Skip to main content
SpringerLink
Log in

A fully automatic multiparametric radiomics model for differentiation of adult pilocytic astrocytomas from high-grade gliomas

  • Neuro
  • Published:
European Radiology Aims and scope Submit manuscript

A Correction to this article was published on 18 March 2022

This article has been updated

Abstract

Objectives

To develop a fully automatic radiomics model to differentiate adult pilocytic astrocytomas (PA) from high-grade gliomas (HGGs).

Methods

This retrospective study included 302 adult patients with PA (n = 62) or HGG (n = 240). The patients were randomly divided into training (n = 211) and test (n = 91) sets. Clinical data were obtained, and radiomic features (n = 372) were extracted from multiparametric MRI with automatic tumour segmentation. After feature selection with F-score, a Light Gradient Boosting Machine classifier with subsampling was trained to develop three models: (1) clinical model, (2) radiomics model, and (3) combined clinical and radiomics model. Human performance was also assessed. The performance of the classifier was validated in the test set. SHapley Additive exPlanations (SHAP) was applied to explore the interpretability of the model.

Results

A total of 15 radiomic features were selected. In the test set, the combined clinical and radiomics model (area under the curve [AUC], 0.93) showed a significantly higher performance than the clinical model (AUC, 0.79, p = 0.037) and had a similar performance to the radiomics model (AUC, 0.92, p = 0.828). The combined clinical and radiomics model also showed a significantly higher performance than humans (AUC, 0.76–0.81, p < 0.05). The model explanation by SHAP suggested that lower intratumoural heterogeneity from T2-weighted images was highly associated with PA diagnosis.

Conclusions

The fully automatic combined clinical and radiomics model may be helpful for differentiating adult PAs from HGGs.

Key Points

• Differentiating adult PAs from HGGs is challenging because PAs may manifest a large spectrum of imaging presentations, often including aggressive imaging features.

• The fully automatic combined clinical and radiomics model showed a significantly higher performance than the clinical model or humans.

• The model explanation by SHAP suggested that second-order features from T2-weighted imaging were important in diagnosis and might reflect the underlying pathophysiology that PAs have lesser tissue heterogeneity than HGGs.

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

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Change history

Abbreviations

AUC:

Area under the curve

CI:

Confidence interval

FLAIR:

Fluid-attenuation inversion recovery

GLCM:

Grey-level co-occurrence matrix

GLSZM:

Grey-level size zone matrix

HGG:

High-grade glioma

IDH:

Isocitrate dehydrogenase

NGTDM:

Neighbouring grey-tone difference matrix

PA:

Pilocytic astrocytoma

SHAP:

SHapley Additive exPlanations

T1:

T1-weighted

T1C:

Post-contrast T1-weighted

T2:

T2-weighted

WHO:

World Health Organization

References

  1. Ostrom QT, Gittleman H, Truitt G, Boscia A, Kruchko C, Barnholtz-Sloan JS (2018) CBTRUS Statistical Report: Primary Brain and Other Central Nervous System Tumors Diagnosed in the United States in 2011-2015. Neuro Oncol 20:iv1-iv86

  2. Burkhard C, Di Patre PL, Schüler D et al (2003) A population-based study of the incidence and survival rates in patients with pilocytic astrocytoma. J Neurosurg 98:1170–1174

    Article  Google Scholar 

  3. Gregory TA, Chumbley LB, Henson JW, Theeler BJ (2021) Adult pilocytic astrocytoma in the molecular era: a comprehensive review. CNS Oncol 10:Cns68

  4. Gaudino S, Martucci M, Russo R et al (2017) MR imaging of brain pilocytic astrocytoma: beyond the stereotype of benign astrocytoma. Childs Nerv Syst 33:35–54

    Article  Google Scholar 

  5. Mair MJ, Wöhrer A, Furtner J et al (2020) Clinical characteristics and prognostic factors of adult patients with pilocytic astrocytoma. J Neurooncol 148:187–198

    Article  CAS  Google Scholar 

  6. Theeler BJ, Ellezam B, Sadighi ZS et al (2014) Adult pilocytic astrocytomas: clinical features and molecular analysis. Neuro Oncol 16:841–847

    Article  CAS  Google Scholar 

  7. Collins VP, Jones DT, Giannini C (2015) Pilocytic astrocytoma: pathology, molecular mechanisms and markers. Acta Neuropathol 129:775–788

    Article  CAS  Google Scholar 

  8. Palma L, Guidetti B (1985) Cystic pilocytic astrocytomas of the cerebral hemispheres. Surgical experience with 51 cases and long-term results. J Neurosurg 62:811–815

    Article  CAS  Google Scholar 

  9. Weller M, van den Bent M, Tonn JC et al (2017) European Association for Neuro-Oncology (EANO) guideline on the diagnosis and treatment of adult astrocytic and oligodendroglial gliomas. Lancet Oncol 18:e315–e329

    Article  Google Scholar 

  10. Kikuchi K, Hiwatashi A, Togao O et al (2018) Usefulness of perfusion- and diffusion-weighted imaging to differentiate between pilocytic astrocytomas and high-grade gliomas: a multicenter study in Japan. Neuroradiology 60:391–401

    Article  Google Scholar 

  11. de Fatima Vasco Aragao M, Law M, Batista de Almeida D et al (2014) Comparison of perfusion, diffusion, and MR spectroscopy between low-grade enhancing pilocytic astrocytomas and high-grade astrocytomas. AJNR Am J Neuroradiol 35:1495–1502

    Article  Google Scholar 

  12. Park YW, Kim D, Eom J et al (2021) A diagnostic tree for differentiation of adult pilocytic astrocytomas from high-grade gliomas. Eur J Radiol 143:109946

  13. Sharma MK, Mansur DB, Reifenberger G et al (2007) Distinct genetic signatures among pilocytic astrocytomas relate to their brain region origin. Cancer Res 67:890–900

    Article  CAS  Google Scholar 

  14. Johnson DR, Brown PD, Galanis E, Hammack JE (2012) Pilocytic astrocytoma survival in adults: analysis of the Surveillance, Epidemiology, and End Results Program of the National Cancer Institute. J Neurooncol 108:187–193

    Article  Google Scholar 

  15. Shin I, Park YW, Ahn SS et al (2022) Clinical factors and conventional MRI may independently predict progression-free survival and overall survival in adult pilocytic astrocytomas. Neuroradiology. https://doi.org/10.1007/s00234-021-02872-y

  16. Jungk C, Reinhardt A, Warta R et al (2019) Extent of Resection, MGMT Promoter Methylation Status and Tumor Location Independently Predict Progression-Free Survival in Adult Sporadic Pilocytic Astrocytoma. Cancers (Basel) 11:1072

    Article  CAS  Google Scholar 

  17. Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: Images Are More than Pictures, They Are Data. Radiology 278:563–577

    Article  Google Scholar 

  18. Park YW, Han K, Ahn SS et al (2018) Whole-Tumor Histogram and Texture Analyses of DTI for Evaluation of IDH1-Mutation and 1p/19q-Codeletion Status in World Health Organization Grade II Gliomas. AJNR Am J Neuroradiol 39:693–698

    Article  CAS  Google Scholar 

  19. Park YW, Choi YS, Ahn SS, Chang JH, Kim SH, Lee SK (2019) Radiomics MRI Phenotyping with Machine Learning to Predict the Grade of Lower-Grade Gliomas: A Study Focused on Nonenhancing Tumors. Korean J Radiol 20:1381–1389

    Article  Google Scholar 

  20. Kickingereder P, Burth S, Wick A et al (2016) Radiomic Profiling of Glioblastoma: Identifying an Imaging Predictor of Patient Survival with Improved Performance over Established Clinical and Radiologic Risk Models. Radiology 280:880–889

    Article  Google Scholar 

  21. Park JE, Park SY, Kim HJ, Kim HS (2019) Reproducibility and Generalizability in Radiomics Modeling: Possible Strategies in Radiologic and Statistical Perspectives. Korean J Radiol 20:1124–1137

    Article  Google Scholar 

  22. Won SY, Park YW, Ahn SS et al (2021) Quality assessment of meningioma radiomics studies: Bridging the gap between exploratory research and clinical applications. Eur J Radiol 138:109673

    Article  Google Scholar 

  23. 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  Google Scholar 

  24. Yan H, Parsons DW, Jin G et al (2009) IDH1 and IDH2 mutations in gliomas. N Engl J Med 360:765–773

    Article  CAS  Google Scholar 

  25. Takano S, Tian W, Matsuda M et al (2011) Detection of IDH1 mutation in human gliomas: comparison of immunohistochemistry and sequencing. Brain Tumor Pathol 28:115–123

  26. Kickingereder P, Isensee F, Tursunova I et al (2019) Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: a multicentre, retrospective study. Lancet Oncol 20:728–740

    Article  Google Scholar 

  27. Isensee F, Petersen J, Kohl SA, Jäger PF, Maier-Hein KH (2019) nnu-net: Breaking the spell on successful medical image segmentation. arXiv preprint arXiv:190408128 1:1-8

  28. Tustison NJ, Avants BB, Cook PA et al (2010) N4ITK: improved N3 bias correction. IEEE Trans Med Imaging 29:1310–1320

    Article  Google Scholar 

  29. van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res 77:e104–e107

    Article  Google Scholar 

  30. Zwanenburg A, Leger S, Vallières M, Löck S (2016) Image biomarker standardisation initiative. arXiv preprint arXiv:161207003

  31. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357

    Article  Google Scholar 

  32. DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837–845

    Article  CAS  Google Scholar 

  33. Lundberg S, Lee S-IJapa (2017) A unified approach to interpreting model predictions. arXiv:1705.07874

  34. Dong F, Li Q, Xu D et al (2019) Differentiation between pilocytic astrocytoma and glioblastoma: a decision tree model using contrast-enhanced magnetic resonance imaging-derived quantitative radiomic features. Eur Radiol 29:3968–3975

    Article  Google Scholar 

  35. Zhao Y, Lu Y, Li X, Zheng Y, Yin B (2020) The Evaluation of Radiomic Models in Distinguishing Pilocytic Astrocytoma From Cystic Oligodendroglioma With Multiparametric MRI. J Comput Assist Tomogr 44:969–976

    Article  Google Scholar 

  36. Li M, Wang H, Shang Z, Yang Z, Zhang Y, Wan H (2020) Ependymoma and pilocytic astrocytoma: Differentiation using radiomics approach based on machine learning. J Clin Neurosci 78:175–180

    Article  Google Scholar 

  37. Ellison DW, Hawkins C, Jones DTW et al (2019) cIMPACT-NOW update 4: diffuse gliomas characterized by MYB, MYBL1, or FGFR1 alterations or BRAF(V600E) mutation. Acta Neuropathol 137:683–687

    Article  CAS  Google Scholar 

  38. Lundberg S, Lee S-I (2017) A unified approach to interpreting model predictions. In Adv. Neural Information Processing 4765–4774. (Curran Associates)

  39. Bang M, Eom J, An C et al (2021) An interpretable multiparametric radiomics model for the diagnosis of schizophrenia using magnetic resonance imaging of the corpus callosum. Transl Psychiatry 11:462

    Article  CAS  Google Scholar 

  40. Patel AP, Tirosh I, Trombetta JJ et al (2014) Single-cell RNA-seq highlights intratumoral heterogeneity in primary glioblastoma. Science 344:1396–1401

    Article  CAS  Google Scholar 

  41. Wesseling P, Kros JM, Jeuken JW (2011) The pathological diagnosis of diffuse gliomas: towards a smart synthesis of microscopic and molecular information in a multidisciplinary context. Diagn Histopathol 17:486–494

    Article  Google Scholar 

  42. An C, Park YW, Ahn SS, Han K, Kim H, Lee SK (2021) Radiomics machine learning study with a small sample size: Single random training-test set split may lead to unreliable results. PLoS One 16:e0256152

Download references

Funding

This research received funding from the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, Information and Communication Technologies & Future Planning (2020R1A2C1003886). This research was also supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2020R1I1A1A01071648). This research was supported by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (HI21C1161).

Author information

Authors and Affiliations

  1. Department of Radiology and Research Institute of Radiological Science and Center for Clinical Imaging Data Science, Yonsei University College of Medicine, 50-1 Yonsei-ro, Seodaemun-gu, Seoul, 120-752, Korea

    Yae Won Park, Sung Soo Ahn & Seung-Koo Lee

  2. Department of Computer Science, Yonsei University, Seoul, Korea

    Jihwan Eom

  3. Department of Psychology, Yonsei University, Seoul, Korea

    Dain Kim

  4. Department of Neurosurgery, Yonsei University College of Medicine, Seoul, Korea

    Eui Hyun Kim, Seok-Gu Kang & Jong Hee Chang

  5. Department of Pathology, Yonsei University College of Medicine, Seoul, Korea

    Se Hoon Kim

Authors
  1. Yae Won Park
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jihwan Eom
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dain Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Sung Soo Ahn
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Eui Hyun Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Seok-Gu Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Jong Hee Chang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Se Hoon Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Seung-Koo Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sung Soo Ahn.

Ethics declarations

Guarantor

The scientific guarantor of this publication is Professor Seung-Koo Lee, MD, PhD, from Yonsei University College of Medicine (slee@yuhs.ac).

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

We consulted a PhD who has significant statistical expertise (K.H, a biostatistician with 11 years of experience in biostatistics).

Informed consent

The Institutional Review Board waived the requirement to obtain informed patient consent for this retrospective study.

Ethical approval

The Institutional Review Board of our university waived the requirement for informed patient consent for this retrospective study.

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.

The original online version of this article was revised: The title was incorrectly given as “A fully automatic multiparametric radiomics model for differentiation of adult pilocytic astrocytomas from glioblastomas” but should have been instead “A fully automatic multiparametric radiomics model for differentiation of adult pilocytic astrocytomas from high-grade gliomas”.

Supplementary information

ESM 1

(DOCX 22 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Park, Y.W., Eom, J., Kim, D. et al. A fully automatic multiparametric radiomics model for differentiation of adult pilocytic astrocytomas from high-grade gliomas. Eur Radiol 32, 4500–4509 (2022). https://doi.org/10.1007/s00330-022-08575-z

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-022-08575-z

Keywords

Search

Navigation