Outcome Prediction for Patient with High-Grade Gliomas from Brain Functional and Structural Networks

Abstract

High-grade glioma (HGG) is a lethal cancer, which is characterized by very poor prognosis. To help optimize treatment strategy, accurate preoperative prediction of HGG patient's outcome (i.e., survival time) is of great clinical value. However, there are huge individual variability of HGG, which produces a large variation in survival time, thus making prognostic prediction more challenging. Previous brain imaging-based outcome prediction studies relied only on the imaging intensity inside or slightly around the tumor, while ignoring any information that is located far away from the lesion (i.e., the “normal appearing” brain tissue). Notably, in addition to altering MR image intensity, we hypothesize that the HGG growth and its mass effect also change both structural (can be modeled by diffusion tensor imaging (DTI)) and functional brain connectivities (estimated by functional magnetic resonance imaging (rs-fMRI)). Therefore, integrating connectomics information in outcome prediction could improve prediction accuracy. To this end, we unprecedentedly devise a machine learning-based HGG prediction framework that can effectively extract valuable features from complex human brain connectome using network analysis tools, followed by a novel multi-stage feature selection strategy to single out good features while reducing feature redundancy. Ultimately, we use support vector machine (SVM) to classify HGG outcome as either bad (survival time ≤ 650 days) or good (survival time >650 days). Our method achieved 75 % prediction accuracy. We also found that functional and structural networks provide complementary information for the outcome prediction, thus leading to increased prediction accuracy compared with the baseline method, which only uses the basic clinical information (63.2 %).

Altered structural hub connectivity and its clinical relevance in glioma

“…2,[12][13][14] In newly diagnosed glioma, hub-related functional connectivity in the hemisphere contralateral to the tumor is increased, 7 possibly reflecting network failure in response to local dysfunction as an initially compensatory but long-term detrimental relaying of load. 10 Structural connectivity throughout macroscopically tumor-free brain regions also experimentally associates with molecular subtype 15 and prognosis, 16 indicating that connectivity measures may inform our understanding of performance status and survival beyond the currently known molecular determinants.…”

A sparse representation‐based radiomics for outcome prediction of higher grade gliomas

“…Recently, radiomics has achieved notable success in some clinical diagnostic and prognostic applications . By converting medical images into mineable high‐throughput features, radiomics provides a more comprehensive quantification of the entire tumor and subsequently makes an effective decision using these data.…”

Test-Retest Reliability of “High-Order” Functional Connectivity in Young Healthy Adults

“…This indicates that we can use dHOFC to further construct more complex brain functional networks with more information introduced. This HOFC method has been successfully applied to early MCI detection (Chen et al, 2016a ) and early AD detection (Chen et al, 2016b ), as well as prediction of overall survival time of patients with brain gliomas (Liu et al, 2016 ), all with significantly better accuracy than LOFC.…”