Share：
Share this content in WeChat
X
[Chinese] [PDF] 4 1
• Reviews •
Research progress of MRI radiomics in differential diagnosis and prognostic evaluation of primary central nervous system lymphoma
ZHONG Qi  CUI Jiacheng  XU Donghao  XU Lei 

Cite this article as: ZHONG Q, CUI J C, XU D H, et al. Research progress of MRI radiomics in differential diagnosis and prognostic evaluation of primary central nervous system lymphoma[J]. Chin J Magn Reson Imaging, 2026, 17(3): 168-173. DOI:10.12015/issn.1674-8034.2026.03.024.


[Abstract] Primary central nervous system lymphoma (PCNSL) is an aggressive extranodal lymphoma that remains clinically rare. Owing to its highly invasive tumor biology and the fact that therapeutic options are constrained by the blood–brain barrier, patients with PCNSL exhibit markedly poor overall prognosis, making PCNSL one of the most challenging lymphoma subtypes in contemporary clinical oncology. Although MRI is now widely used for the diagnosis and grading of central nervous system tumors, the underlying molecular mechanisms, tumor microenvironment, and biological processes within the lesions still require further exploration. Radiomics can mine deeper information from the tumor, enabling more objective and comprehensive assessment of tumor heterogeneity, and has shown great potential for diagnosis, grading, and prognosis prediction across various cancers. This review focuses on the latest applications and research advances of MRI-based radiomics in the diagnosis and prognostic prediction of PCNSL, highlights current limitations, and outlines future research directions, aiming to further advance the field.
[Keywords] primary central nervous system lymphoma；magnetic resonance imaging；artificial intelligence；radiomics；diagnosis；prognosis

ZHONG Qi1   CUI Jiacheng2   XU Donghao3   XU Lei3*  

1 Medical Imaging College of Shandong Second Medical University, Weifang 261053, China

2 Medical Imaging College of Binzhou Medical University, Yantai 264003, China

3 Department of Medical Imaging, Shengli Oilfield Central Hospital, Dongying 257034, China

Corresponding author: XU L, E-mail: bmd588@126.com

Conflicts of interest   None.

Received  2025-11-29
Accepted  2026-02-10
DOI: 10.12015/issn.1674-8034.2026.03.024
Cite this article as: ZHONG Q, CUI J C, XU D H, et al. Research progress of MRI radiomics in differential diagnosis and prognostic evaluation of primary central nervous system lymphoma[J]. Chin J Magn Reson Imaging, 2026, 17(3): 168-173. DOI:10.12015/issn.1674-8034.2026.03.024.

[1]
SHEN B Y, XING S, FU W W. Clinicopathological features and research progress of primary central nervous system large B-cell lymphoma in immune-privileged sites[J]. Journal of Clinical and Experimental Pathology, 2024, 40(5): 471-475. DOI: 10.13315/j.cnki.cjcep.2024.05.005.
[2]
PIAO H Z, WANG Y L, SIMA X T, et al. CACA integrated diagnosis and treatment guidelines for primary central nervous system lymphoma (abridged version)[J]. Cancer, 2023, 42(1): 49-57. DOI: 10.20124/j.cnki.1000-467x.2023.01.004.
[3]
ALAGGIO R, AMADOR C, ANAGNOSTOPOULOS I, et al. The 5th edition of the World Health Organization Classification of Haematolymphoid Tumours: Lymphoid Neoplasms[J]. Leukemia, 2022, 36(7): 1720-1748. DOI: 10.1038/s41375-022-01620-2.
[4]
ZHANG C, LIN S M, WANG C W. Research advances in primary central nervous system lymphoma[J]. Chinese Journal of Minimally Invasive Neurosurgery, 2024, 28(12): 742-747. DOI: 10.11850/j.issn.1009-122X.2024.12.012.
[5]
Lymphoid Disease Group, Chinese Society of Hematology, Chinese Medical Association; Lymphoma Expert Committee of Chinese Society of Clinical Oncology (CSCO). Chinese expert consensus on the diagnosis and treatment of primary central nervous system lymphoma (2024 version)[J]. Journal of Leukemia & Lymphoma, 2024, 33(3): 129-137. DOI: 10.3760/cma.j.cn115356-20231019-00058.
[6]
MENDEZ J S, OSTROM Q T, GITTLEMAN H, et al. The elderly left behind-changes in survival trends of primary central nervous system lymphoma over the past 4 decades[J]. Neuro Oncol, 2018, 20(5): 687-694. DOI: 10.1093/neuonc/nox187.
[7]
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 [2025-11-29] . https://www.ejradiology.com/article/S0720-048X(22)00489-2/fulltext. DOI: 10.1016/j.ejrad.2022.110639.
[8]
CHEONG E N, PARK J E, PARK S Y, et al. Achieving imaging and computational reproducibility on multiparametric MRI radiomics features in brain tumor diagnosis: phantom and clinical validation[J]. Eur Radiol, 2024, 34(3): 2008-2023. DOI: 10.1007/s00330-023-10164-7.
[9]
CHEN C H, LUO P, DONG W J, et al. Advances in MRI machine learning for prognostic evaluation of pituitary neuroendocrine tumors[J]. Chin J Magn Reson Imaging, 2025, 16(2): 154-158, 171. DOI: 10.12015/issn.1674-8034.2025.02.025.
[10]
KIM Y, CHO H 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.
[11]
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.
[12]
LU G, ZHANG Y, WANG W, et al. Machine Learning and Deep Learning CT-Based Models for Predicting the Primary Central Nervous System Lymphoma and Glioma Types: A Multicenter Retrospective Study[J/OL]. Front Neurol, 2022, 13: 905227 [2025-11-29]. https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2022.905227/full. DOI: 10.3389/fneur.2022.905227.
[13]
LIU J, TU J, XU L, et al. MRI-based radiomics signatures for preoperative prediction of Ki-67 index in primary central nervous system lymphoma[J/OL]. Eur J Radiol, 2024, 178: 111603 [2025-11-29]. https://pubmed.ncbi.nlm.nih.gov/38976966/. DOI: 10.1016/j.ejrad.2024.111603.
[14]
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.
[15]
LIN Q S, YU H, PAN M J, et al. Construction of different machine learning models based on T 1WI-enhanced images fordifferentiating between glioblastoma and primary central nervous system lymphoma[J]. Journal of China Clinic Medical Imaging, 2024, 35(1): 1-6. DOI: 10.12117/jccmi.2024.01.001.
[16]
WANG M X, LIU G L, LI Y H, et al. Value of multiparametric MRI-based machine learning models in differential diagnosis of primary central nervous system lymphoma and atypical glioblastoma[J]. Chin J Med Imaging, 2024, 32(11): 1089-1096. DOI: 10.3969/j.issn.1005-5185.2024.11.001.
[17]
KANG D, PARK J E, KIM Y H, 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.
[18]
YU X, HONG W, YE M, et al. Atypical primary central nervous system lymphoma and glioblastoma: multiparametric differentiation based on non-enhancing volume, apparent diffusion coefficient, and arterial spin labeling[J]. Eur Radiol, 2023, 33(8): 5357-5367. DOI: 10.1007/s00330-023-09681-2.
[19]
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.
[20]
KICKINGEREDER P, WIESTLER B, SAHM F, et al. Primary central nervous system lymphoma and atypical glioblastoma: multiparametric differentiation by using diffusion-, perfusion-, and susceptibility-weighted MR imaging[J]. Radiology, 2014, 272(3): 843-850. DOI: 10.1148/radiol.14132740.
[21]
LIU D, CHEN J, GE H, et al. Differentiation of malignant brain tumor types using intratumoral and peritumoral radiomic features[J/OL]. Front Oncol, 2022, 12: 848846 [2025-11-29]. https://pmc.ncbi.nlm.nih.gov/articles/PMC9366472/. DOI: 10.3389/fonc.2022.848846.
[22]
KONG Z, JIANG C, ZHU R, et al. 18F-FDG-PET-based radiomics features to distinguish primary central nervous system lymphoma from glioblastoma[J/OL]. Neuroimage Clin, 2019, 23: 101912 [2025-11-29]. https://pmc.ncbi.nlm.nih.gov/articles/PMC6702330/. DOI: 10.1016/j.nicl.2019.101912.
[23]
DESTITO M, MARZULLO A, LEONE R, et al. Radiomics-Based Machine Learning Model for Predicting Overall and Progression-Free Survival in Rare Cancer: A Case Study for Primary CNS Lymphoma Patients[J/OL]. Bioengineering (Basel), 2023, 10(3): 285 [2025-11-29]. https://pubmed.ncbi.nlm.nih.gov/36978676/. DOI: 10.3390/bioengineering10030285.
[24]
SWINBURNE NC, SCHEFFLEIN J, SAKAI Y, et al. Machine learning for semi-automated classification of glioblastoma, brain metastasis and central nervous system lymphoma using magnetic resonance advanced imaging[J/OL]. Ann Transl Med, 2019, 7(11): 232 [2025-11-29]. https://pubmed.ncbi.nlm.nih.gov/31317002/. DOI: 10.21037/atm.2018.08.05.
[25]
CHEN C, ZHUO H, WEI X, et al. Contrast-Enhanced MRI Texture Parameters as Potential Prognostic Factors for Primary Central Nervous System Lymphoma Patients Receiving High-Dose Methotrexate-Based Chemotherapy[J/OL]. Contrast Media Mol Imaging, 2019, 2019: 5481491 [2025-11-29]. https://pmc.ncbi.nlm.nih.gov/articles/PMC6875177/. DOI: 10.1155/2019/5481491.
[26]
LIU J, TU J, HU B, et al. Prognostic Assessment in Patients With Primary Diffuse Large B-Cell Lymphoma of the Central Nervous System Using MRI-Based Radiomics[J]. J Magn Reson Imaging, 2025, 61(3): 1142-1152. DOI: 10.1002/jmri.29533.
[27]
SHE Z, MARZULLO A, DESTITO M, et al. Deep learning-based overall survival prediction model in patients with rare cancer: a case study for primary central nervous system lymphoma[J]. Int J Comput Assist Radiol Surg, 2023, 18(10): 1849-1856. DOI: 10.1007/s11548-023-02886-2.
[28]
YU J, DU H, YE X, et al. High-dose methotrexate-based regimens and post-remission consolidation for treatment of newly diagnosed primary CNS lymphoma: meta-analysis of clinical trials[J/OL]. Sci Rep, 2021, 11(1): 2125 [2025-11-29]. https://pubmed.ncbi.nlm.nih.gov/33483528/. DOI: 10.1038/s41598-020-80724-0.
[29]
SUN X, WU Y, XING R, et al. Non-Myeloablative Chemotherapy as Consolidation Strategy After High-Dose Methotrexate-Based Chemoimmunotherapy in Patients With Primary CNS Lymphoma: A Retrospective Single Center Study in China[J/OL]. Front Oncol, 2022, 12: 792274 [2025-11-29]. https://doi.org/10.3389/fonc.2022.792274. DOI: 10.3389/fonc.2022.792274.
[30]
WANG X, ZHAO L, WANG S, et al. Utility of contrast-enhanced MRI radiomics features combined with clinical indicators for predicting induction chemotherapy response in primary central nervous system lymphoma[J]. J Neurooncol, 2024, 166(3): 451-460. DOI: 10.1007/s11060-023-04554-6.
[31]
LIU G, ZHANG X, ZHANG N, et al. Detecting Double Expression Status in Primary Central Nervous System Lymphoma Using Multiparametric MRI Based Machine Learning[J]. J Magn Reson Imaging, 2024, 59(1): 231-239. DOI: 10.1002/jmri.28782.
[32]
WANG M, LIU G, ZHANG N, et al. Detecting B-cell lymphoma-6 overexpression status in primary central nervous system lymphoma using multiparametric MRI-based machine learning[J]. Neuroradiology, 2025, 67(3): 563-573. DOI: 10.1007/s00234-025-03551-y.

PREV Research progress of multimodal magnetic resonance imaging in occupational manganese exposure-induced neurotoxicity
NEXT Application and progress of multimodal imaging technology in carotid atherosclerotic disease
  


LINK


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