1. Biologically informed deep neural networks provide quantitative assessment of intratumoral heterogeneity in post treatment glioblastoma.
- Author
-
Wang, Hairong, Argenziano, Michael G., Yoon, Hyunsoo, Boyett, Deborah, Save, Akshay, Petridis, Petros, Savage, William, Jackson, Pamela, Hawkins-Daarud, Andrea, Tran, Nhan, Hu, Leland, Singleton, Kyle W., Paulson, Lisa, Dalahmah, Osama Al, Bruce, Jeffrey N., Grinband, Jack, Swanson, Kristin R., Canoll, Peter, and Li, Jing
- Subjects
GLIOMA treatment ,BIOPSY ,GLIOMAS ,PREDICTION models ,COMPUTER-assisted image analysis (Medicine) ,CANCER relapse ,ACADEMIC medical centers ,RESEARCH funding ,NEURONS ,CELL proliferation ,TREATMENT effectiveness ,CANCER patients ,MAGNETIC resonance imaging ,CELL cycle ,DESCRIPTIVE statistics ,GENE expression ,RNA ,IMMUNOHISTOCHEMISTRY ,LONGITUDINAL method ,ARTIFICIAL neural networks ,CYTOKINES ,NEURORADIOLOGY ,COMPARATIVE studies ,MACHINE learning ,INDIVIDUALIZED medicine ,INFLAMMATION ,SENSITIVITY & specificity (Statistics) ,HISTOLOGY ,MOLECULAR pathology ,SEQUENCE analysis ,IMMUNITY ,EVALUATION - Abstract
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. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF