Share：
Share this content in WeChat
X
[Chinese][PDF]411
• Clinical Article •
MRI deep learning study to predict progression-free survival in brain glioma
ZHANG Qiufen  GAO Yu  MAO Ke  HAN Dongming  ZHAI Xiaoyang 

Cite this article as: ZHANG Q F, GAO Y, MAO K, et al. MRI deep learning study to predict progression-free survival in brain glioma[J]. Chin J Magn Reson Imaging, 2025, 16(2): 14-19, 28. DOI:10.12015/issn.1674-8034.2025.02.003.


[Abstract] Objective To develop and validate a deep learning (DL) model for predicting progression-free survival (PFS) in patients with glioma based on T2WI.Materials and Methods MRI and clinical data from 345 patients diagnosed with glioma across three centers were collected. Nine DL models were established to predict PFS, and their performance was validated using an external test set. The best model was determined by the C-index, and the performances of these models were compared. Patients were stratified into high-risk and low-risk groups based on risk score cutoff values calculated from the training set, and differences in PFS between these groups were assessed.Results The training and test sets consisted of 249 and 96 patients, respectively. Compared with other DL models, the Wide ResNet50-2 DL model performed best, achieving C-indexes of 0.694 and 0.714 in the training and test sets, respectively. A combined model incorporating both clinical and DL features showed the highest performance, with C-indexes of 0.724 and 0.795 in the training and external test sets, respectively.Conclusions A DL model based on preoperative MRI can predict PFS in patients with glioma and may serve as a preoperative risk stratification tool.
[Keywords] brain glioma；magnetic resonance imaging；deep learning；machine learning；progression-free survival

ZHANG Qiufen1   GAO Yu2   MAO Ke2   HAN Dongming2   ZHAI Xiaoyang3*  

1 Department of Radiology, the Kaifeng Central Hospital, Kaifeng 475000, China

2 Department of MR, the First Affiliated Hospital of Xinxiang Medical University, Xinxiang 453100, China

3 Department of MR, the First Affiliated Hospital of Henan University of CM, Zhengzhou 450000, China

Corresponding author: ZHAI X Y, E-mail: zxybuddha@163.com

Conflicts of interest   None.

Received  2024-08-15
Accepted  2025-02-10
DOI: 10.12015/issn.1674-8034.2025.02.003
Cite this article as: ZHANG Q F, GAO Y, MAO K, et al. MRI deep learning study to predict progression-free survival in brain glioma[J]. Chin J Magn Reson Imaging, 2025, 16(2): 14-19, 28. DOI:10.12015/issn.1674-8034.2025.02.003.

[1]
OSTROM Q T, BAUCHET L, DAVIS F G, et al. The epidemiology of glioma in adults: a "state of the science" review[J]. Neuro Oncol, 2014, 16(7): 896-913. DOI: 10.1093/neuonc/nou358.
[2]
RASMUSSEN B K, HANSEN S, LAURSEN R J, et al. Epidemiology of glioma: clinical characteristics, symptoms, and predictors of glioma patients grade I-IV in the the Danish Neuro-Oncology Registry[J]. J Neurooncol, 2017, 135(3): 571-579. DOI: 10.1007/s11060-017-2607-5S.
[3]
TYKOCKI T, ELTAYEB M. Ten-year survival in glioblastoma. A systematic review[J]. J Clin Neurosci, 2018, 54: 7-13. DOI: 10.1016/j.jocn.2018.05.002.
[4]
OMURO A, DEANGELIS L M. Glioblastoma and other malignant gliomas: a clinical review[J]. JAMA, 2013, 310(17): 1842-1850. DOI: 10.1001/jama.2013.280319.
[5]
CHAWLA S, SHEHU V, GUPTA P K, et al. Physiological Imaging Methods for Evaluating Response to Immunotherapies in Glioblastomas[J/OL]. Int J Mol Sci, 2021, 22(8): 3867 [2024-11-14]. https://pubmed.ncbi.nlm.nih.gov/33918043/. DOI: 10.3390/ijms22083867.
[6]
TAN A C, ASHLEY D M, LOPEZ G Y, et al. Management of glioblastoma: State of the art and future directions[J]. CA Cancer J Clin, 2020, 70(4): 299-312. DOI: 10.3322/caac.21613.
[7]
HILARIO A, SEPULVEDA J M, PEREZ-NUNEZ A, et al. A prognostic model based on preoperative MRI predicts overall survival in patients with diffuse gliomas[J]. AJNR Am J Neuroradiol, 2014, 35(6): 1096-1102. DOI: 10.3174/ajnr.A3837.
[8]
ZACCAGNA F, GRIST J T, QUARTUCCIO N, et al. Imaging and treatment of brain tumors through molecular targeting: Recent clinical advances[J/OL]. Eur J Radiol, 2021, 142: 109842 [2024-11-14]. https://pubmed.ncbi.nlm.nih.gov/34274843/. DOI: 10.1016/j.ejrad.2021.109842.
[9]
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.
[10]
LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553): 436-444. DOI: 10.1038/nature14539.
[11]
HUANG J, SHLOBIN N A, DECUYPERE M, et al. Deep Learning for Outcome Prediction in Neurosurgery: A Systematic Review of Design, Reporting, and Reproducibility[J]. Neurosurgery, 2022, 90(1): 16-38. DOI: 10.1227/NEU.0000000000001736.
[12]
CIFCI D, FOERSCH S, KATHER J N. Artificial intelligence to identify genetic alterations in conventional histopathology[J]. J Pathol, 2022, 257(4): 430-444. DOI: 10.1002/path.5898.
[13]
HOSNY A, PARMAR C, QUACKENBUSH J, et al. Artificial intelligence in radiology[J]. Nat Rev Cancer, 2018, 18(8): 500-510. DOI: 10.1038/s41568-018-0016-5.
[14]
SKREDE O J, De RAEDT S, KLEPPE A, et al. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study[J]. Lancet, 2020, 395(10221): 350-360. DOI: 10.1016/S0140-6736(19)32998-8.
[15]
TRUHN D, SCHRADING S, HAARBURGER C, et al. Radiomic versus Convolutional Neural Networks Analysis for Classification of Contrast-enhancing Lesions at Multiparametric Breast MRI[J]. Radiology, 2019, 290(2): 290-297. DOI: 10.1148/radiol.2018181352.
[16]
LUO J, PAN M, MO K, et al. Emerging role of artificial intelligence in diagnosis, classification and clinical management of glioma[J]. Semin Cancer Biol, 2023, 91: 110-123. DOI: 10.1016/j.semcancer.2023.03.006.
[17]
WANG R, GAO Y. Research progress of multimodal MRI radiomics and deep learning in glioma[J]. Chin J Magn Reson Imaging, 2024, 15(7): 165-172. DOI: 10.12015/issn.1674-8034.2024.07.028.
[18]
LOUIS D N, PERRY A, WESSELING P, et al. The 2021 WHO Classification of Tumors of the Central Nervous System: a summary[J]. Neuro Oncol, 2021, 23(8): 1231-1251. DOI: 10.1093/neuonc/noab106.
[19]
JIRASEK T, KRSKOVA L, DOLINOVA I, et al. News in WHO 2021 classification of tumours of the central nervous system[J]. Cesk Patol, 2022, 58(3): 126-134.
[20]
National Health Commission of the PRC, CACA, CMDA, Guidelines for the diagnosis and treatment of glioma(2022 edition)[J]. Chinese Journal of Surgery, 2022, 38(8): 757-777. DOI: 10.3760/cma.j.cn112050-20220510-00239.
[21]
TUSTISON N J, AVANTS B B, COOK P A, et al. N4ITK: improved N3 bias correction[J]. IEEE Trans Med Imaging, 2010, 29(6): 1310-1320. DOI: 10.1109/TMI.2010.2046908.
[22]
WANG W, PENG Y, FENG X, et al. Development and Validation of a Computed Tomography-Based Radiomics Signature to Predict Response to Neoadjuvant Chemotherapy for Locally Advanced Gastric Cancer[J/OL]. JAMA Netw Open, 2021, 4(8): e2121143 [2024-11-14]. https://doi.org/10.1001/jamanetworkopen.2021.21143. DOI: 10.1001/jamanetworkopen.2021.21143.
[23]
CLARKE R. Introduction: Cancer Gene Networks[J]. Methods Mol Biol, 2017, 1513: 1-9. DOI: 10.1007/978-1-4939-6539-7_1.
[24]
SOEDA A, HARA A, KUNISADA T, et al. The evidence of glioblastoma heterogeneity[J/OL]. Sci Rep, 2015, 5: 7979 [2024-11-14]. https://pubmed.ncbi.nlm.nih.gov/25623281/. DOI: 10.1038/srep07979.
[25]
ALVES T R, LIMA F R, KAHN S A, et al. Glioblastoma cells: a heterogeneous and fatal tumor interacting with the parenchyma[J]. Life Sci, 2011, 89(15-16): 532-539. DOI: 10.1016/j.lfs.2011.04.022.
[26]
LEMEE J M, CLAVREUL A, MENEI P. Intratumoral heterogeneity in glioblastoma: don't forget the peritumoral brain zone[J]. Neuro Oncol, 2015, 17(10): 1322-1332. DOI: 10.1093/neuonc/nov119.
[27]
NICHOLSON J G, FINE H A. Diffuse Glioma Heterogeneity and Its Therapeutic Implications[J]. Cancer Discov, 2021, 11(3): 575-590. DOI: 10.1158/2159-8290.CD-20-1474.
[28]
LI X, ZHANG S, ZHANG Q, et al. Diagnosis of thyroid cancer using deep convolutional neural network models applied to sonographic images: a retrospective, multicohort, diagnostic study[J]. Lancet Oncol, 2019, 20(2): 193-201. DOI: 10.1016/S1470-2045(18)30762-9.
[29]
TABASSUM M, SUMAN A A, SUERO M E, et al. Radiomics and Machine Learning in Brain Tumors and Their Habitat: A Systematic Review[J/OL]. Cancers (Basel), 2023, 15(15): 3845 [2024-11-14]. https://pubmed.ncbi.nlm.nih.gov/37568660/. DOI: 10.3390/cancers15153845.
[30]
WANG K, LU X, ZHOU H, et al. Deep learning Radiomics of shear wave elastography significantly improved diagnostic performance for assessing liver fibrosis in chronic hepatitis B: a prospective multicentre study[J]. Gut, 2019, 68(4): 729-741. DOI: 10.1136/gutjnl-2018-316204.
[31]
FATHI K A, SAXENA S, TOORENS E, et al. Clinical measures, radiomics, and genomics offer synergistic value in AI-based prediction of overall survival in patients with glioblastoma[J/OL]. Sci Rep, 2022, 12(1): 8784 [2024-11-14]. https://pubmed.ncbi.nlm.nih.gov/35610333/. DOI: 10.1038/s41598-022-12699-z.
[32]
LUO C, YANG J, LIU Z, et al. Predicting the recurrence and overall survival of patients with glioma based on histopathological images using deep learning[J/OL]. Front Neurol, 2023, 14: 1100933 [2024-11-14]. https://pubmed.ncbi.nlm.nih.gov/37234780/. DOI: 10.3389/fneur.2023.1100933.
[33]
JIANG X, ZHAO H, SALDANHA O L, et al. An MRI Deep Learning Model Predicts Outcome in Rectal Cancer[J/OL]. Radiology, 2023, 307(5): e222223 [2024-11-14]. https://doi.org/10.1148/radiol.222223. DOI: 10.1148/radiol.222223.
[34]
DELGADO-LOPEZ P D, CORRALES-GARCIA E M.Survival in glioblastoma: a review on the impact of treatment modalities[J/OL]. Clin Transl Oncol, 2016, 18(11): 1062-1071. DOI: 10.1007/s12094-016-1497-x.
[35]
HUANG B, CHEN T, ZHANG Y, et al. Deep Learning for the Prediction of the Survival of Midline Diffuse Glioma with an H3K27M Alteration[J/OL]. Brain Sci, 2023, 13(10): 1483 [2024-11-14]. https://pubmed.ncbi.nlm.nih.gov/37891850/. DOI: 10.3390/brainsci13101483.
[36]
BRAT D J, VERHAAK R G, ALDAPE K D, et al. Comprehensive, Integrative Genomic Analysis of Diffuse Lower-Grade Gliomas[J]. N Engl J Med, 2015, 372(26): 2481-2498. DOI: 10.1056/NEJMoa1402121.
[37]
HUANG X Y, CHEN F L, ZHANG Y, et al. A predictive model for survival outcomes of glioma patients based on multi-parametric, multi-regional MRI radiomics features and clinical features[J]. Journal of Southern Medical University, 2024, 44(10): 2004-2014. DOI: 10.12122/j.issn.1673-4254.2024.10.19.
[38]
MAHOOTIHA M, TAK D, YE Z, et al. Multimodal deep learning improves recurrence risk prediction in pediatric low-grade gliomas[J]. Neuro Oncol, 2025, 27(1): 277-290. DOI: 10.1093/neuonc/noae173.

PREV 3D-pCASL in the developmental brain abnormalities of preterm infants born to hypertensive mothers during pregnancy
NEXT A multicenter study of 2.5D convolutional neural networks based on multi-sequence MRI in distinguishing meningioma
  


LINK


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