Skip to main content

Advertisement

Springer Nature Link
Log in

A transfer learning approach on MRI-based radiomics signature for overall survival prediction of low-grade and high-grade gliomas

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Lower-grade gliomas (LGG) can eventually progress to glioblastoma (GBM) and death. In the context of the transfer learning approach, we aimed to train and test an MRI-based radiomics model for predicting survival in GBM patients and validate it in LGG patients. From each patient’s 704 MRI-based radiomics features, we chose seventeen optimal radiomics signatures in the GBM training set (n = 71) and used these features in both the GBM testing set (n = 31) and LGG validation set (n = 107) for further analysis. Each patient’s risk score, calculated based on those optimal radiomics signatures, was chosen to represent the radiomics model. We compared the radiomics model with clinical, gene status models, and combined model integrating radiomics, clinical, and gene status in predicting survival. The average iAUCs of combined models in training, testing, and validation sets were respectively 0.804, 0.878, and 0.802, and those of radiomics models were 0.798, 0.867, and 0.717. The average iAUCs of gene status and clinical models ranged from 0.522 to 0.735 in all three sets. The radiomics model trained in GBM patients can effectively predict the overall survival of GBM and LGG patients, and the combined model improved this ability.

Graphical Abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  1. Ostrom QT et al (2018) Epidemiology of intracranial gliomas. Prog Neurol Surg 30:1–11

    Article  PubMed  Google Scholar 

  2. Ohgaki H, Kleihues P (2005) Epidemiology and etiology of gliomas. Acta Neuropathol 109(1):93–108

    Article  PubMed  Google Scholar 

  3. Ostrom QT et al (2014) The epidemiology of glioma in adults: a “state of the science” review. Neuro Oncol 16(7):896–913

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Komori T (2017) The 2016 WHO classification of tumours of the central nervous system: the major points of revision. Neurol Med Chir (Tokyo) 57(7):301–311

    Article  PubMed  Google Scholar 

  5. Delfanti RL et al (2017) Imaging correlates for the 2016 update on WHO classification of grade II/III gliomas: implications for IDH, 1p/19q and ATRX status. J Neurooncol 135(3):601–609

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Louis DN et al (2021) The 2021 WHO classification of tumors of the central nervous system: a summary. Neuro Oncol 23(8):1231–1251

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  7. Sanghani P et al (2018) Overall survival prediction in glioblastoma multiforme patients from volumetric, shape and texture features using machine learning. Surg Oncol 27(4):709–714

    Article  PubMed  Google Scholar 

  8. Stupp R et al (2014) High-grade glioma: ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up. Ann Oncol 25:iii93–iii101

  9. Stummer W et al (2006) Fluorescence-guided surgery with 5-aminolevulinic acid for resection of malignant glioma: a randomised controlled multicentre phase III trial. Lancet Oncol 7(5):392–401

    Article  CAS  PubMed  Google Scholar 

  10. Thakkar JP et al (2014) Epidemiologic and molecular prognostic review of glioblastoma. Cancer Epidemiol Biomarkers Prev 23(10):1985–1996

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  11. Network CGAR (2015) Comprehensive, integrative genomic analysis of diffuse lower-grade gliomas. N Engl J Med 372(26):2481–2498

    Article  Google Scholar 

  12. Gorlia T et al (2013) New validated prognostic models and prognostic calculators in patients with low-grade gliomas diagnosed by central pathology review: a pooled analysis of EORTC/RTOG/NCCTG phase III clinical trials. Neuro Oncol 15(11):1568–1579

    Article  PubMed  PubMed Central  Google Scholar 

  13. Li G et al (2022) An MRI radiomics approach to predict survival and tumour-infiltrating macrophages in gliomas. Brain 145(3):1151–1161

  14. Yan J et al (2021) Quantitative MRI-based radiomics for noninvasively predicting molecular subtypes and survival in glioma patients. NPJ Precis Oncol 5(1):1–9

    CAS  Google Scholar 

  15. Chato L, Latifi S (2021) Machine learning and radiomic features to predict overall survival time for glioblastoma patients. J Pers Med 11(12):1336

    Article  PubMed  PubMed Central  Google Scholar 

  16. Lu Y et al (2020) Machine learning-based radiomic, clinical and semantic feature analysis for predicting overall survival and MGMT promoter methylation status in patients with glioblastoma. Magn Reson Imaging 74:161–170

    Article  CAS  PubMed  Google Scholar 

  17. Bae S et al (2018) Radiomic MRI phenotyping of glioblastoma: improving survival prediction. Radiology 289(3):797–806

    Article  PubMed  Google Scholar 

  18. Choi YS et al (2020) Machine learning and radiomic phenotyping of lower grade gliomas: improving survival prediction. Eur Radiol 30(7):3834–3842

    Article  PubMed  Google Scholar 

  19. Zhang H et al (2016) Radiomics for survival analysis and prediction in glioblastoma (GBM)—a preliminary study. Int J Radiat Oncol Biol Phys 96(2):E106–E107

    Article  Google Scholar 

  20. Choi Y et al (2021) Radiomics may increase the prognostic value for survival in glioblastoma patients when combined with conventional clinical and genetic prognostic models. Eur Radiol 31(4):2084–2093

    Article  CAS  PubMed  Google Scholar 

  21. Aerts HJ et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006

    Article  CAS  PubMed  Google Scholar 

  22. Oberheim Bush NA, Chang S (2016) Treatment strategies for low-grade glioma in adults. J Oncol Pract 12(12):1235–1241

    Article  PubMed  Google Scholar 

  23. Claus EB et al (2015) Survival and low-grade glioma: the emergence of genetic information. Neurosurg Focus 38(1):E6

    Article  PubMed  PubMed Central  Google Scholar 

  24. Bakas S et al (2017) Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features. Sci Data 4(1):1–13

    Article  Google Scholar 

  25. Rathore S et al (2017) Brain cancer imaging phenomics toolkit (brain-CaPTk): an interactive platform for quantitative analysis of glioblastoma. In: Brainlesion: glioma, multiple sclerosis, stroke and traumatic brain injuries: Third International Workshop, BrainLes 2017, held in Conjunction with MICCAI 2017, Quebec City, QC, Canada. Revised selected papers 3, pp 133–145

  26. Bakas S et al (2020) Overall survival prediction in glioblastoma patients using structural magnetic resonance imaging (MRI): advanced radiomic features may compensate for lack of advanced MRI modalities. J Med Imaging (Bellingham) 7(3):031505

    PubMed  Google Scholar 

  27. Baid U et al (2020) Overall survival prediction in glioblastoma with radiomic features using machine learning. Front Comput Neurosci 14:61

  28. Priya S et al (2021) Survival prediction in glioblastoma on post-contrast magnetic resonance imaging using filtration based first-order texture analysis: comparison of multiple machine learning models. Neuroradiol J 34(4):355–362

    Article  PubMed  PubMed Central  Google Scholar 

  29. Mao X et al (2018) A 15-long non-coding RNA signature to improve prognosis prediction of cervical squamous cell carcinoma. Gynecol Oncol 149(1):181–187

    Article  CAS  PubMed  Google Scholar 

  30. Sana J et al (2014) Risk score based on microRNA expression signature is independent prognostic classifier of glioblastoma patients. Carcinogenesis 35(12):2756–2762

    Article  CAS  PubMed  Google Scholar 

  31. Li C et al (2020) Identification of a four-gene panel predicting overall survival for lung adenocarcinoma. BMC Cancer 20(1):1198

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  32. Xue M et al (2019) Identification of prognostic signatures for predicting the overall survival of uveal melanoma patients. J Cancer 10(20):4921

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  33. Shang J et al (2017) Identification of lung adenocarcinoma specific dysregulated genes with diagnostic and prognostic value across 27 TCGA cancer types. Oncotarget 8(50):87292

    Article  PubMed  PubMed Central  Google Scholar 

  34. Pak E et al (2021) Prediction of prognosis in glioblastoma using radiomics features of dynamic contrast-enhanced mri. Korean J Radiol 22(9):1514

    Article  PubMed  PubMed Central  Google Scholar 

  35. Qian Z et al (2018) Radiogenomics of lower-grade gliomas: a radiomic signature as a biological surrogate for survival prediction. Aging (Albany NY) 10(10):2884

    Article  CAS  PubMed  Google Scholar 

  36. Ma C et al (2021) Quantitative integration of radiomic and genomic data improves survival prediction of low-grade glioma patients. Math Biosci Eng 18(1):727–744

    Article  Google Scholar 

  37. Tian M et al (2018) Impact of gender on the survival of patients with glioblastoma. Biosci Rep 38(6):BSR20180752

  38. Sun Y et al (2019) Characteristics and prognostic factors of age-stratified high-grade intracranial glioma patients: a population-based analysis. Bosn J Basic Med Sci 19(4):375

    PubMed  PubMed Central  Google Scholar 

  39. Han S et al (2020) IDH mutation in glioma: molecular mechanisms and potential therapeutic targets. Br J Cancer 122(11):1580–1589

    Article  PubMed  PubMed Central  Google Scholar 

  40. Fuster-Garcia E et al (2021) MGMT methylation may benefit overall survival in patients with moderately vascularized glioblastomas. Eur Radiol 31(3):1738–1747

    Article  CAS  PubMed  Google Scholar 

  41. Han F et al (2016) PTEN gene mutations correlate to poor prognosis in glioma patients: a meta-analysis. Onco Targets Ther 9:3485

    CAS  PubMed  PubMed Central  Google Scholar 

  42. Tan Y et al (2019) Improving survival prediction of high-grade glioma via machine learning techniques based on MRI radiomic, genetic and clinical risk factors. Eur J Radiol 120:108609

    Article  PubMed  Google Scholar 

  43. Dar JA, Srivastava KK, Lone SA (2022) Fr-WCSO-DRN: fractional water cycle swarm optimizer-based deep residual network for pulmonary abnormality detection from respiratory sound signals. SN Comput Sci 3(5):378

    Article  Google Scholar 

  44. Dar JA, Srivastava KK, Ahmed Lone S (2022) Design and development of hybrid optimization enabled deep learning model for COVID-19 detection with comparative analysis with DCNN, BIAT-GRU. XGBoost. Comput Biol Med 150:106123

    Article  CAS  PubMed  Google Scholar 

  45. Ponnupilla Omana S et al (2023) Henry gas bird swarm optimization algorithm-based deep learning for brain tumor classification using magnetic resonance imaging. Concurr Comput: Pract Exp 35(4):e7541

    Article  Google Scholar 

  46. Kudulaiti N et al (2021) A nomogram for individualized prediction of overall survival in patients with newly diagnosed glioblastoma: a real-world retrospective cohort study. BMC Surg 21(1):1–11

    Article  Google Scholar 

  47. Paul R et al (2016) Deep feature transfer learning in combination with traditional features predicts survival among patients with lung adenocarcinoma. Tomography 2(4):388–395

    Article  PubMed  PubMed Central  Google Scholar 

  48. Vial A et al (2018) The role of deep learning and radiomic feature extraction in cancer-specific predictive modelling: a review. Transl Cancer Res 7(3):803–816

    Article  Google Scholar 

  49. Dar JA, Srivastava KK, Lone SA (2022) Spectral features and optimal hierarchical attention networks for pulmonary abnormality detection from the respiratory sound signals. Biomed Signal Process Control 78:103905

    Article  Google Scholar 

Download references

Funding

This work was supported by the National Science and Technology Council, Taiwan (grant numbers MOST110-2221-E-038–001-MY2 and MOST111-2628-E-038–002-MY3).

Author information

Author notes

  1. Viet Huan Le and Tran Nguyen Tuan Minh contributed equally to this work.

Authors and Affiliations

  1. International Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei, 110, Taiwan

    Viet Huan Le, Tran Nguyen Tuan Minh & Quang Hien Kha

  2. Department of Thoracic Surgery, Khanh Hoa General Hospital, Nha Trang City, 65000, Vietnam

    Viet Huan Le

  3. Professional Master Program in Artificial Intelligence in Medicine, College of Medicine, Taipei Medical University, Taipei, 110, Taiwan

    Nguyen Quoc Khanh Le

  4. Research Center for Artificial Intelligence in Medicine, Taipei Medical University, Taipei, 110, Taiwan

    Nguyen Quoc Khanh Le

  5. AIBioMed Research Group, Taipei Medical University, Taipei, 110, Taiwan

    Nguyen Quoc Khanh Le

  6. Translational Imaging Research Center, Taipei Medical University Hospital, Taipei, 110, Taiwan

    Nguyen Quoc Khanh Le

Authors
  1. Viet Huan Le
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Tran Nguyen Tuan Minh
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Quang Hien Kha
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Nguyen Quoc Khanh Le
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Nguyen Quoc Khanh Le.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher's note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 30.4 KB)

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Le, V.H., Minh, T.N.T., Kha, Q.H. et al. A transfer learning approach on MRI-based radiomics signature for overall survival prediction of low-grade and high-grade gliomas. Med Biol Eng Comput 61, 2699–2712 (2023). https://doi.org/10.1007/s11517-023-02875-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-023-02875-2

Keywords