Overall survival time prediction for high-grade glioma patients based on large-scale brain functional networks

Abstract

High-grade glioma (HGG) is a lethal cancer with poor outcome. Accurate preoperative overall survival (OS) time prediction for HGG patients is crucial for treatment planning. Traditional presurgical and noninvasive OS prediction studies have used radiomics features at the local lesion area based on the magnetic resonance images (MRI). However, the highly complex lesion MRI appearance may have large individual variability, which could impede accurate individualized OS prediction. In this paper, we propose a novel concept, namely brain connectomics-based OS prediction. It is based on presurgical resting-state functional MRI (rs-fMRI) and the non-local, large-scale brain functional networks where the global and systemic prognostic features rather than the local lesion appearance are used to predict OS. We propose that the connectomics features could capture tumor-induced network-level alterations that are associated with prognosis. We construct both low-order (by means of sparse representation with regional rs-fMRI signals) and high-order functional connectivity (FC) networks (characterizing more complex multi-regional relationship by synchronized dynamics FC time courses). Then, we conduct a graph-theoretic analysis on both networks for a jointly, machine-learning-based individualized OS prediction. Based on a preliminary dataset (N = 34 with bad OS, mean OS, ~400 days; N = 34 with good OS, mean OS, ~1030 days), we achieve a promising OS prediction accuracy (86.8%) on separating the individuals with bad OS from those with good OS. However, if using only conventionally derived descriptive features (e.g., age and tumor characteristics), the accuracy is low (63.2%). Our study highlights the importance of the rs-fMRI and brain functional connectomics for treatment planning.

Brain Tumor Segmentation and Survival Prediction Using Multimodal MRI Scans With Deep Learning

“…Accurate and robust predictions of overall survival, using automated algorithms, for patients diagnosed with gliomas can provide valuable guidance for diagnosis, treatment planning, and outcome prediction (Liu et al, 2018). However, it is difficult to select reliable and potent prognostic features.…”

A Comparison Study of Machine Learning (Random Survival Forest) and Classic Statistic (Cox Proportional Hazards) for Predicting Progression in High-Grade Glioma after Proton and Carbon Ion Radiotherapy

“…Machine learning (ML), a branch of artificial intelligence, has been employed to predict prognosis in a variety of cancer types. Noticeably, series of studies applying ML algorithms to predict the survival of HGG under standard photon-based radiotherapy have reported good performance in recent years (8)(9)(10)(11)(12)(13). However, it is still controversial that which methods among ML algorithms and conventional modeling can achieve better performance in survival analysis, particularly in terms of time-to-event censored data (14)(15)(16).…”

A toolbox for brain network construction and classification (BrainNetClass)

“…Of note, for certain network construction methods (e.g., dHOFC and SSGSR), we fixed the feature extraction methods to keep consistent with the previous studies (Chen et al, ; Zhang, Zhang, et al, ). There are many other network properties, such as the shortest path length and betweenness centrality; they could also be jointly used as network features for better capturing the network topology in the future version (Liu et al, ).…”

“…Users may visualize the most important links or ROIs that may help to discover potential disease biomarkers. For dHOFC, a total of K matrices (each has a size of N × N ) will be generated to identify the important “high‐order” nodes (i.e., a cluster of synchronized dynamic FC links), as shown in (Liu et al, ).…”