Functional and structural reorganization in brain tumors: a machine learning approach using desynchronized functional oscillations

• Published in: Communications biology 2024-04, Vol.7 (1), p.419-17, Article 419
• Main Authors: Falcó-Roget, Joan, Cacciola, Alberto, Sambataro, Fabio, Crimi, Alessandro
• Format: Article
• Language: English
• Subjects: 59; 59/36; 59/57; 631/378; 631/67/2321; 692/617/375/1345; Biomedical and Life Sciences; Brain - diagnostic imaging; Brain architecture; Brain cancer; Brain mapping; Brain Mapping - methods; Brain Neoplasms - diagnostic imaging; Brain tumors; Diffusion Tensor Imaging - methods; Edema; Humans; Learning algorithms; Life Sciences; Machine Learning; Magnetic resonance imaging; Neural networks; Neuroimaging; Oscillations; Structure-function relationships; Substantia alba; Synchronization; Tumors
• ISSN: 2399-3642; 2399-3642
• DOI: 10.1038/s42003-024-06119-3

Neuroimaging studies have allowed for non-invasive mapping of brain networks in brain tumors. Although tumor core and edema are easily identifiable using standard MRI acquisitions, imaging studies often neglect signals, structures, and functions within their presence. Therefore, both functional and diffusion signals, as well as their relationship with global patterns of connectivity reorganization, are poorly understood. Here, we explore the functional activity and the structure of white matter fibers considering the contribution of the whole tumor in a surgical context. First, we find intertwined alterations in the frequency domain of local and spatially distributed resting-state functional signals, potentially arising within the tumor. Second, we propose a fiber tracking pipeline capable of using anatomical information while still reconstructing bundles in tumoral and peritumoral tissue. Finally, using machine learning and healthy anatomical information, we predict structural rearrangement after surgery given the preoperative brain network. The generative model also disentangles complex patterns of connectivity reorganization for different types of tumors. Overall, we show the importance of carefully designing studies including MR signals within damaged brain tissues, as they exhibit and relate to non-trivial patterns of both structural and functional (dis-)connections or activity. A multimodal MRI study analyzes how signals within brain tumors shape the organization of brain networks and predict surgical outcomes with simple machine learning methods.