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

Saeedeh Mahmoodifar; Dhiraj J Pangal; Josh Neman; Gabriel Zada; Jeremy Mason; Bodour Salhia; Tehila Kaisman-Elbaz; Selcuk Peker; Yavuz Samanci; Andréanne Hamel; David Mathieu; Manjul Tripathi; Jason Sheehan; Stylianos Pikis; Georgios Mantziaris; Paul K Newton

doi:10.1007/s11060-024-04630-5

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

J Neurooncol. 2024 Apr 2. doi: 10.1007/s11060-024-04630-5. Online ahead of print.

Authors

Saeedeh Mahmoodifar¹, Dhiraj J Pangal², Josh Neman², Gabriel Zada², Jeremy Mason^{3

4}, Bodour Salhia⁵, Tehila Kaisman-Elbaz⁶, Selcuk Peker⁷, Yavuz Samanci⁷, Andréanne Hamel⁸, David Mathieu⁸, Manjul Tripathi⁹, Jason Sheehan¹⁰, Stylianos Pikis¹⁰, Georgios Mantziaris¹⁰, Paul K Newton¹¹

Affiliations

¹ Department of Physics & Astronomy, University of Southern California, Los Angeles, CA, 90089, USA.
² Department of Neurosurgery, Keck School of Medicine, University of Southern California, Los Angeles, CA, 90033, USA.
³ Catherine & Joseph Aresty Department of Urology, Institute of Urology, Keck School of Medicine, University of Southern California, Los Angeles, CA, 90033, USA.
⁴ Convergent Science Institute in Cancer, Michelson Center for Convergent Bioscience, University of Southern California, Los Angeles, CA, 90089, USA.
⁵ Department of Translational Genomics Keck School of Medicine, University of Southern California, Los Angeles, CA, 90033, USA.
⁶ Rose Ella Burkhardt Brain Tumor & Neuro-Oncology Center, Neurological Institute, The Cleveland Clinic, Cleveland, OH, 44195, USA.
⁷ Department of Neurosurgery, Koc University School of Medicine, Istanbul, Turkey.
⁸ Department of Neurosurgery, Université de Sherbrooke, Centre de recherche du CHUS, QC, Canada.
⁹ Department of Neurosurgery, Postgraduate Institute of Medical Education and Research, Chandigarh, India.
¹⁰ Department of Neurological Surgery, University of Virginia, Charlottesville, VA, 22903, USA.
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. newton@usc.edu.

PMID: 38563856
DOI: 10.1007/s11060-024-04630-5

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.

Keywords: Brain metastases; Deep learning models; Pan cancer analysis; Principal components.

Grants and funding

USC Norris Comprehensive Cancer Center Pilot Award/NH/NIH HHS/United States