Skip to main content

Advertisement

SpringerLink
Log in

Comparative analysis of the spatial distribution of brain metastases across several primary cancers using machine learning and deep learning models

  • Research
  • Published:
Journal of Neuro-Oncology Aims and scope Submit manuscript

Abstract

Objective

Brain metastases (BM) are associated with poor prognosis and increased mortality rates, making them a significant clinical challenge. Studying BMs can aid in improving early detection and monitoring. Systematic comparisons of anatomical distributions of BM from different primary cancers, however, remain largely unavailable.

Methods

To test the hypothesis that anatomical BM distributions differ based on primary cancer type, we analyze the spatial coordinates of BMs for five different primary cancer types along principal component (PC) axes. The dataset includes 3949 intracranial metastases, labeled by primary cancer types and with six features. We employ PC coordinates to highlight the distinctions between various cancer types. We utilized different Machine Learning (ML) algorithms (RF, SVM, TabNet DL) models to establish the relationship between primary cancer diagnosis, spatial coordinates of BMs, age, and target volume.

Results

Our findings revealed that PC1 aligns most with the Y axis, followed by the Z axis, and has minimal correlation with the X axis. Based on PC1 versus PC2 plots, we identified notable differences in anatomical spreading patterns between Breast and Lung cancer, as well as Breast and Renal cancer. In contrast, Renal and Lung cancer, as well as Lung and Melanoma, showed similar patterns. Our ML and DL results demonstrated high accuracy in distinguishing BM distribution for different primary cancers, with the SVM algorithm achieving 97% accuracy using a polynomial kernel and TabNet achieving 96%. The RF algorithm ranked PC1 as the most important discriminating feature.

Conclusions

In summary, our results support accurate multiclass ML classification regarding brain metastases distribution.

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

Similar content being viewed by others

Data Availability

Data that are used in this study are part of the International Radiosurgery Registry Foundation (Study #: IRRF 02-15-2022), & Topography of Brain Metastases by Primary Cancer Genetic Subtypes & Data collection was approved by institutional review boards at each of the institutions affiliated with the IRRF. Due to retrospective design, informed consents were not obtained.

References

  1. Cardinal T, Pangal D, Strickland BA, Newton P, Mahmoodifar S, Mason J, Craig D, Simon T, Tew BY, Yu M et al (2022) Anatomical and topographical variations in the distribution of brain metastases based on primary cancer origin and molecular subtypes: a systematic review. Neuro-Oncol Adv 4(1):170. https://doi.org/10.1093/noajnl/vdab170

    Article  Google Scholar 

  2. In GK, Mason J, Lin S, Newton PK, Kuhn P, Nieva J (2017) Development of metastatic brain disease involves progression through lung metastases in egfr mutated non-small cell lung cancer. Converg Sci Phys Oncol 3(3):035002. https://doi.org/10.1088/2057-1739/aa7a8d

    Article  Google Scholar 

  3. Newton PK, Mason J, Venkatappa N, Jochelson MS, Hurt B, Nieva J, Comen E, Norton L, Kuhn P (2015) Spatiotemporal progression of metastatic breast cancer: a markov chain model highlighting the role of early metastatic sites. NPJ Breast Cancer 1(1):1–9. https://doi.org/10.1038/npjbcancer.2015.18

    Article  Google Scholar 

  4. Newton PK, Mason J, Hurt B, Bethel K, Bazhenova L, Nieva J, Kuhn P (2014) Entropy, complexity and markov diagrams for random walk cancer models. Sci Rep 4(1):7558. https://doi.org/10.1038/srep07558

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Newton PK, Mason J, Bethel K, Bazhenova L, Nieva J, Norton L, Kuhn P (2013) Spreaders and sponges define metastasis in lung cancer: a markov chain monte carlo mathematical model. Can Res 73(9):2760–2769. https://doi.org/10.1158/0008-5472.CAN-12-4488

    Article  CAS  Google Scholar 

  6. Newton PK, Mason J, Bethel K, Bazhenova LA, Nieva J, Kuhn P (2012) A stochastic markov chain model to describe lung cancer growth and metastasis. PLoS ONE 7(4):34637. https://doi.org/10.1371/journal.pone.0034637

    Article  CAS  Google Scholar 

  7. Schroeder T, Bittrich P, Kuhne J, Noebel C, Leischner H, Fiehler J, Schroeder J, Schoen G, Gellisen S (2020) Mapping distribution of brain metastases: does the primary tumor matter? J Neuro-Oncol 147:229–235. https://doi.org/10.1007/s11060-020-03419-6

    Article  CAS  Google Scholar 

  8. Neman J, Franklin M, Madaj Z, Deshpande K, Triche TJ, Sadlik G, Carmichael JD, Chang E, Yu C, Strickland BA et al (2021) Use of predictive spatial modeling to reveal that primary cancers have distinct central nervous system topography patterns of brain metastasis. J Neurosurg 136(1):88–96. https://doi.org/10.3171/2021.1.JNS203536

    Article  PubMed  PubMed Central  Google Scholar 

  9. Mahmoodifar S, Pangal DJ, Cardinal T, Craig D, Simon T, Tew BY, Yang W, Chang E, Yu M, Neman J et al (2022) A quantitative characterization of the spatial distribution of brain metastases from breast cancer and respective molecular subtypes. J Neuro-Oncol 160(1):241–251. https://doi.org/10.1007/s11060-022-04147-9

    Article  CAS  Google Scholar 

  10. Fidler IJ, Yano S, Zhang R-d, Fujimaki T, Bucana CD (2002) The seed and soil hypothesis: vascularisation and brain metastases. Lancet Oncol 3(1):53–57. https://doi.org/10.1016/s1470-2045(01)00622-2

    Article  CAS  PubMed  Google Scholar 

  11. Fidler IJ (2011) The role of the organ microenvironment in brain metastasis. In: Seminars in cancer biology, vol 21. Elsevier, pp 107–112. https://doi.org/10.1016/j.semcancer.2010.12.009

  12. Kirby M (2000) Geometric data analysis: an empirical approach to dimensionality reduction and the study of patterns. John Wiley & Sons Inc, New York

    Google Scholar 

  13. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830

    Google Scholar 

  14. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) Smote: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357. https://doi.org/10.1613/jair.953

    Article  Google Scholar 

  15. Lemaître G, Nogueira F, Aridas CK (2017) Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning. J Mach Learn Res 18(1):559–563

    Google Scholar 

  16. Breiman L (2001) Random forests. Mach Learn 45:5–32

    Article  Google Scholar 

  17. Gupta P, Garg S (2020) Breast cancer prediction using varying parameters of machine learning models. Procedia Comput Sci 171:593–601. https://doi.org/10.1016/j.procs.2020.04.064

    Article  Google Scholar 

  18. Ramaswamy S, Tamayo P, Rifkin R, Mukherjee S, Yeang C-H, Angelo M, Ladd C, Reich M, Latulippe E, Mesirov JP et al (2001) Multiclass cancer diagnosis using tumor gene expression signatures. Proc Natl Acad Sci 98(26):15149–15154. https://doi.org/10.1073/pnas.211566398

  19. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778. https://doi.org/10.1109/CVPR.2016.90

  20. Arik SÖ, Pfister T (2021) Tabnet: attentive interpretable tabular learning. In: Proceedings of the AAAI conference on artificial intelligence, vol 35, pp 6679–6687. https://doi.org/10.1609/aaai.v35i8.16826

  21. Quattrocchi CC, Errante Y, Gaudino C, Mallio CA, Giona A, Santini D, Tonini G, Zobel BB (2012) Spatial brain distribution of intra-axial metastatic lesions in breast and lung cancer patients. J Neuro-Oncol 110:79–87. https://doi.org/10.1007/s11060-012-0937-x

Download references

Funding

Partial funding through the USC Norris Comprehensive Cancer Center’s Multi-Level Cancer Risk Prediction Models pilot Project Award, ‘Molecular, Clinical and Neuro-imaging Determinants of Spatiotemporal Pathogenesis of Cancer-Specific Brain Metastases: Data Analysis and Longitudinal Modeling’ (12/01/2020-11/30/2021) is gratefully acknowledged.

Author information

Authors and Affiliations

  1. Department of Physics & Astronomy, University of Southern California, Los Angeles, CA, 90089, USA

    Saeedeh Mahmoodifar

  2. Department of Neurosurgery, Keck School of Medicine, University of Southern California, Los Angeles, CA, 90033, USA

    Dhiraj J. Pangal, Josh Neman & Gabriel Zada

  3. Catherine & Joseph Aresty Department of Urology, Institute of Urology, Keck School of Medicine, University of Southern California, Los Angeles, CA, 90033, USA

    Jeremy Mason

  4. Convergent Science Institute in Cancer, Michelson Center for Convergent Bioscience, University of Southern California, Los Angeles, CA, 90089, USA

    Jeremy Mason

  5. Department of Translational Genomics Keck School of Medicine, University of Southern California, Los Angeles, CA, 90033, USA

    Bodour Salhia

  6. Rose Ella Burkhardt Brain Tumor & Neuro-Oncology Center, Neurological Institute, The Cleveland Clinic, Cleveland, OH, 44195, USA

    Tehila Kaisman-Elbaz

  7. Department of Neurosurgery, Koc University School of Medicine, Istanbul, Turkey

    Selcuk Peker & Yavuz Samanci

  8. Department of Neurosurgery, Université de Sherbrooke, Centre de recherche du CHUS, QC, Canada

    Andréanne Hamel & David Mathieu

  9. Department of Neurosurgery, Postgraduate Institute of Medical Education and Research, Chandigarh, India

    Manjul Tripathi

  10. Department of Neurological Surgery, University of Virginia, Charlottesville, VA, 22903, USA

    Jason Sheehan, Stylianos Pikis & Georgios Mantziaris

  11. Department of Aerospace & Mechanical Engineering, Mathematics, Quantitative & Computational Biology, and Lawrence J. Ellison Institute for Transformative Medicine, University of Southern California, Los Angeles, CA, 90089, USA

    Paul K. Newton

Authors
  1. Saeedeh Mahmoodifar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dhiraj J. Pangal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Josh Neman
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Gabriel Zada
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jeremy Mason
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Bodour Salhia
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Tehila Kaisman-Elbaz
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Selcuk Peker
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Yavuz Samanci
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Andréanne Hamel
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. David Mathieu
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Manjul Tripathi
    View author publications

    You can also search for this author in PubMed Google Scholar

  13. Jason Sheehan
    View author publications

    You can also search for this author in PubMed Google Scholar

  14. Stylianos Pikis
    View author publications

    You can also search for this author in PubMed Google Scholar

  15. Georgios Mantziaris
    View author publications

    You can also search for this author in PubMed Google Scholar

  16. Paul K. Newton
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

S.M., D.P., J.M., and P.N. wrote the main manuscript text. D.P., B.S., J.N., and G.Z. provided and interpreted the data. S.M. and P.N. prepared figures and plots. T.K.E, S.P., Y.S., A.H., D.M., M.T., J.S., S.P., and G.M. collected the data. All authors reviewed the manuscript.

Corresponding author

Correspondence to Paul K. Newton.

Ethics declarations

Competing interests

The authors declare no competing interests.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file 1 (zip 6 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

Mahmoodifar, S., Pangal, D.J., Neman, J. et al. Comparative analysis of the spatial distribution of brain metastases across several primary cancers using machine learning and deep learning models. J Neurooncol (2024). https://doi.org/10.1007/s11060-024-04630-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11060-024-04630-5

Keywords

Search

Navigation