Biologically informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post treatment glioblastoma
Intratumoral heterogeneity poses a significant challenge to the diagnosis and treatment of recurrent glioblastoma. This study addresses the need for non-invasive approaches to map heterogeneous landscape of histopathological alterations throughout the entire lesion for each patient. We developed BioNet, a biologically-informed neural network, to predict regional distributions of two primary tissue-specific gene modules: proliferating tumor (Pro) and reactive/inflammatory cells (Inf). BioNet significantly outperforms existing methods (p < 2e-26). In cross-validation, BioNet achieved AUCs of 0.80 (Pro) and 0.81 (Inf), with accuracies of 80% and 75%, respectively. In blind tests, BioNet achieved AUCs of 0.80 (Pro) and 0.76 (Inf), with accuracies of 81% and 74%. Competing methods had AUCs lower or around 0.6 and accuracies lower or around 70%. BioNet's voxel-level prediction maps reveal intratumoral heterogeneity, potentially improving biopsy targeting and treatment evaluation. This non-invasive approach facilitates regular monitoring and timely therapeutic adjustments, highlighting the role of ML in precision medicine.
Authors
- Deborah Boyett (ORCID: https://orcid.org/0000-0002-6795-5966)
- Kristin R. Swanson (ORCID: https://orcid.org/0000-0002-2464-6119)
- Hairong Wang (ORCID: https://orcid.org/0000-0003-3941-721X)
- Nhan L. Tran (ORCID: https://orcid.org/0000-0003-0908-9964)
- Kyle Singleton (ORCID: https://orcid.org/0000-0002-9969-8474)
- Akshay Save (ORCID: https://orcid.org/0000-0003-1739-423X)
- Lisa Paulson
- Petros Petridis (ORCID: https://orcid.org/0000-0001-7608-5723)
- Peter Canoll (ORCID: https://orcid.org/0000-0002-7001-0226)
- Andrea Hawkins‐Daarud (ORCID: https://orcid.org/0000-0002-6391-4155)
- Jeffrey N. Bruce (ORCID: https://orcid.org/0000-0002-6844-0286)
- Leland Hu (ORCID: https://orcid.org/0000-0001-9282-7619)
- William Savage (ORCID: https://orcid.org/0000-0001-6864-8485)
- Jack Grinband (ORCID: https://orcid.org/0000-0001-7658-6755)
- Osama Al‐Dalahmah (ORCID: https://orcid.org/0000-0002-3442-5459)
- Michael Argenziano (ORCID: https://orcid.org/0000-0003-3374-9037)
- Hyunsoo Yoon (ORCID: https://orcid.org/0000-0002-6371-7055)
- Pamela Jackson (ORCID: https://orcid.org/0000-0002-8424-4007)
- Jing Li (ORCID: https://orcid.org/0000-0001-7028-3681)
Institutions
- Georgia Institute of Technology (US)
- Yonsei University (KR)
- Columbia University Irving Medical Center (US)
- Mayo Clinic Hospital (US)
- Mayo Clinic in Florida (US)
- Neurological Surgery (US)
- New York University (US)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2024-10-19
- DOI
- https://doi.org/10.1038/s41746-024-01277-4
- Citations
- 3
- Primary Topic
- Glioma Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 1.31
Funders
- National Science Foundation
- National Institutes of Health
- National Cancer Institute
- National Institute of Neurological Disorders and Stroke