Skip to main content
SpringerLink
Log in

Current Status of the Use of Machine Learning and Magnetic Resonance Imaging in the Field of Neuro-Radiomics

  • Conference paper
  • First Online:
Radiomics and Radiogenomics in Neuro-oncology (RNO-AI 2019)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 11991))

  • 363 Accesses

Abstract

Brain tumors exhibit heterogeneous profile with anomalous hemodynamics. In spite of significant advances at diagnostic and therapeutic fronts in the past couple of decades, the prognosis still remains poor. Magnetic resonance imaging (MRI), which provides information about the structural and functional aspects of the tumor in a noninvasive manner, has gained a lot of popularity for evaluating brain tumors. Several studies have been proposed in the recent past that focused on quantifying the characteristics of brain tumors as seen on MRI scans in terms of various descriptors, such as shape/morphology, texture, signal strength, and temporal dynamics, and then integrating these quantitative descriptors into various diagnostic and prognostic indices. This article first presents an overview of various MRI imaging sequences, such as contrast-enhanced, dynamic susceptibility contrast, diffusion tensor imaging, and conventional MRI, used in routine clinical settings. Later, it provides a detailed overview of the current status of the use of machine learning on MRI scans, with focus on clinical applications of these imaging sequences in brain tumors, including grading, assessment of the treatment response, prediction of prognosis, and identification of molecular markers. The article also highlights current challenges and future research directions.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Louis, D.N., et al.: The 2016 world health organization classification of tumors of the central nervous system: a summary. Acta Neuropathol. 131, 803–820 (2016)

    Article  Google Scholar 

  2. Hardee, M.E., Zagzag, D.: Mechanisms of glioma-associated neovascularization. Am. J. Pathol. 181, 1126–1141 (2012)

    Article  Google Scholar 

  3. Chaddad, A., et al.: Prediction of survival with multi-scale radiomic analysis in glioblastoma patients. Med. Biol. Eng. Comput. 56, 2287–2300 (2018)

    Article  Google Scholar 

  4. Asai, A., et al.: Subacute brain atrophy after radiation therapy for malignant brain tumor. Cancer 63, 1962–1974 (1989)

    Article  Google Scholar 

  5. Shukla, G., et al.: Advanced magnetic resonance imaging in glioblastoma: a review. Chin. Clin. Oncol. 6, 40 (2017)

    Article  Google Scholar 

  6. Villanueva-Meyer, J.E., et al.: Current clinical brain tumor imaging. Neurosurgery 81, 397–415 (2017)

    Article  Google Scholar 

  7. Lambin, P., et al.: Radiomics: extracting more information from medical images using advanced feature analysis. Eur. J. Cancer 48, 441–446 (2012)

    Article  Google Scholar 

  8. Kumar, V., et al.: Radiomics: the process and the challenges. Magn. Reson. Imaging 30, 1234–1248 (2012)

    Article  Google Scholar 

  9. Rathore, S., et al.: Radiopathomics: integration of radiographic and histologic characteristics for prognostication in glioblastoma. Soc. Neuro-Oncol. (2019)

    Google Scholar 

  10. Gillies, R.J., et al.: Radiomics: images are more than pictures, they are data. Radiology 278, 563–577 (2015)

    Article  Google Scholar 

  11. Zhou, M., et al.: Radiomics in brain tumor: image assessment, quantitative feature descriptors, and machine-learning approaches. Am. J. Neuroradiol. 39, 208–216 (2018)

    Article  Google Scholar 

  12. Yushkevich, P.A., et al.: User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability. NeuroImage 31, 1116–1128 (2006)

    Article  Google Scholar 

  13. Gaonkar, B., et al.: Automated segmentation of brain lesions by combining intensity and spatial information. In: IEEE International Symposium on Biomedical Imaging (ISBI), pp. 93–96 (2010)

    Google Scholar 

  14. Lian, Y., Song, Z.: Automated brain tumor segmentation in magnetic resonance imaging based on sliding-window technique and symmetry analysis. Chin. Med. J. 127, 462–468 (2014)

    Google Scholar 

  15. Lu, S., et al.: Peritumoral diffusion tensor imaging of high-grade gliomas and metastatic brain tumors. Am. J. Neuroradiol. 24, 937–941 (2003)

    Google Scholar 

  16. Wintermark, M., et al.: Comparative overview of brain perfusion imaging techniques. J. Neuroradiol. 32, 294–314 (2005)

    Article  Google Scholar 

  17. Tykocinski, E.S., et al.: Use of magnetic perfusion-weighted imaging to determine epidermal growth factor receptor variant III expression in glioblastoma. Neurooncol. 14, 613–623 (2012)

    Google Scholar 

  18. Fedorov, A., et al.: 3D slicer as an image computing platform for the Quantitative Imaging Network. Magn. Reson. Imaging 30, 1323–1341 (2012)

    Article  Google Scholar 

  19. van Griethuysen, J.J.M., et al.: Computational radiomics system to decode the radiographic phenotype. Cancer Res. 77, e104–e107 (2017)

    Article  Google Scholar 

  20. Davatzikos, C., et al.: Cancer imaging phenomics toolkit: quantitative imaging analytics for precision diagnostics and predictive modeling of clinical outcome. J. Med. Imaging: Spec. Sect. Quant. Imaging Methods Transl. Dev. – Honoring Mem. Dr. Larry Clarke 5, 011018 (2018)

    Google Scholar 

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

    Article  Google Scholar 

  22. Rathore, S., et al.: Radiomic MRI signature reveals three distinct subtypes of glioblastoma with different clinical and molecular characteristics, offering prognostic value beyond IDH1. Nat. Sci. Rep. 8, 5087 (2018)

    Article  Google Scholar 

  23. Rathore, S., et al.: Radiomic signature of infiltration in peritumoral edema predicts subsequent recurrence in glioblastoma: implications for personalized radiotherapy planning. J. Med. Imaging (Bellingham) 5, 021219 (2018)

    Google Scholar 

  24. Akbari, H., et al.: Quantitative radiomics and machine learning to distinguish true progression from pseudoprogression in patients with GBM. In: 56th Annual Meeting, American Society of NeuroRadiology (ASNR) (2018)

    Google Scholar 

  25. Arbabshirani, M.R., et al.: Single subject prediction of brain disorders in neuroimaging: promises and pitfalls. NeuroImage 145, 137–165 (2017)

    Article  Google Scholar 

  26. Yang, D., et al.: Evaluation of tumor-derived MRI-texture features for discrimination of molecular subtypes and prediction of 12-month survival status in glioblastoma. Med. Phys. 42, 6725–6735 (2015)

    Article  Google Scholar 

  27. Rathore, S., et al.: Quantitative imaging predictors of overallsurvival in glioblastoma patients robust in the presence of inter-scanner variations. Soc. Neuro-Oncol. 20(Suppl. 6), vi184 (2018)

    Google Scholar 

  28. Chato, L., Latifi, S.: Machine learning and deep learning techniques to predict overall survival of brain tumor patients using MRI images. In: 2017 IEEE 17th International Conference on Bioinformatics and Bioengineering (BIBE), pp. 9–14 (2017)

    Google Scholar 

  29. Krizhevsky, A., et al.: ImageNet Classification with Deep Convolutional Neural Networks. NIPS (2012)

    Google Scholar 

  30. Lao, J., et al.: A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme. Sci. Rep. 7, 10353 (2017)

    Article  Google Scholar 

  31. Molina-García, D., et al.: Prognostic models based on imaging findings in glioblastoma: human versus machine. Sci. Rep. 9, 5982 (2019)

    Article  Google Scholar 

  32. Akbari, H., et al.: Imaging surrogates of infiltration obtained via multiparametric imaging pattern analysis predict subsequent location of recurrence of glioblastoma. Neurosurgery 78, 572–580 (2016)

    Article  Google Scholar 

  33. Rathore, S., et al.: Technical note: a radiomic signature of infiltration in peritumoral edema predicts subsequent recurrence in glioblastoma. In: Medical Imaging 2018: Image-Guided Procedures, Robotic Interventions, and Modeling, vol. 10576, p. 105760O (2018)

    Google Scholar 

  34. Sloan, A.E., et al.: Radiomics-based identification of peritumoral infiltration in de novo glioblastoma imaging presents targets amenable for potential targeted extended resection: a neurosurgical survey. J. Clin. Oncol. 37, e13573 (2019)

    Article  Google Scholar 

  35. Chang, P.D., et al.: A multiparametric model for mapping cellularity in glioblastoma using radiographically localized biopsies. AJNR Am. J. Neuroradiol. 38, 890–898 (2017)

    Article  Google Scholar 

  36. Macdonald, D.R., et al.: Response criteria for phase II studies of supratentorial malignant glioma. J. Clin. Oncol. 8, 1277–1280 (1990)

    Article  Google Scholar 

  37. Hu, X., et al.: Support vector machine multiparametric MRI identification of pseudoprogression from tumor recurrence in patients with resected glioblastoma. J. Magn. Reson. Imaging: JMRI 33, 296–305 (2011)

    Article  Google Scholar 

  38. Parekh, V., et al.: Multiparametric Deep Learning and Radiomics for Tumor Grading and Treatment Response Assessment of Brain Cancer: Preliminary Results (2019)

    Google Scholar 

  39. Qian, X., et al.: Stratification of pseudoprogression and true progression of glioblastoma multiform based on longitudinal diffusion tensor imaging without segmentation. Med. Phys. 43, 5889 (2016)

    Article  Google Scholar 

  40. Abrol, S., et al.: Radiomic analysis of pseudo-progression compared to true progression in glioblastoma patients: a large-scale multi-institutional study. J. Clin. Oncol. 35, 2015 (2017)

    Article  Google Scholar 

  41. Booth, T.C., et al.: Analysis of heterogeneity in T2-weighted MR images can differentiate pseudoprogression from progression in glioblastoma. PLoS ONE 12, e0176528 (2017)

    Article  Google Scholar 

  42. Akbari, H., et al.: Quantitative image analysis and machine learning techniques for distinguishing true progression from pseudoprogression in patients with glioblastoma. J. Neuro-Oncol. 20, vi191–vi192 (2018)

    Google Scholar 

  43. Jang, B.-S., et al.: Prediction of pseudoprogression versus progression using machine learning algorithm in glioblastoma. Sci. Rep. 8, 12516 (2018)

    Article  Google Scholar 

  44. Davatzikos, C., et al.: Precision diagnostics based on machine learning-derived imaging signatures. Magn. Reson. Imaging 64, 49–61 (2019)

    Article  Google Scholar 

  45. Itakura, H., et al.: Magnetic resonance image features identify glioblastoma phenotypic subtypes with distinct molecular pathway activities. Sci. Transl. Med. 7, 303ra138–303ra138 (2015)

    Google Scholar 

  46. Kickingereder, P., et al.: 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 (2016)

    Article  Google Scholar 

  47. Rathore, S., et al.: Radiologic subtypes of glioblastoma calculated via multi-parametric imaging signatures reveal complementary information to current Who classification. Neuro-Oncol. 19, vi155–vi156 (2017)

    Google Scholar 

  48. Rathore, S., et al.: Imaging pattern analysis reveals three distinct phenotypic subtypes of GBM with different survival rates. Neuro-Oncol. 18, vi128 (2016)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Center for Biomedical Image Computing and Analytics (CBICA), Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA

    Ashish Singh & Michel Bilello

Authors
  1. Ashish Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Michel Bilello
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Michel Bilello .

Editor information

Editors and Affiliations

  1. LUMS School of Science and Engineering, Lahore, Pakistan

    Hassan Mohy-ud-Din

  2. University of Pennsylvania, Philadelphia, PA, USA

    Saima Rathore

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Singh, A., Bilello, M. (2020). Current Status of the Use of Machine Learning and Magnetic Resonance Imaging in the Field of Neuro-Radiomics. In: Mohy-ud-Din, H., Rathore, S. (eds) Radiomics and Radiogenomics in Neuro-oncology. RNO-AI 2019. Lecture Notes in Computer Science(), vol 11991. Springer, Cham. https://doi.org/10.1007/978-3-030-40124-5_1

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-40124-5_1

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-40123-8

  • Online ISBN: 978-3-030-40124-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Societies and partnerships

Search

Navigation