Skip to main content

Advertisement

SpringerLink
Log in

Radiomic features from dynamic susceptibility contrast perfusion-weighted imaging improve the three-class prediction of molecular subtypes in patients with adult diffuse gliomas

  • Imaging Informatics and Artificial Intelligence
  • Published:
European Radiology Aims and scope Submit manuscript

Abstract

Objectives

To investigate whether radiomic features extracted from dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) can improve the prediction of the molecular subtypes of adult diffuse gliomas, and to further develop and validate a multimodal radiomic model by integrating radiomic features from conventional and perfusion MRI.

Methods

We extracted 1197 radiomic features from each sequence of conventional MRI and DSC-PWI, respectively. The Boruta algorithm was used for feature selection and combination, and a three-class random forest method was applied to construct the models. We also constructed a combined model by integrating radiomic features and clinical metrics. The models’ diagnostic performance for discriminating the molecular subtypes (IDH wild type [IDHwt], IDH mutant and 1p/19q-noncodeleted [IDHmut-noncodel], and IDH mutant and 1p/19q-codeleted [IDHmut-codel]) was compared using AUCs in the validation set.

Results

We included 272 patients (training set, n = 166; validation set, n = 106) with grade II–IV gliomas (mean age, 48.7 years; range, 19–77 years). The proportions of the molecular subtypes were 66.2% IDHwt, 15.1% IDHmut-noncodel, and 18.8% IDHmut-codel. Nineteen radiomic features (13 from conventional MRI and 6 from DSC-PWI) were selected to build the multimodal radiomic model. In the validation set, the multimodal radiomic model showed better performance than the conventional radiomic model did in predicting the IDHwt and IDHmut-codel subtypes, which was comparable to the conventional radiomic model in predicting the IDHmut-noncodel subtype. The multimodal radiomic model yielded similar performance as the combined model in predicting the three molecular subtypes.

Conclusions

Adding DSC-PWI to conventional MRI can improve molecular subtype prediction in patients with diffuse gliomas.

Key Points

• The multimodal radiomic model outperformed conventional MRI when predicting both the IDH wild type and IDH mutant and 1p/19q-codeleted subtypes of gliomas.

• The multimodal radiomic model showed comparable performance to the combined model in the prediction of the three molecular subtypes.

• Radiomic features from T1-weighted gadolinium contrast-enhanced and relative cerebral blood volume images played an important role in the prediction of molecular subtypes.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

Abbreviations

DSC-PWI:

Dynamic susceptibility contrast perfusion-weighted imaging

FISH:

Fluorescence in situ hybridization

FLAIR:

Fluid-attenuated inversion recovery

FOV:

Field of view

IDH:

Isocitrate dehydrogenase

NEX:

Number of excite

rCBF:

Relative cerebral blood flow

rCBV:

Relative cerebral blood volume

T1:

T1-weighted

T1c:

T1-weighted gadolinium contrast-enhanced

T2:

T2-weighted

TE:

Echo time

TR:

Repetition time

VOI:

Volume of interest

WHO:

World Health Organization

References

  1. Louis DN, Perry A, Reifenberger G et al (2016) The 2016 World Health Organization classification of tumors of the central nervous system: a summary. Acta Neuropathol 131:803–820

    Article  PubMed  Google Scholar 

  2. Stupp R, Hegi ME, Mason WP et al (2009) European Organisation for Research and Treatment of Cancer Brain Tumour and Radiation Oncology Groups; National Cancer Institute of Canada Clinical Trials Group. Effects of radiotherapy with concomitant and adjuvant temozolomide versus radiotherapy alone on survival in glioblastoma in a randomised phase III study: 5-year analysis of the EORTC-NCIC trial. Lancet Oncol 10:459–466

    Article  CAS  PubMed  Google Scholar 

  3. Suzuki H, Aoki K, Chiba K et al (2015) Mutational landscape and clonal architecture in grade II and III gliomas. Nat Genet 47:458–468

    Article  CAS  PubMed  Google Scholar 

  4. Louis DN, Perry A, Wesseling P, et al (2021) The 2021 WHO classification of tumors of the central nervous system: a summary. Neuro Oncol 29:noab106

  5. Cairncross JG, Wang M, Jenkins RB et al (2014) Benefit from procarbazine, lomustine, and vincristine in oligodendroglial tumors is associated with mutation of IDH. J Clin Oncol 32:783–790

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. van den Bent MJ, Brandes AA, Taphoorn MJ et al (2013) Adjuvant procarbazine, lomustine, and vincristine chemotherapy in newly diagnosed anaplastic oligodendroglioma: long-term follow-up of EORTC brain tumor group study 26951. J Clin Oncol 31:344–350

    Article  PubMed  Google Scholar 

  7. Eckel-Passow JE, Lachance DH, Molinaro AM et al (2015) Glioma groups based on 1p/19q, IDH, and TERT promoter mutations in tumors. N Engl J Med 372:2499–2508

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  8. Wong QH, Li KK, Wang WW et al (2021) Molecular landscape of IDH-mutant primary astrocytoma grade IV/glioblastomas. Mod Pathol 34:1245–1260

    Article  CAS  PubMed  Google Scholar 

  9. Cagney DN, Sul J, Huang RY, Ligon KL, Wen PY, Alexander BM (2018) The FDA NIH Biomarkers, EndpointS, and other Tools (BEST) resource in neuro-oncology. Neuro Oncol 20:1162–1172

    Article  CAS  PubMed  Google Scholar 

  10. Rodriguez FJ, Mota RA, Scheithauer BW et al (2009) Interphase cytogenetics for 1p19q and t(1;19)(q10;p10) may distinguish prognostically relevant subgroups in extraventricular neurocytoma. Brain Pathol 19:623–629

    Article  CAS  PubMed  Google Scholar 

  11. Akyerli CB, Yüksel Ş, Can Ö et al (2018) Use of telomerase promoter mutations to mark specific molecular subsets with reciprocal clinical behavior in IDH mutant and IDH wild-type diffuse gliomas. J Neurosurg 128:1102–1114

    Article  CAS  PubMed  Google Scholar 

  12. Yan J, Liu L, Wang W et al (2020) Radiomic features from multi-parameter MRI combined with clinical parameters predict molecular subgroups in patients with medulloblastoma. Front Oncol 10:558162

    Article  PubMed  PubMed Central  Google Scholar 

  13. Coroller TP, Bi WL, Huynh E et al (2017) Radiographic prediction of meningioma grade by semantic and radiomic features. PLoS One 12:e0187908

  14. Zhang B, Chang K, Ramkissoon S et al (2017) Multimodal MRI features predict isocitrate dehydrogenase genotype in high-grade gliomas. Neuro Oncol 19:109–117

    Article  CAS  PubMed  Google Scholar 

  15. Yan J, Zhang B, Zhang S et al (2021) Quantitative MRI-based radiomics for noninvasively predicting molecular subtypes and survival in glioma patients. NPJ Precis Oncol 5:72

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  16. van der Voort SR, Incekara F, Wijnenga MMJ et al (2019) Predicting the 1p/19q codeletion status of presumed low-grade glioma with an externally validated machine learning algorithm. Clin Cancer Res 25:7455–7462

    Article  PubMed  Google Scholar 

  17. Cui Y, Tha KK, Terasaka S et al (2016) Prognostic imaging biomarkers in glioblastoma: development and independent validation on the basis of multiregion and quantitative analysis of MR images. Radiology 278:546–553

    Article  PubMed  Google Scholar 

  18. Yan J, Zhang S, Li KK et al (2020) Incremental prognostic value and underlying biological pathways of radiomics patterns in medulloblastoma. EBioMedicine 61:103093

    Article  PubMed  PubMed Central  Google Scholar 

  19. Holdsworth SJ, Bammer R (2008) Magnetic resonance imaging techniques: fMRI, DWI, and PWI. Semin Neurol 28:395–406

    Article  PubMed  PubMed Central  Google Scholar 

  20. Kickingereder P, Sahm F, Radbruch A et al (2015) IDH mutation status is associated with a distinct hypoxia/angiogenesis transcriptome signature which is non-invasively predictable with rCBV imaging in human glioma. Sci Rep 5:16238

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  21. Zhang HW, Lyu GW, He WJ et al (2020) DSC and DCE histogram analyses of glioma biomarkers, including IDH, MGMT, and TERT, on differentiation and survival. Acad Radiol 27:e263–e271

    Article  PubMed  Google Scholar 

  22. Wu H, Tong H, Du X et al (2020) Vascular habitat analysis based on dynamic susceptibility contrast perfusion MRI predicts IDH mutation status and prognosis in high-grade gliomas. Eur Radiol 30:3254–3265

    Article  CAS  PubMed  Google Scholar 

  23. Z wanenburg A, Leger S, V allières M, Löck S (2019) Image biomarker standardisation initiative. Available online at: http://arxiv.org/abs/1612.07003

  24. Breiman L (2001) Random forests. Machine Learn 45:5–32

  25. Louis DN, Perry A, Reifenberger G et al (2018) cIMPACT-NOW update 3: recommended diagnostic criteria for “Diffuse astrocytic glioma, IDH-wildtype, with molecular features of glioblastoma, WHO grade IV.” Acta Neuropathol 136:805–810

    Article  PubMed  PubMed Central  Google Scholar 

  26. Brat DJ, Aldape K, Colman H et al (2020) cIMPACT-NOW update 5: recommended grading criteria and terminologies for IDH-mutant astrocytomas. Acta Neuropathol 139:603–608

    Article  PubMed  PubMed Central  Google Scholar 

  27. Zhang X, Tian Q, Wang L et al (2018) Radiomics strategy for molecular subtype stratification of lower-grade glioma: detecting IDH and TP53 mutations based on multimodal MRI. J Magn Reson Imaging 48:916–926

    Article  PubMed  Google Scholar 

  28. Lu CF, Hsu FT, Hsieh KL et al (2018) Machine learning-based radiomics for molecular subtyping of gliomas. Clin Cancer Res 24:4429–4436

    Article  PubMed  Google Scholar 

  29. Zhang L, He L, Lugano R et al (2018) IDH mutation status is associated with distinct vascular gene expression signatures in lower-grade gliomas. Neuro Oncol 20:1505–1516

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  30. Kapoor GS, Gocke TA, Chawla S et al (2009) Magnetic resonance perfusion-weighted imaging defines angiogenic subtypes of oligodendroglioma according to 1p19q and EGFR status. J Neurooncol 92:373–386

    Article  PubMed  Google Scholar 

  31. Song S, Wang L, Yang H et al (2021) Static 18F-FET PET and DSC-PWI based on hybrid PET/MR for the prediction of gliomas defined by IDH and 1p/19q status. Eur Radiol 31:4087–4096

    Article  CAS  PubMed  Google Scholar 

  32. Yang X, Lin Y, Xing Z, She D, Su Y, Cao D (2020) Predicting 1p/19q codeletion status using diffusion-, susceptibility-, perfusion-weighted, and conventional MRI in IDH-mutant lower-grade gliomas. Acta Radiol 22:284185120973624

    Google Scholar 

  33. Kim M, Jung SY, Park JE et al (2020) Diffusion- and perfusion-weighted MRI radiomics model may predict isocitrate dehydrogenase (IDH) mutation and tumor aggressiveness in diffuse lower grade glioma. Eur Radiol 30:2142–2151

    Article  PubMed  Google Scholar 

  34. Yamashita K, Hiwatashi A, Togao O et al (2016) MR imaging-based analysis of glioblastoma multiforme: estimation of IDH1 mutation status. AJNR Am J Neuroradiol 37:58–65

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  35. Lee B, Park JE, Bjørnerud A, Kim JH, Lee JY, Kim HS (2018) Clinical value of vascular permeability estimates using dynamic susceptibility contrast MRI: improved diagnostic performance in distinguishing hypervascular primary CNS lymphoma from glioblastoma. AJNR Am J Neuroradiol 39:1415–1422

    CAS  PubMed  PubMed Central  Google Scholar 

  36. Macyszyn L, Akbari H, Pisapia JM et al (2016) Imaging patterns predict patient survival and molecular subtype in glioblastoma via machine learning techniques. Neuro Oncol 18:417–425

    Article  PubMed  Google Scholar 

Download references

Funding

This study has received funding from the National Natural Science Foundation of China (No. 82102149, 82273493, 81702465, 82173090, U1804172, U1904148), the Excellent Youth Talent Cultivation Program of Innovation in Health Science and Technology of Henan Province (YXKC2022061), the Key Program of Medical Science and Technique Foundation of Henan Province (No. SBGJ202002062), and the Science and Technology Program of Henan Province (No. 192102310390, 202102310454, 202102310113, 202102310136, 202102310138, 202102310083).

Author information

Author notes

  1. Dongling Pei, Fangzhan Guan, and Xuanke Hong contributed equally to this work

Authors and Affiliations

  1. Department of Neurosurgery, The First Affiliated Hospital of Zhengzhou University, Jian She Dong Road 1, Zhengzhou, 450052, Henan, China

    Dongling Pei, Fangzhan Guan, Xuanke Hong, Zhen Liu, Yuning Qiu, Wenchao Duan, Minkai Wang, Chen Sun, Wenqing Wang, Xiangxiang Wang, Yu Guo, Zilong Wang, Zhongyi Liu, Aoqi Xing, Zhixuan Guo, Lin Luo, Xianzhi Liu & Zhenyu Zhang

  2. Department of Pathology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, China

    Weiwei Wang

  3. Department of MRI, The First Affiliated Hospital of Zhengzhou University, Jian She Dong Road 1, Zhengzhou, 450052, Henan, China

    Jingliang Cheng & Jing Yan

  4. Department of Radiology, The First Affiliated Hospital of Jinan University, Tianhe District, No. 613 Huangpu West Road, Guangzhou, Guangdong, China

    Bin Zhang

Authors
  1. Dongling Pei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fangzhan Guan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Xuanke Hong
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Zhen Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Weiwei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yuning Qiu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Wenchao Duan
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Minkai Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Chen Sun
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Wenqing Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Xiangxiang Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Yu Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Zilong Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Zhongyi Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Aoqi Xing
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Zhixuan Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  17. Lin Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

  18. Xianzhi Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  19. Jingliang Cheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  20. Bin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  21. Zhenyu Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  22. Jing Yan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Bin Zhang, Zhenyu Zhang or Jing Yan.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Jing Yan.

Conflict of interest

The authors of this manuscript declare no relationships with any companies whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• diagnostic or prognostic study

• performed at one institution

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 2020 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

Pei, D., Guan, F., Hong, X. et al. Radiomic features from dynamic susceptibility contrast perfusion-weighted imaging improve the three-class prediction of molecular subtypes in patients with adult diffuse gliomas. Eur Radiol 33, 3455–3466 (2023). https://doi.org/10.1007/s00330-023-09459-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-023-09459-6

Keywords

Search

Navigation