Multiparametric MRI along with machine learning predicts prognosis and treatment response in pediatric low-grade glioma
Anahita Fathi Kazerooni, Adam Kraya, Komal S. Rathi, Meen Chul Kim, Arastoo Vossough, Nastaran Khalili, Ariana Familiar, Deep Gandhi, Neda Khalili, Varun Kesherwani, Debanjan Haldar, Hannah Anderson, Run Jin, Aria Mahtabfar, Sina Bagheri, Yiran Guo, Qi Li, Xiaoyan Huang, Yuankun Zhu, Alex Sickler, Matthew R. Lueder, Saksham Phul, Mateusz Koptyra, Phillip B. Storm, Jeffrey B. Ware, Yuanquan Song, Christos Davatzikos, Jessica Foster, Sabine Mueller, Michael J. Fisher, Adam Resnick, Ali Nabavizadeh
Abstract
Pediatric low-grade gliomas (pLGGs) exhibit heterogeneous prognoses and variable responses to treatment, leading to tumor progression and adverse outcomes in cases where complete resection is unachievable. Early prediction of treatment responsiveness and suitability for immunotherapy has the potential to improve clinical management and outcomes. Here, we present a radiogenomic analysis of pLGGs, integrating MRI and RNA sequencing data. We identify three immunologically distinct clusters, with one group characterized by increased immune activity and poorer prognosis, indicating potential benefit from immunotherapies. We develop a radiomic signature that predicts these immune profiles with over 80% accuracy. Furthermore, our clinicoradiomic model predicts progression-free survival and correlates with treatment response. We also identify genetic variants and transcriptomic pathways associated with progression risk, highlighting links to tumor growth and immune response. This radiogenomic study in pLGGs provides a framework for the identification of high-risk patients who may benefit from targeted therapies. Understanding the molecular and pathological features of paediatric low-grade glioma (pLGG) is crucial to develop targeted therapies. Here, the authors perform a radiogenomic analysis of pLGGs combining treatment-naïve multiparametric MRI and RNA sequencing, enabling prognostication based on immune profiles as well as prediction of treatment response.