiomics model to select patients for radiotherapy after surgery for WHO grade 2 meningiomas[J/OL]. Radiat Oncol, 2022, 17(1): 147 [2023-11-16]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9396861/. DOI: 10.1186/s13014-022-02090-7.
[8]
DUAN C, ZHOU X, WANG J, et al. A radiomics nomogram for predicting the meningioma grade based on enhanced T1WI images[J/OL]. Br J Radiol, 2022, 95(1137): 20220141 [2023-11-13]. https://doi.org/10.1259/bjr.20220141. DOI: 10.1259/bjr.20220141.
[9]
YANG L, XU P, ZHANG Y, et al. A deep learning radiomics model may help to improve the prediction performance of preoperative grading in meningioma[J]. Neuroradiology, 2022, 64(7): 1373-1382. DOI: 10.1007/s00234-022-02894-0.
[10]
SPECKTER H, RADULOVIC M, TRIVODALIEV K, et al. MRI radiomics in the prediction of the volumetric response in meningiomas after gamma knife radiosurgery[J]. J Neurooncol, 2022, 159(2): 281-291. DOI: 10.1007/s11060-022-04063-yMRI.
[11]
DUAN C, LI N, LI Y, et al. Prediction of progesterone receptor expression in high-grade meningioma by using radiomics based on enhanced T1WI[J/OL]. Clin Radiol, 2023, S0009-9260(23)00271-4 [2023-11-13]. https://www.clinicalradiologyonline.net/article/S0009-9260(23)00271-4/abstract. DOI: 10.1016/j.crad.2023.06.006.
[12]
LIN Y, DAI P, LIN Q, et al. A predictive nomogram for atypical meningioma based on preoperative magnetic resonance imaging and routine blood tests[J/OL]. World Neurosurg, 2022, 163: e610-e616 [2023-11-16]. https://www.sciencedirect.com/science/article/abs/pii/S1878875022004727?via%3Dihub. DOI: 10.1016/j.wneu.2022.04.034.
[13]
BRUNASSO L, FERINI G, BONOSI L, et al. A spotlight on the role of radiomics and machine-learning applications in the management of intracranial meningiomas: A new perspective in neuro-oncology: A review[J/OL]. Life (Basel), 2022, 12(4): 586 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9026541/. DOI: 10.3390/life12040586.
[14]
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.
[15]
PARK M J, KIM H S, JAHNG G H, et al. Semiquantitative assessment of intratumoral susceptibility signals using non-contrast-enhanced high-field high-resolution susceptibility-weighted imaging in patients with gliomas: comparison with MR perfusion imaging[J]. AJNR Am J Neuroradiol, 2009, 30(7): 1402-1408. DOI: 10.3174/ajnr.A1593.
[16]
MATSUSUE E, INOUE C, TABUCHI S, et al. Utility of 3T single-voxel proton MR spectroscopy for differentiating intracranial meningiomas from intracranial enhanced mass lesions[J/OL]. Acta Radiol Open, 2021, 10(4): 20584601211009472 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8215334/. DOI: 10.1177/20584601211009472.
[17]
KONG X, LUO Y, LI Y, et al. Preoperative prediction and histological stratification of intracranial solitary fibrous tumours by machine-learning models[J/OL]. Clin Radiol, 2023, 78(3): e204-e213 [2023-11-13]. https://www.clinicalradiologyonline.net/article/S0009-9260(22)00713-9/abstract. DOI: 10.1016/j.crad.2022.10.013.
[18]
EL-ABTAH M E, MURAYI R, LEE J, et al. Radiological differentiation between intracranial meningioma and solitary fibrous tumor/hemangiopericytoma: A systematic literature review[J]. World Neurosurg, 2023, 170: 68-83. DOI: 10.1016/j.wneu.2022.11.062.
[19]
FAN Y, LIU P, LI Y, et al. Non-invasive preoperative imaging differential diagnosis of intracranial hemangiopericytoma and angiomatous meningioma: A novel developed and validated multiparametric MRI-based clini-radiomic model[J/OL]. Front Oncol, 2022, 11: 792521 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8763962/. DOI: 10.3389/fonc.2021.792521.
[20]
WEI J, LI L, HAN Y, et al. Accurate preoperative distinction of intracranial hemangiopericytoma from meningioma using a multihabitat and multisequence-based radiomics diagnostic technique[J/OL]. Front Oncol, 2020, 10: 534 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7248296/. DOI: 10.3389/fonc.2020.00534.
[21]
LI X, LU Y, 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.
[22]
DONG J, YU M, MIAO Y, 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 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7725548/. DOI: 10.1155/2020/5042356.
[23]
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.
[24]
BI Y Z, BAI J, BAI P R, et al. Machine learning models based on radiomics in differentiating solitary fibrous tumor from angiomatous meningioma[J]. Chin J Magn Reson Imaging, 2023, 14(9): 50-55. DOI: 10.12015/issn.1674-8034.2023.09.009.
[25]
ZHANG Y, SHANG L, CHEN C, et al. Machine-learning classifiers in discrimination of lesions located in the anterior skull base[J/OL]. Front Oncol, 2020, 10: 752 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7270197/. DOI: 10.3389/fonc.2020.00752.
[26]
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.
[27]
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.
[28]
UNGAN G, ARÚS C, VELLIDO A, et al. A comparison of non-negative matrix underapproximation methods for the decomposition of magnetic resonance spectroscopy data from human brain tumors[J/OL]. NMR Biomed, 2023, 36(12): e5020 [2023-11-16]. https://analyticalsciencejournals.onlinelibrary.wiley.com/doi/10.1002/nbm.5020. DOI: 10.1002/nbm.5020.
[29]
CHO Y D, CHOI G H, LEE S P, et al. (1)H-MRS metabolic patterns for distinguishing between meningiomas and other brain tumors[J]. Magn Reson Imaging, 2003, 21(6): 663-672. DOI: 10.1016/s0730-725x(03)00097-3.
[30]
JASKÓLSKI D J, FORTUNIAK J, STEFAŃCZYK L, et al. Differential diagnosis of intracranial meningiomas based on magnetic resonance spectroscopy[J]. Neurol Neurochir Pol, 2013, 47(3): 247-255. DOI: 10.5114/ninp.2013.32998.
[31]
ARMASHI A R AL, ALKREKSHI A, ZUBAIDI A AL, et al. Grade Ⅲ solitary fibrous tumor/hemangiopericytoma: An enthralling intracranial tumor-A case report and literature review[J]. Radiol Case Rep, 2022, 17(10): 3792-3796. DOI: 10.1016/j.radcr.2022.07.007.
[32]
YANG X, XING Z, SHE D, et al. Grading of IDH-mutant astrocytoma using diffusion, susceptibility and perfusion-weighted imaging[J/OL]. BMC Med Imaging, 2022, 22(1): 105 [2023-11-16]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9150301/. DOI: 10.1186/s12880-022-00832-3.
[33]
ZHAO Z, NIE C, ZHAO L, et al. Multi-parametric MRI-based machine learning model for prediction of WHO grading in patients with meningiomas[J/OL]. Eur Radiol, 2023, 10.1007/s00330-023-10252-8 [2023-11-13]. https://link.springer.com/article/10.1007/s00330-023-10252-8. DOI: 10.1007/s00330-023-10252-8.
[34]
XIAO D, ZHAO Z, LIU J, et al. Diagnosis of invasive meningioma based on brain-tumor interface radiomics features on brain MR images: A multicenter study[J/OL]. Front Oncol, 2021, 11: 708040 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8422846/. DOI: 10.3389/fonc.2021.708040.
[35]
LI N, MO Y, HUANG C, et al. A clinical semantic and radiomics nomogram for predicting brain invasion in WHO Grade Ⅱ meningioma based on tumor and tumor-to-brain interface features[J/OL]. Front Oncol, 2021, 11: 752158 [2023-11-13]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8570084/. DOI: 10.3389/fonc.2021.752158.
[36]
SUN K, ZHANG J, LIU Z, et al. A deep learning radiomics analysis for identifying sinus invasion in patients with meningioma before operation using tumor and peritumoral regions[J]. Eur J Radiol, 2022, 149: 110187 [2023-11-13]. https://pubmed.ncbi.nlm.nih.gov/35183900/. DOI: 10.1016/j.ejrad.2022.110187.
[37]
JOO L, PARK J E, PARK S Y, et al. Extensive peritumoral edema and brain-to-tumor interface MRI features enable prediction of brain invasion in meningioma: development and validation[J]. Neuro Oncol, 2021, 23(2): 324-333. DOI: 10.1093/neuonc/noaa190.

PREV ADC radiomics model in predicting 1p/19q molecular features of lower-grade gliomas
NEXT Individual-based morphological brain network and its association with acute mild traumatic brain injury
  


LINK


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