Share：
Share this content in WeChat
X
[Chinese][PDF]3656
• Clinical Article •
The value of multi-parametric MRI-based radiomics models in distinguishing primary central nervous system lymphoma from high-grade glioma
ZHANG Shaoru  ZHOU Yunshu  ZHANG Ruodi  LIU Shili  CHEN Xiaohua  WANG Zhuo  CHEN Zhiqiang 

Cite this article as: ZHANG S R, ZHOU Y S, ZHANG R D, et al. The value of multi-parametric MRI-based radiomics models in distinguishing primary central nervous system lymphoma from high-grade glioma[J]. Chin J Magn Reson Imaging, 2023, 14(10): 53-57, 64. DOI:10.12015/issn.1674-8034.2023.10.010.


[Abstract] Objective To explore the value of multi-parametric MRI-based radiomics models in differentiating primary central nervous system lymphoma (PCNSL) from high-grade glioma.Materials and Methods All preoperative routine MRI images of 99 patients with high-grade gliomas and primary PCNSLs who confirmed by pathology were collected, and all patients were randomly divided into training (n=69) and testing (n=30) sets at 7:3 ratios. ROI1 included the of core the tumor, ROI2 included the core of tumor and peritumoral edema. Delineated the ROI on the axial contrast enhancement (CE)-T1WI and T2 fluid-attenuated inversion-recovery (FLAIR) images. The independent sample t-test or the Mann-Whitney U test, the Pearson correlation analysis and the least absolute shrinkage and selection operator (LASSO) were used to screen out the features, the radiomics score of each patients were also calculated. We used the logistic regression (LR) algorithm to construct models for CE-T1WI, T2 FLAIR and a combined model as well. The receiver operating characteristic (ROC) was used to evaluate classifier performance, calculating the area under curve (AUC), accuracy, sensitivity, specificity to the corresponding radiomics model.Results Among single-sequence radiomics models, the CE-T1WI model had the best prediction performance, its AUC values in the training and testing groups were 0.952 and 0.949, respectively. The T2 FLAIR model established by the core features of the tumor is superior to the model based on the whole tumor, its AUC values in the training and testing groups were 0.915 and 0.898, respectively. The AUC values of the combined model in the training and the testing groups were 0.978 and 0.983, respectively.Conclusions Multi-parametric MRI-based radiomics models had good diagnostic performance in differentiating PCNSL from high-grade glioma, among single-sequence radiomics models, the CE-T1WI model had the best prediction performance, the combined model increased the accuracy of the model, the features of tumor core area are more related to tumor classification.
[Keywords] primary central nervous system lymphoma；high-grade glioma；magnetic resonance imaging；radiomics；antidiastole

ZHANG Shaoru1   ZHOU Yunshu1   ZHANG Ruodi1   LIU Shili1   CHEN Xiaohua1   WANG Zhuo1   CHEN Zhiqiang2, 3*  

1 Clinical Medicine School of Ningxia Medical University, Yinchuan 750003, China

2 Department of Radiology, the First Affiliated Hospital of Hainan Medical College, Haikou 570102, China

3 Department of Radiology, General Hospital of Ningxia Medical University, Yinchuan 750004, China

Corresponding author: CHEN Z Q, E-mail: zhiqiang_chen99@163.com

Conflicts of interest   None.

ACKNOWLEDGMENTS Key Research and Development Program of Ningxia Hui Autonomous Region (No. 2019BEG03033); Natural Science Foundation of Ningxia Hui Autonomous Region (No. 2022AAC03472); "Chunhui Project" of the Ministry of Education (No. Z2012002).
Received  2023-01-15
Accepted  2023-09-21
DOI: 10.12015/issn.1674-8034.2023.10.010
Cite this article as: ZHANG S R, ZHOU Y S, ZHANG R D, et al. The value of multi-parametric MRI-based radiomics models in distinguishing primary central nervous system lymphoma from high-grade glioma[J]. Chin J Magn Reson Imaging, 2023, 14(10): 53-57, 64. DOI:10.12015/issn.1674-8034.2023.10.010.

[1]
NAGANE M. Molecular pathogenesis and therapeutic development of primary central nervous system lymphoma: update and future perspectives[J]. Rinsho Ketsueki, 2022, 63(9): 1145-1156. DOI: 10.11406/rinketsu.63.1145.
[2]
TARICIOTTI L, CACCAVELLA V M, FIORE G, et al. A deep learning model for preoperative differentiation of glioblastoma, brain metastasis and primary central nervous system lymphoma: a pilot study[J/OL]. Front Oncol, 2022, 12: 816638 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8907851/. DOI: 10.3389/fonc.2022.816638.
[3]
BRANCATO V, CERRONE M, LAVITRANO M, et al. A systematic review of the current status andquality of radiomics for glioma differential diagnosis[J/OL]. Cancers (Basel), 2022, 14(11): 2731 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9179305/. DOI: 10.3390/cancers14112731.
[4]
GUHA A, GODA J S, DASGUPTA A, et al. Classifying primary central nervous system lymphoma from glioblastoma using deep learning and radiomics based machine learning approach - a systematic review and meta-analysis[J/OL]. Front Oncol, 2022, 12: 884173 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9574102/. DOI: 10.3389/fonc.2022.884173.
[5]
CASSINELLI PETERSEN G I, SHATALOV J, VERMA T, et al. Machine learning in differentiating gliomas from primary CNS lymphomas: a systematic review, reporting quality, and risk of bias assessment[J]. AJNR Am J Neuroradiol, 2022, 43(4): 526-533. DOI: 10.3174/ajnr.A7473.
[6]
CHEN T, LIU Y, WANG Y, et al. Evidence-based expert consensus on the management of primary central nervous system lymphoma in China[J/OL]. J Hematol Oncol, 2022, 15(1): 136 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9524012/. DOI: 10.1186/s13045-022-01356-7.
[7]
ZHANG Y, LIANG K, HE J, et al. Deep learning with data enhancement for the differentiation of solitary and multiple cerebral glioblastoma, lymphoma, and tumefactive demyelinating lesion[J/OL]. Front Oncol, 2021, 11: 665891 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8416477/. DOI: 10.3389/fonc.2021.665891.
[8]
GRITSCH S, BATCHELOR T T, GONZALEZ-CASTRO L N. Diagnostic, therapeutic, and prognostic implications of the 2021 World Health Organization classification of tumors of the central nervous system[J]. Cancer, 2022, 128(1): 47-58. DOI: 10.1002/cncr.33918.
[9]
GERAGHTY B J, DASGUPTA A, SANDHU M, et al. Predicting survival in patients with glioblastoma using MRI radiomic features extracted from radiation planning volumes[J]. J Neurooncol, 2022, 156(3): 579-588. DOI: 10.1007/s11060-021-03939-9.
[10]
FATANIA K, MOHAMUD F, CLARK A, et al. Intensity standardization of MRI prior to radiomic feature extractionfor artificial intelligence research in glioma—a systematic review[J]. Eur Radiol, 2022, 32(10): 7014- 7025. DOI: 10.1007/s00330-022-08807-2.
[11]
TANG W, DUAN J Y, YU Z Y, et al. Value of enhanced MRI radiomics in predicting IDH-1 genotype in gliomas[J]. Chin J Magn Reson Imaging, 2022, 13(5): 111-114. DOI: 10.12015/issn.1674-8034.2022.05.020.
[12]
LÜ J B, QI X, CHEN Z G, et al. Research progress of MRI based radiomics in differentiating high-grade gliomas from solitary brain metastases[J]. Chin J Magn Reson Imaging, 2021, 12(6): 108-110. DOI: 10.12015/issn.1674-8034.2021.06.022.
[13]
JING H, YANG F, PENG K, et al. Multimodal MRI-based radiomic nomogram for the early differentiation of recurrence and pseudoprogression of high-grade glioma[J]. Biomed Res Int, 2022, 2022: 1-17. DOI: 10.1155/2022/4667117.
[14]
AFTAB K, AAMIR F B, Mallick S, et al. Radiomics for precision medicine in glioblastoma[J]. J Neurooncol, 2022, 156(2): 217-231. DOI: 10.1007/s11060-021-03933-1.
[15]
ABDEL-RAZEK A A K, ALKSAS A, SHEHATA M, et al. Clinical applications of artificial intelligence and radiomics in neuro oncology imaging[J/OL]. Insights into Imaging, 2021, 12(1): 152 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8531173/. DOI: 10.1186/s13244-021-01102-6.
[16]
YI Z, LONG L, ZENG Y, et al. Current advances and challenges in radiomics of brain tumors[J/OL]. Front Oncol, 2021, 11: 732196 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8551958/. DOI: 10.3389/fonc.2021.732196.
[17]
SUH H B, CHOI Y S, BAE S, et al. Primary central nervous system lymphoma and atypical glioblastoma: differentiation using radiomics approach[J]. Eur Radiol, 2018, 28(9): 3832-3839. DOI: 10.1007/s00330-018-5368-4.
[18]
PRIYA S, LIU Y, WARD C, et al. Radiomic based machine learning performance for a three class problem in neuro-oncology: time to test the waters?[J/OL]. Cancers (Basel), 2021, 13(11): 2568 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8197204/. DOI: 10.3390/cancers13112568.
[19]
LI Z, BAI H, SUN Q, et al. Multiregional radiomics profiling from multiparametric MRI: Identifying an imaging predictor of IDH1 mutation status in glioblastoma[J]. Cancer Med, 2018, 7(12): 5999-6009. DOI: 10.1002/cam4.1863.
[20]
OZTURK K, SOYLU E, CAYCI Z. Differentiation between primary CNS lymphoma and atypical glioblastoma according to major genomic alterations using diffusion and susceptibility-weighted MR imaging[J/OL]. Eur J Radiol, 2021, 141: 109784 [2023-01-15]. https://pubmed.ncbi.nlm.nih.gov/34051685/. DOI: 10.1016/j.ejrad.2021.109784.
[21]
HAN Y, WANG Z, LI W, et al. Differentiation between primary central nervous system lymphoma and atypical glioblastoma based on MRI morphological feature and signal intensity ratio: a retrospective multicenter study[J/OL]. Front Oncol, 2022, 12: 811197 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8841723/. DOI: 10.3389/fonc.2022.811197.
[22]
WU S, MENG J, YU Q, et al. Radiomics-based machine learning methods for isocitrate dehydrogenase genotype prediction of diffuse gliomas[J]. J Cancer Res Clin Oncol, 2019, 145(3): 543-550. DOI: 10.1007/s00432-018-2787-1.
[23]
LU C F, HSU F T, HSIEH K L, et al. Machine learning-based radiomics for molecular subtyping of gliomas[J]. Clin Cancer Res, 2018, 24(18): 4429-4436. DOI: 10.1158/1078-0432.CCR-17-3445.
[24]
BEIG N, BERA K, TIWARI P. Introduction to radiomics and radiogenomics in neuro-oncology: implications and challenges[J]. Neurooncol Adv, 2020, 2: 3-14. DOI: 10.1093/noajnl/vdaa148.
[25]
MAYERHOEFER M E, MATERKA A, LANGS G, et al. Introduction to radiomics[J]. J Nucl Med, 2020, 61(4): 488-495. DOI: 10.2967/jnumed.118.222893.
[26]
LIU D, CHEN J, GE H, et al. Differentiation of malignant brain tumor types using intratumoral an peritumoral radiomic features[J/OL]. Front Oncol, 2022, 12: 848846 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9366472/.. DOI: 10.3389/fonc.2022.848846.
[27]
PRIYA S, WARD C, LOCKE T, et al. Glioblastoma and primary central nervous system lymphoma: differentiation using MRI derived first-order texture analysis-a machine learning study[J]. Neuroradiol J, 2021, 34(4): 320-328. DOI: 10.3390/cancers13112568.
[28]
KIM Y, CHO H, KIM S T, et al. Radiomics features to distinguish glioblastoma from primary central nervous system lymphoma on multi-parametric MRI[J]. Neuroradiology, 2018, 60(12): 1297-1305. DOI: 10.1007/s00234-018-2091-4.
[29]
XIA W, HU B, LI H, et al. Multiparametric-MRI-based radiomics model for differentiating primary central nervous system lymphoma from glioblastoma: development and cross-vendor validation[J]. J Magn Reson Imaging, 2021, 53(1): 242-250. DOI: 10.1002/jmri.27344.
[30]
BATHLA G, PRIYA S, LIU Y, et al. Radiomics-based differentiation between glioblastoma and primary central nervous system lymphoma: a comparison of diagnostic performance across different MRI sequences and machine learning techniques[J]. Eur Radiol, 2021, 31(11): 8703-8713. DOI: 10.1007/s00330-021-07845-6.
[31]
XIA W, HU B, LI H, et al. Deep learning for automatic differential diagnosis of primary central nervous system lymphoma and glioblastoma: multi-parametric magnetic resonance imaging based convolutional neural network model[J]. J Magn Reson Imaging, 2021, 54(3): 880-887. DOI: 10.1002/jmri.27592.
[32]
HE J, REN J, NIU G, et al. Multiparametric MR radiomics in brain glioma: models comparation to predict biomarker status[J/OL]. BMC Med Imaging, 2022, 22(1): 137 [2023-01-15]. https://pubmed.ncbi.nlm.nih.gov/35931979/. DOI: 10.1186/s12880-022-00865-8.
[33]
KANG D, PARK J E, KIM Y, et al. Diffusion radiomics as a diagnostic model for atypical manifestation of primary central nervous system lymphoma: development and multicenter external validation[J]. Neuro Oncol, 2018, 20(9): 1251-1261. DOI: 10.1093/neuonc/noy021.
[34]
ZHANG L, LIU X, XU X, et al. An integrative non-invasive malignant brain tumors classification and Ki-67 labeling index prediction pipeline with radiomics approach[J/OL]. Eur J Radiol, 2023, 158: 110639 [2023-01-15]. https://pubmed.ncbi.nlm.nih.gov/36463703/. DOI: 10.1016/j.ejrad.2022.110639.
[35]
TAN Y, ZHANG S, WEI J, et al. A radiomics nomogram may improve the prediction of IDH genotype for astrocytoma before surgery[J]. Eur Radiol, 2019, 29(7): 3325-3337. DOI: 10.1007/s00330-019-06056-4.
[36]
GUO W, SHE D, XING Z, et al. Multiparametric MRI-based radiomics model for predicting H3 K27M mutant status in diffuse midline glioma: a comparative study across different sequences and machine learning techniques[J/OL]. Front Oncol, 2022, 12: 796583 [2023-01-15]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8928064/. DOI: 10.3389/fonc.2022.796583.

PREV The correlation between the number and location distribution of cerebral microbleeds and imaging of cerebral small vessel disease
NEXT Value of arterial spin labeling and diffusion tensor imaging in evaluating IDH1 gene phenotype in gliomas
  


LINK


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